技术领域technical field
本申请涉及自动驾驶领域，尤其涉及一种自动驾驶方法和自动驾驶装置。The present application relates to the field of automatic driving, in particular to an automatic driving method and an automatic driving device.
背景技术Background technique
人工智能(Artificial Intelligence,AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，人工智能是计算机科学的一个分支，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式作出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is the branch of computer science that attempts to understand the nature of intelligence and produce a new class of intelligent machines that respond in ways similar to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
自动驾驶是人工智能领域的一种主流应用，自动驾驶技术依靠计算机视觉、雷达、监控装置和全球定位系统等协同合作，让机动车辆可以在不需要人类主动操作下，实现自动驾驶。自动驾驶的车辆使用各种计算系统来帮助将乘客从一个位置运输到另一位置。一些自动驾驶车辆可能要求来自操作者(诸如，领航员、驾驶员、或者乘客)的一些初始输入或者连续输入。自动驾驶车辆准许操作者从手动模操作式切换到自动驾驶模式或者介于两者之间的模式。由于自动驾驶技术无需人类来驾驶机动车辆，所以理论上能够有效避免人类的驾驶失误，减少交通事故的发生，且能够提高公路的运输效率。因此，自动驾驶技术越来越受到重视。Autonomous driving is a mainstream application in the field of artificial intelligence. Autonomous driving technology relies on the cooperation of computer vision, radar, monitoring devices and global positioning systems, so that motor vehicles can achieve automatic driving without the need for active human operation. Autonomous vehicles use various computing systems to help transport passengers from one location to another. Some autonomous vehicles may require some initial or continuous input from an operator, such as a navigator, driver, or passenger. An autonomous vehicle allows the operator to switch from a manual mode of operation to an automated driving mode or something in between. Since autonomous driving technology does not require humans to drive motor vehicles, it can theoretically effectively avoid human driving errors, reduce traffic accidents, and improve road transportation efficiency. Therefore, autonomous driving technology is getting more and more attention.
目前，自动驾驶车辆在自动驾驶模式下根据采集的路况信息以及导航信息，按照预置的驾驶规则执行驾驶操作。然而，自动驾驶车辆在自动驾驶模式下执行的驾驶操作对于乘客来说往往不是最佳的。如何优化自动驾驶车辆在自动驾驶模式下执行的驾驶操作以更好地满足乘客的驾驶习惯是需要解决的问题。At present, in the automatic driving mode, the self-driving vehicle performs driving operations according to the preset driving rules according to the collected road condition information and navigation information. However, the driving maneuvers performed by autonomous vehicles in autonomous mode are often not optimal for the passengers. How to optimize the driving operations performed by autonomous vehicles in autonomous driving mode to better meet the driving habits of passengers is a problem that needs to be solved.
发明内容Contents of the invention
本申请实施例公开了一种自动驾驶方法和自动驾驶装置，可以优化自动驾驶车辆在自动驾驶模式下执行的驾驶操作，进而更好地满足用户的驾驶习惯。The embodiment of the present application discloses an automatic driving method and an automatic driving device, which can optimize the driving operation performed by the automatic driving vehicle in the automatic driving mode, so as to better meet the driving habits of the user.
第一方面，本申请实施例提供了一种自动驾驶方法，该方法可包括：自动驾驶装置获取当前路况信息；根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数；若存在，则获取该目标驾驶控制参数，并根据该目标驾驶控制参数以目标驾驶风格进行驾驶；该目标驾驶控制参数包括目标车辆的历史驾驶控制参数，该历史驾驶控制参数包括该目标车辆按照该目标驾驶风格进行驾驶得到的驾驶控制参数；若不存在，则根据实时驾驶控制参数以当前驾驶风格进行驾驶；该实时驾驶控制参数为该自动驾驶装置按照预设决策机制决策出的驾驶控制参数。In the first aspect, the embodiment of the present application provides an automatic driving method, which may include: the automatic driving device acquires current road condition information; according to the current road condition information, query whether there is a target matching the current road condition information from the database A driving control parameter; if it exists, the target driving control parameter is obtained, and the target driving control parameter is used to drive according to the target driving style; the target driving control parameter includes the historical driving control parameters of the target vehicle, and the historical driving control parameters include the The driving control parameters obtained by driving the target vehicle according to the target driving style; if it does not exist, then driving with the current driving style according to the real-time driving control parameters; the real-time driving control parameters are determined by the automatic driving device according to the preset decision-making mechanism driving control parameters.
该目标车辆的历史驾驶控制参数可以是驾驶员在手动模式下驾驶该目标车辆得到的历史驾驶参数。该目标车辆可以是该自动驾驶装置，也可以不是该自动驾驶装置。可选的，该目标车辆的历史驾驶控制参数可以是由参考驾驶控制参数转换的，且可作为该自动驾驶装置的历史驾驶控制参数。该参考驾驶控制参数为驾驶员在手动模式下驾驶该目标车辆得到的历史驾驶参数。应理解，若目标车辆的历史驾驶控制参数不能直接作为自动驾驶装置的历史驾驶控制参数，则自动驾驶装置可将该目标车辆的历史驾驶控制参数转换为该自动驾驶装置的历史驾驶控制参数。在实际应用，若自动驾驶装置和目标车辆使用相同的驾驶控制参数实现的驾驶操作存在区别，即该自动驾驶装置不能直接使用目标车辆的驾驶控制参数，则该自动驾驶装置可将该目标车辆的历史驾驶控制参数转换为该自动驾驶装置的历史驾驶控制参数。The historical driving control parameters of the target vehicle may be historical driving parameters obtained by the driver driving the target vehicle in manual mode. The target vehicle may or may not be the automatic driving device. Optionally, the historical driving control parameters of the target vehicle may be converted from reference driving control parameters, and may be used as historical driving control parameters of the automatic driving device. The reference driving control parameters are historical driving parameters obtained by the driver driving the target vehicle in manual mode. It should be understood that if the historical driving control parameters of the target vehicle cannot be directly used as the historical driving control parameters of the automatic driving device, the automatic driving device may convert the historical driving control parameters of the target vehicle into the historical driving control parameters of the automatic driving device. In practical applications, if the driving operation of the automatic driving device and the target vehicle using the same driving control parameters is different, that is, the automatic driving device cannot directly use the driving control parameters of the target vehicle, the automatic driving device can use the target vehicle's driving control parameters The historical driving control parameters are converted into historical driving control parameters of the automatic driving device.
本申请实施例中，自动驾驶装置在查询到与当前路况相匹配的目标驾驶控制参数后，按照该目标驾驶控制参数进行驾驶，在未查询该目标驾驶控制参数时按照其当前决策出的驾驶控制参数进行驾驶；使得该自动驾驶装置能够利用乘客以往的历史驾驶控制参数对其当前决策出的驾驶操作进行优化。由于目标驾驶控制参数是符合乘客的驾驶习惯的历史驾驶控制参数，使用这些历史驾驶控制参数对该自动驾驶装置的驾驶操作进行优化，可以更好的满足乘客的驾驶习惯。In the embodiment of the present application, after the automatic driving device inquires the target driving control parameters matching the current road conditions, it drives according to the target driving control parameters; parameters; so that the automatic driving device can use the past historical driving control parameters of the passengers to optimize the driving operation currently decided by them. Since the target driving control parameters are historical driving control parameters that conform to the driving habits of the passengers, using these historical driving control parameters to optimize the driving operation of the automatic driving device can better meet the driving habits of the passengers.
在一个可选的实现方式中，在获取目标驾驶控制参数之前，该方法还包括：确定第一驾驶行为，该第一驾驶行为是该自动驾驶装置按照该预设决策机制决策出的驾驶行为；确定该数据库中与该当前路况信息相匹配的第二驾驶行为，该数据库中的驾驶行为包括该目标车辆按照该目标驾驶风格进行驾驶的历史驾驶行为；判断该第一驾驶行为与该第二驾驶行为是否相同，若相同，则执行该获取该目标驾驶控制参数的步骤。In an optional implementation manner, before acquiring the target driving control parameters, the method further includes: determining a first driving behavior, where the first driving behavior is a driving behavior determined by the automatic driving device according to the preset decision-making mechanism; Determining the second driving behavior in the database that matches the current road condition information, the driving behavior in the database includes the historical driving behavior of the target vehicle driving according to the target driving style; judging the relationship between the first driving behavior and the second driving behavior Whether the behaviors are the same, if they are the same, execute the step of obtaining the target driving control parameter.
与当前路况信息相匹配的历史驾驶行为可以为与当前路况信息相匹配的驾驶控制参数对应的驾驶行为。可以理解，如果当前路况信息匹配的历史驾驶行为与当前确定的在当前路况信息下待执行的驾驶行为不同，那么与当前路况信息相匹配的驾驶控制参数对应的驾驶行为也与当前确定的在当前路况信息下待执行的驾驶行为不同。这样若按照与当前路况信息相匹配的驾驶控制参数进行驾驶，很可能不符合安全驾驶标准或者交通法规。在该实现方式中，在当前路况信息匹配的历史驾驶行为与当前确定的在当前路况下待执行的驾驶行为相同的情况下，获取与该当前路况相匹配的驾驶控制参数；可以有效避免自动驾驶装置执行的驾驶行为不符合安全驾驶标准或交规。The historical driving behavior matching the current road condition information may be the driving behavior corresponding to the driving control parameter matching the current road condition information. It can be understood that if the historical driving behavior matched by the current road condition information is different from the currently determined driving behavior under the current road condition information, then the driving behavior corresponding to the driving control parameters matched with the current road condition information is also different from the currently determined driving behavior under the current road condition information. The driving behavior to be executed under the road condition information is different. In this way, if the vehicle is driven according to the driving control parameters that match the current road condition information, it may not comply with safe driving standards or traffic regulations. In this implementation, when the historical driving behavior matched by the current road condition information is the same as the currently determined driving behavior to be executed under the current road condition, the driving control parameters matching the current road condition are obtained; automatic driving can be effectively avoided The driving behavior performed by the device does not comply with safe driving standards or traffic regulations.
在一个可选的实现方式中，确定驾驶风格数据库中与该当前路况相匹配的第二驾驶行为包括：在该驾驶风格数据库中包括与该当前路况信息相匹配的目标路况信息的情况下，确定该驾驶风格数据库中该目标路况信息对应的驾驶行为为该第二驾驶行为；该驾驶风格数据库包括至少一项历史路况信息，以及该至少一项历史路况信息与驾驶行为的对应关系，，该历史路况信息包括该目标路况信息。In an optional implementation manner, determining the second driving behavior in the driving style database that matches the current road condition includes: if the driving style database includes target road condition information that matches the current road condition information, determine The driving behavior corresponding to the target road condition information in the driving style database is the second driving behavior; the driving style database includes at least one piece of historical road condition information, and the corresponding relationship between the at least one piece of historical road condition information and driving behavior, the history The traffic condition information includes the target traffic condition information.
在该实现方式中，可以准确、快速地确定与当前路况相匹配的第二驾驶行为。In this implementation manner, the second driving behavior matching the current road condition can be accurately and quickly determined.
在一个可选的实现方式中，在根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数之前，该方法还包括：获得驾驶数据文件；判断该驾驶数据文件是否包括该目标车辆按照该目标驾驶风格进行驾驶的历史路况信息、历史驾驶控制参数以及历史驾驶行为中的至少一项，若是，则执行该根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数的步骤。In an optional implementation manner, before querying from the database whether there is a target driving control parameter matching the current road condition information according to the current road condition information, the method further includes: obtaining a driving data file; Whether the file includes at least one of the historical road condition information, historical driving control parameters, and historical driving behavior of the target vehicle driving according to the target driving style; The step of matching the current road condition information with the target driving control parameters.
自动驾驶装置在获得该驾驶数据文件之前，仅能根据实时驾驶控制参数进行驾驶；在获得该驾驶数据文件之后，可以利用该驾驶数据文件包括的历史路况信息、历史驾驶控制参数以及历史驾驶行为按照目标驾驶风格进行驾驶。在该实现方式中，在获得驾驶数据文件之后，确定按照该目标驾驶风格进行驾驶；可以保证在按照目标驾驶风格进行驾驶之前已得到按照目标驾驶风格进行驾驶所需的历史驾驶数据，安全性高。Before obtaining the driving data file, the automatic driving device can only drive according to real-time driving control parameters; after obtaining the driving data file, it can use the historical road condition information, historical driving control parameters and historical driving behavior included in the driving data file to Drive with the target driving style. In this implementation, after the driving data file is obtained, it is determined to drive according to the target driving style; it can be guaranteed that the historical driving data required for driving according to the target driving style has been obtained before driving according to the target driving style, and the safety is high .
在一个可选的实现方式中，获得驾驶数据文件包括：接收来自第一终端的该驾驶数据文件；或者，在接收到来自第二终端的第一指令后，从服务器获取该驾驶数据文件；该第一指令用于指示该自动驾驶装置从该服务器获取该驾驶数据文件。In an optional implementation manner, obtaining the driving data file includes: receiving the driving data file from the first terminal; or, after receiving the first instruction from the second terminal, obtaining the driving data file from the server; the The first instruction is used to instruct the automatic driving device to obtain the driving data file from the server.
在该实现方式中，自动驾驶装置可以通过多种方式快速地获取驾驶数据文件，以便于满足不同用户的需求。In this implementation manner, the automatic driving device can quickly obtain driving data files in various ways, so as to meet the needs of different users.
在一个可选的实现方式中，确定按照目标驾驶风格进行驾驶包括：在接收到用户输入的第三指令或者来自第三终端的第四指令的情况下，确定按照该目标驾驶风格进行驾驶；该第三指令和该第四指令均用于指示该自动驾驶装置按照该目标驾驶风格进行驾驶。该自动驾驶装置存储有该历史驾驶控制参数。In an optional implementation manner, determining to drive according to the target driving style includes: determining to drive according to the target driving style when receiving a third instruction input by a user or a fourth instruction from a third terminal; Both the third instruction and the fourth instruction are used to instruct the automatic driving device to drive according to the target driving style. The automatic driving device stores the historical driving control parameters.
在该实现方式中，用户可以快速、方便地指示自动驾驶装置按照目标驾驶风格进行驾驶，用户体验好。In this implementation manner, the user can quickly and conveniently instruct the automatic driving device to drive according to the target driving style, and the user experience is good.
在一个可选的实现方式中，根据该目标驾驶控制参数以目标驾驶风格进行驾驶包括：在该目标驾驶控制参数符合安全驾驶标准和交规的情况下，根据该目标驾驶控制参数进行驾驶。In an optional implementation manner, driving with a target driving style according to the target driving control parameter includes: driving according to the target driving control parameter when the target driving control parameter complies with safe driving standards and traffic regulations.
在该实现方式中，可以有效保证自动驾驶装置按照目标驾驶控制参数进行驾驶，能够符合安全驾驶标准和交规。In this implementation manner, it can effectively ensure that the automatic driving device drives according to the target driving control parameters, and can comply with safe driving standards and traffic regulations.
在一个可选的实现方式中，在获取目标驾驶控制参数之后，该方法还包括：在该目标驾驶控制参数不符合安全驾驶标准或者交规的情况下，按照实时驾驶控制参数进行驾驶，该实时驾驶参数为该自动驾驶装置当前决策出的驾驶控制参数。In an optional implementation, after acquiring the target driving control parameter, the method further includes: driving according to the real-time driving control parameter when the target driving control parameter does not meet the safe driving standard or traffic regulations, the real-time driving The parameter is a driving control parameter currently determined by the automatic driving device.
自动驾驶装置按照实时驾驶控制参数进行驾驶必定符合安全驾驶标准和交规。在该实现方式中，可以保证自动驾驶装置的驾驶行为均符合安全驾驶标准和交规。The driving of the automatic driving device according to the real-time driving control parameters must meet the safe driving standards and traffic regulations. In this implementation manner, it can be ensured that the driving behavior of the automatic driving device complies with safe driving standards and traffic regulations.
在一个可选的实现方式中，该驾驶数据文件为将该历史驾驶行为、该历史路况信息以及该历史驾驶控制参数作为一个整体存储在数据库中，该历史路况信息和该历史驾驶控制参数分别为该目标车辆在驾驶员手动驾驶的过程中采集的路况信息以及驾驶控制参数，该历史路况信息与该历史驾驶控制参数在时间维度相对应，该历史驾驶行为是该目标车辆根据该历史路况信息和该历史驾驶控制参数确定的驾驶行为。In an optional implementation, the driving data file is to store the historical driving behavior, the historical road condition information and the historical driving control parameters in a database as a whole, and the historical road condition information and the historical driving control parameters are respectively The road condition information and driving control parameters collected by the target vehicle during manual driving by the driver, the historical road condition information corresponds to the historical driving control parameters in the time dimension, and the historical driving behavior is obtained by the target vehicle according to the historical road condition information and The driving behavior determined by the historical driving control parameters.
在该实现方式中，根据历史路况信息和历史驾驶控制参数确定历史驾驶行为，进而将历史驾驶行为、历史路况信息以及历史驾驶控制参数作为一个整体存储以得到驾驶数据文件；可以高效的生成包含一个用户驾驶风格的驾驶数据文件。In this implementation, the historical driving behavior is determined according to the historical road condition information and historical driving control parameters, and then the historical driving behavior, historical road condition information and historical driving control parameters are stored as a whole to obtain a driving data file; it is possible to efficiently generate a file containing a A driving data file of the user's driving style.
第二方面，本申请实施例提供了一种自动驾驶装置，该自动驾驶装置可包括：传感器、存储器以及处理器；该传感器用于采集当前路况信息；该存储器用于存储代码；该处理器通过读取该存储器中存储的该代码以用于执行如下操作：根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数；若存在，则获取该目标驾驶控制参数，并根据该目标驾驶控制参数以目标驾驶风格进行驾驶；该目标驾驶控制参数包括目标车辆的历史驾驶控制参数，该历史驾驶控制参数包括该目标车辆按照该目标驾驶风格进行驾驶得到的驾驶控制参数；若不存在，则根据实时驾驶控制参数以当前驾驶风格进行驾驶；该实时驾驶控制参数为该自动驾驶装置按照预设决策机制决策出的驾驶控制参数。In a second aspect, an embodiment of the present application provides an automatic driving device, which may include: a sensor, a memory, and a processor; the sensor is used to collect current road condition information; the memory is used to store codes; Reading the code stored in the memory is used to perform the following operations: according to the current road condition information, query whether there is a target driving control parameter matching the current road condition information from the database; if so, obtain the target driving control parameter parameters, and drive with the target driving style according to the target driving control parameters; the target driving control parameters include the historical driving control parameters of the target vehicle, and the historical driving control parameters include the driving control obtained by driving the target vehicle according to the target driving style parameter; if it does not exist, then drive with the current driving style according to the real-time driving control parameter; the real-time driving control parameter is the driving control parameter determined by the automatic driving device according to the preset decision-making mechanism.
在一个可选的实现方式中，处理器，还用于确定第一驾驶行为，该第一驾驶行为是该自动驾驶装置按照该预设决策机制决策出的驾驶行为；确定该数据库中与该当前路况信息相匹配的第二驾驶行为，该数据库中的驾驶行为包括该目标车辆按照该目标驾驶风格进行驾驶的历史驾驶行为；判断该第一驾驶行为与该第二驾驶行为是否相同，若相同，则执行该获取该目标驾驶控制参数的步骤。In an optional implementation manner, the processor is further configured to determine a first driving behavior, where the first driving behavior is a driving behavior determined by the automatic driving device according to the preset decision-making mechanism; The second driving behavior that matches the road condition information, the driving behavior in the database includes the historical driving behavior of the target vehicle driving according to the target driving style; determine whether the first driving behavior is the same as the second driving behavior, and if they are the same, Then execute the step of obtaining the target driving control parameter.
在一个可选的实现方式中，处理器，具体用于在该数据库中包括与该当前路况信息相匹配的目标路况信息的情况下，确定该数据库中该目标路况信息对应的驾驶行为为该第二驾驶行为；该数据库包括至少一项历史路况信息，以及该至少一项历史路况信息与驾驶行为的对应关系，该历史路况信息包括该目标路况信息。In an optional implementation manner, the processor is specifically configured to determine that the driving behavior corresponding to the target road condition information in the database is the first driving behavior when the database includes target road condition information matching the current road condition information. 2. Driving behavior: the database includes at least one piece of historical road condition information, and the corresponding relationship between the at least one piece of historical road condition information and driving behavior, and the historical road condition information includes the target road condition information.
在一个可选的实现方式中，该装置还包括：通信接口，用于获取或接收驾驶数据文件；In an optional implementation manner, the device further includes: a communication interface, configured to obtain or receive a driving data file;
处理器，还用于判断该驾驶数据文件是否包括该目标车辆按照该目标驾驶风格进行驾驶的历史路况信息、历史驾驶控制参数以及历史驾驶行为中的至少一项，若是，则执行该根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数的步骤。The processor is also used to judge whether the driving data file includes at least one of historical road condition information, historical driving control parameters and historical driving behavior of the target vehicle driven according to the target driving style, and if so, execute the The road condition information is a step of querying from the database whether there is a target driving control parameter matching the current road condition information.
在一个可选的实现方式中，通信接口，具体用于接收来自第一终端的该驾驶数据文件；或者，该通信接口，具体用于在接收到来自第二终端的第一指令后，从服务器获取该驾驶数据文件；该第一指令用于指示该自动驾驶装置从该服务器获取该驾驶数据文件。In an optional implementation manner, the communication interface is specifically used for receiving the driving data file from the first terminal; or, the communication interface is specifically used for receiving the first instruction from the second terminal, from the server Obtain the driving data file; the first instruction is used to instruct the automatic driving device to obtain the driving data file from the server.
在一个可选的实现方式中，该装置还包括：通信接口，用于接收用户输入的第三指令或者来自第三终端的第四指令；该处理器，具体用于在该接收单元接收到该第三指令或者该第四指令的情况下，确定按照该目标驾驶风格进行驾驶；该第三指令和该第四指令均用于指示该自动驾驶装置按照该目标驾驶风格进行驾驶。In an optional implementation manner, the device further includes: a communication interface, configured to receive a third instruction input by a user or a fourth instruction from a third terminal; the processor is specifically configured to receive the instruction at the receiving unit. In the case of the third instruction or the fourth instruction, it is determined to drive according to the target driving style; both the third instruction and the fourth instruction are used to instruct the automatic driving device to drive according to the target driving style.
在一个可选的实现方式中，该处理器，具体用于在该目标驾驶控制参数符合安全驾驶标准和交规的情况下，控制该自动驾驶装置根据该目标驾驶控制参数进行驾驶。In an optional implementation manner, the processor is specifically configured to control the automatic driving device to drive according to the target driving control parameter when the target driving control parameter complies with safe driving standards and traffic regulations.
在一个可选的实现方式中，该处理器，还用于在该目标驾驶控制参数不符合安全驾驶标准或者交规的情况下，控制该自动驾驶装置根据实时驾驶控制参数进行驾驶；该实时驾驶控制参数为该自动驾驶装置当前决策出的驾驶控制参数。In an optional implementation, the processor is also used to control the automatic driving device to drive according to the real-time driving control parameters when the target driving control parameters do not meet the safe driving standards or traffic regulations; the real-time driving control The parameter is a driving control parameter currently determined by the automatic driving device.
在一个可选的实现方式中，该驾驶数据文件为将该历史驾驶行为、该历史路况信息以及该历史驾驶控制参数作为一个整体存储在该数据库中，该历史路况信息和该历史驾驶控制参数分别为该目标车辆在驾驶员手动驾驶的过程中采集的路况信息以及驾驶控制参数，该历史路况信息与该历史驾驶控制参数在时间维度相对应，该历史驾驶行为是该目标车辆根据该历史路况信息和该历史驾驶控制参数确定的驾驶行为。In an optional implementation, the driving data file is to store the historical driving behavior, the historical road condition information and the historical driving control parameters in the database as a whole, and the historical road condition information and the historical driving control parameters are respectively The road condition information and driving control parameters collected by the target vehicle during manual driving by the driver, the historical road condition information corresponds to the historical driving control parameters in the time dimension, and the historical driving behavior is the target vehicle according to the historical road condition information and the driving behavior determined by the historical driving control parameters.
第三方面，本申请实施例提供了一种计算机可读存储介质，该计算机存储介质存储有计算机程序，该计算机程序包括程序指令，该程序指令当被处理器执行时使该处理器执行上述第一方面以及任一种可选的实现方式的方法。In a third aspect, an embodiment of the present application provides a computer-readable storage medium, the computer storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the above-mentioned A method in one aspect and any optional implementation manner.
第四方面，本申请实施例提供了一种计算机程序产品，该计算机程序产品包括程序指令，该程序指令当被处理器执行时使该信处理器执行上述第一方面以及任一种可选的实现方式的方法。In a fourth aspect, an embodiment of the present application provides a computer program product, the computer program product includes program instructions, and when the program instructions are executed by a processor, the information processor executes the above first aspect and any optional method of implementation.
附图说明Description of drawings
为了更清楚地说明本申请实施例或背景技术中的技术方案，下面将对本申请实施例或背景技术中所需要使用的附图进行说明。In order to more clearly illustrate the technical solutions in the embodiment of the present application or the background art, the following will describe the drawings that need to be used in the embodiment of the present application or the background art.
图1是本申请实施例提供的自动驾驶装置100的功能框图；FIG. 1 is a functional block diagram of an automatic driving device 100 provided by an embodiment of the present application;
图2为本申请实施例提供的一种自动驾驶系统的结构示意图；FIG. 2 is a schematic structural diagram of an automatic driving system provided in an embodiment of the present application;
图3为本申请实施例提供的一种自动驾驶方法流程图；FIG. 3 is a flow chart of an automatic driving method provided in an embodiment of the present application;
图4为本申请实施例提供的一种路况匹配和驾驶行为匹配的示意图；FIG. 4 is a schematic diagram of road condition matching and driving behavior matching provided by an embodiment of the present application;
图5为本申请实施例提供的另一种自动驾驶方法流程图；FIG. 5 is a flow chart of another automatic driving method provided by the embodiment of the present application;
图6为本申请实施例提供的一种驾驶数据文件生成方法流程图；FIG. 6 is a flow chart of a method for generating a driving data file provided in an embodiment of the present application;
图7为本申请实施例提供的一种通过神经网络学习得到驾驶行为的示意图；FIG. 7 is a schematic diagram of driving behavior obtained through neural network learning provided by an embodiment of the present application;
图8为本申请实施例提供的另一种通过神经网络学习得到驾驶行为的示意图；Fig. 8 is a schematic diagram of another driving behavior obtained through neural network learning provided by the embodiment of the present application;
图9为本申请实施例提供的一种自动驾驶装置的结构示意图；FIG. 9 is a schematic structural diagram of an automatic driving device provided in an embodiment of the present application;
图10为本申请实施例提供的一种驾驶数据文件生成装置的结构示意图；FIG. 10 is a schematic structural diagram of a device for generating driving data files provided by an embodiment of the present application;
图11为本申请实施例提供的一种计算机程序产品的结构示意图。FIG. 11 is a schematic structural diagram of a computer program product provided by an embodiment of the present application.
具体实施方式Detailed ways
为了使本技术领域的人员更好地理解本申请实施例方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。In order to enable those skilled in the art to better understand the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only It is an embodiment of a part of the application, but not all of the embodiments.
本申请的说明书实施例和权利要求书及上述附图中的术语“第一”、“第二”、和“第三”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元。方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", and "third" in the description, embodiments and claims of the present application and the above drawings are used to distinguish similar objects, but not necessarily to describe a specific order or priority. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, of a sequence of steps or elements. A method, system, product or device is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to the process, method, product or device.
在主流的自动驾驶研究机构和厂商中，自动驾驶系统中的控制模块(motionplanner)用于输出车辆的速度和角度。而上游的决策模块(behavior planner)的输出作为控制模块的输入，上游任务模块(mission planner)的输出作为决策模块的输入。每一层模块都会接收感知系统(perception system)的输出作为输入。各模块根据上游模块的输出和感知模块的输入，独立计算输出。各模块不会向上游模块反馈自己的输出，整个自动驾驶系统自上而下，呈流水线式。此种形式的自动驾驶系统中所有模块的输出在相同输入下几乎全部为固定值，出现偏差的概率接近于零。也就是说，自动驾驶车辆在自动驾驶模式下按照预置的驾驶规则(即默认驾驶风格)执行驾驶操作。自动驾驶车辆按照默认风格驾驶进行驾驶时，在保障安全性的同时也彻底丢弃了乘车人对舒适度的需求，也不能进一步优化其在自动驾驶模式下执行的驾驶操作。因此，如何优化自动驾驶车辆在自动驾驶模式下执行的驾驶操作以满足不同用户的需求是目前需要解决的问题。本申请实施例提供的自动驾驶方法可以应用到自动驾驶场景。下面对自动驾驶场景进行简单的介绍。In mainstream autonomous driving research institutions and manufacturers, the control module (motionplanner) in the autonomous driving system is used to output the speed and angle of the vehicle. The output of the upstream decision-making module (behavior planner) is used as the input of the control module, and the output of the upstream task module (mission planner) is used as the input of the decision-making module. Each layer module receives the output of the perception system as input. Each module independently calculates the output based on the output of the upstream module and the input of the perception module. Each module will not feed back its own output to the upstream module, and the entire automatic driving system is pipelined from top to bottom. The outputs of all modules in this form of automatic driving system are almost all fixed values under the same input, and the probability of deviation is close to zero. That is to say, the self-driving vehicle performs driving operations according to the preset driving rules (ie, the default driving style) in the self-driving mode. When the self-driving vehicle drives according to the default style, it completely discards the occupant's demand for comfort while ensuring safety, and cannot further optimize the driving operation performed in the self-driving mode. Therefore, how to optimize the driving operation performed by the autonomous vehicle in the autonomous driving mode to meet the needs of different users is a problem that needs to be solved at present. The automatic driving method provided in the embodiment of the present application can be applied to automatic driving scenarios. The following is a brief introduction to the autonomous driving scenario.
自动驾驶场景1：自动驾驶装置(例如自动驾驶汽车)在接收到用户输入或用户发送的指示该自动驾驶装置按照某种驾驶风格进行驾驶的指令后，按照该驾驶风格进行驾驶。Autonomous driving scenario 1: After an automatic driving device (such as a self-driving car) receives a user input or an instruction sent by the user instructing the automatic driving device to drive according to a certain driving style, it drives according to the driving style.
自动驾驶场景2：用户利用手机或者其他便携设备将驾驶数据文件导入至自动驾驶装置，该自动驾驶装置上运行的自动驾驶系统结合该驾驶数据文件中的历史驾驶数据对驾驶操作进一步优化，进而改善该用户的乘车体验。Autonomous driving scenario 2: The user uses a mobile phone or other portable device to import the driving data file to the automatic driving device, and the automatic driving system running on the automatic driving device further optimizes the driving operation by combining the historical driving data in the driving data file, thereby improving The user's ride experience.
自动驾驶场景3：用户通过终端(例如手机)向自动驾驶装置发送指令，该自动驾驶装置根据该指令从云服务器获取驾驶数据文件，该自动驾驶装置上运行的自动驾驶系统结合该驾驶数据文件中的历史驾驶数据对驾驶操作进一步优化，进而改善该用户的乘车体验。Autonomous driving scenario 3: The user sends an instruction to the automatic driving device through a terminal (such as a mobile phone), and the automatic driving device obtains the driving data file from the cloud server according to the instruction, and the automatic driving system running on the automatic driving device combines the driving data file The historical driving data further optimizes the driving operation, thereby improving the user's ride experience.
图1是本申请实施例提供的自动驾驶装置100的功能框图。在一个实施例中，将自动驾驶装置100配置为完全或部分地自动驾驶模式。例如，自动驾驶装置100可以在处于部分自动驾驶模式中的同时控制自身，并且可通过人为操作来确定自动驾驶装置100及其周边环境的当前状态，确定周边环境中的至少一个其他车辆的可能行为，并确定该其他车辆执行可能行为的可能性相对应的置信水平，基于所确定的信息来控制自动驾驶装置100。在自动驾驶装置100处于自动驾驶模式中时，可以将自动驾驶装置100置为在没有和人交互的情况下操作。在一个实施例中，将自动驾驶装置100配置手动驾驶模式。在自动驾驶装置100处于手动驾驶模式中时，可以将自动驾驶装置100置为在人的控制下进行行驶。Fig. 1 is a functional block diagram of an automatic driving device 100 provided by an embodiment of the present application. In one embodiment, the automatic driving device 100 is configured in a fully or partially automatic driving mode. For example, the automatic driving device 100 can control itself while being in a partial automatic driving mode, and can determine the current state of the automatic driving device 100 and its surrounding environment through human operation, and determine the possible behavior of at least one other vehicle in the surrounding environment , and determine a confidence level corresponding to the possibility of the other vehicle performing a possible behavior, and control the automatic driving device 100 based on the determined information. When the automatic driving device 100 is in the automatic driving mode, the automatic driving device 100 may be set to operate without human interaction. In one embodiment, the automatic driving device 100 is configured in a manual driving mode. When the automatic driving device 100 is in the manual driving mode, the automatic driving device 100 can be set to drive under the control of a human.
自动驾驶装置100可包括各种子系统，例如行进系统102、传感器系统104、控制系统106、一个或多个外围设备108以及电源110、计算机系统112和用户接口116。可选地，自动驾驶装置100可包括更多或更少的子系统，并且每个子系统可包括多个元件。另外，自动驾驶装置100的每个子系统和元件可以通过有线或者无线互连。Autonomous driving device 100 may include various subsystems such as travel system 102 , sensor system 104 , control system 106 , one or more peripheral devices 108 as well as power supply 110 , computer system 112 and user interface 116 . Optionally, the automatic driving device 100 may include more or fewer subsystems, and each subsystem may include multiple elements. In addition, each subsystem and component of the automatic driving device 100 may be interconnected by wire or wirelessly.
行进系统102可包括为自动驾驶装置100提供动力运动的组件。在一个实施例中，推进系统102可包括引擎118、能量源119、传动装置120和车轮/轮胎121。引擎118可以是内燃引擎、电动机、空气压缩引擎或其他类型的引擎组合，例如汽油发动机和电动机组成的混动引擎，内燃引擎和空气压缩引擎组成的混动引擎。引擎118将能量源119转换成机械能量。Propulsion system 102 may include components that provide powered motion for automated driving device 100 . In one embodiment, propulsion system 102 may include engine 118 , energy source 119 , transmission 120 , and wheels/tyres 121 . The engine 118 may be an internal combustion engine, an electric motor, an air compression engine or other types of engine combinations, such as a hybrid engine composed of a gasoline engine and an electric motor, or a hybrid engine composed of an internal combustion engine and an air compression engine. Engine 118 converts energy source 119 into mechanical energy.
能量源119的示例包括汽油、柴油、其他基于石油的燃料、丙烷、其他基于压缩气体的燃料、乙醇、太阳能电池板、电池和其他电力来源。能量源119也可以为自动驾驶装置100的其他系统提供能量。Examples of energy source 119 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electrical power. The energy source 119 can also provide energy for other systems of the automatic driving device 100 .
传动装置120可以将来自引擎118的机械动力传送到车轮121。传动装置120可包括变速箱、差速器和驱动轴。在一个实施例中，传动装置120还可以包括其他器件，比如离合器。其中，驱动轴可包括可耦合到一个或多个车轮121的一个或多个轴。Transmission 120 may transmit mechanical power from engine 118 to wheels 121 . Transmission 120 may include a gearbox, a differential, and drive shafts. In one embodiment, the transmission 120 may also include other devices, such as clutches. Among other things, drive shafts may include one or more axles that may be coupled to one or more wheels 121 .
传感器系统104可包括感测关于自动驾驶装置100周边的环境的信息的若干个传感器。例如，传感器系统104可包括定位系统122(定位系统可以是全球定位(globalpositioning system，GPS)系统，也可以是北斗系统或者其他定位系统)、惯性测量单元(inertial measurement unit，IMU)124、雷达126、激光测距仪128以及相机130。传感器系统104还可包括被监视自动驾驶装置100的内部系统的传感器(例如，车内空气质量监测器、燃油量表、机油温度表等)。来自这些传感器中的一个或多个的传感器数据可用于检测对象及其相应特性(位置、形状、方向、速度等)。这种检测和识别是自主自动驾驶装置100的安全操作的关键功能。Sensor system 104 may include a number of sensors that sense information about the environment surrounding autonomous driving device 100 . For example, the sensor system 104 may include a positioning system 122 (the positioning system may be a global positioning (global positioning system, GPS) system, Beidou system or other positioning systems), an inertial measurement unit (inertial measurement unit, IMU) 124, a radar 126 , a laser range finder 128 and a camera 130 . The sensor system 104 may also include sensors that monitor internal systems of the automatic driving device 100 (eg, an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding properties (position, shape, orientation, velocity, etc.). Such detection and identification are critical functions for the safe operation of autonomous autopilot 100 .
定位系统122可用于估计自动驾驶装置100的地理位置。IMU124用于基于惯性加速度来感测自动驾驶装置100的位置和朝向变化。在一个实施例中，IMU124可以是加速度计和陀螺仪的组合。The positioning system 122 can be used to estimate the geographic location of the autonomous driving device 100 . The IMU 124 is used to sense the position and orientation changes of the automatic driving device 100 based on inertial acceleration. In one embodiment, IMU 124 may be a combination accelerometer and gyroscope.
雷达126可利用无线电信号来感测自动驾驶装置100的周边环境内的物体。Radar 126 may utilize radio signals to sense objects within the environment surrounding autonomous driving device 100 .
激光测距仪128可利用激光来感测自动驾驶装置100所位于的环境中的物体。在一些实施例中，激光测距仪128可包括一个或多个激光源、激光扫描器以及一个或多个检测器，以及其他系统组件。在一些实施例中，除了感测物体以外，激光测距仪128可以是激光雷达(light detection and ranging，LiDAR)。激光雷达，是以发射激光束探测目标的位置、速度等特征量的雷达系统。激光雷达可向目标(即障碍物)或某个方向发射探测信号(激光束)，然后将接收到的从目标反射回来的信号(目标回波)与发射信号进行比较，作适当处理后，就可获得目标的有关信息，例如表示目标的表面特性的点云。点云是在同一空间参考系下表达目标空间分布和目标表面特性的海量点集合。本申请中的点云可以是根据激光测量原理得到的点云，包括每个点的三维坐标。The laser rangefinder 128 may use laser light to sense objects in the environment in which the automatic driving device 100 is located. In some embodiments, laser rangefinder 128 may include one or more laser sources, a laser scanner, and one or more detectors, among other system components. In some embodiments, in addition to sensing objects, laser rangefinder 128 may be a light detection and ranging (LiDAR). Lidar is a radar system that emits laser beams to detect characteristic quantities such as the position and speed of targets. LiDAR can transmit a detection signal (laser beam) to the target (obstacle) or a certain direction, and then compare the received signal (target echo) reflected from the target with the transmitted signal, and after proper processing, it will be Information about the object can be obtained, such as a point cloud representing the surface properties of the object. A point cloud is a collection of massive points expressing the spatial distribution of objects and surface properties of objects in the same spatial reference system. The point cloud in this application may be a point cloud obtained according to the principle of laser measurement, including the three-dimensional coordinates of each point.
相机130可用于捕捉自动驾驶装置100的周边环境的多个图像。相机130可以是静态相机或视频相机。相机130可以实时或周期性的捕捉自动驾驶装置100的周边环境的多个图像。Camera 130 may be used to capture multiple images of the surrounding environment of automatic driving device 100 . Camera 130 may be a still camera or a video camera. The camera 130 can capture multiple images of the surrounding environment of the automatic driving device 100 in real time or periodically.
控制系统106为控制自动驾驶装置100及其组件的操作。控制系统106可包括各种元件，其中包括转向系统132、油门134、制动单元136、计算机视觉系统140、路线控制系统142以及障碍物避免系统144。The control system 106 controls the operation of the automatic driving device 100 and its components. Control system 106 may include various elements including steering system 132 , accelerator 134 , braking unit 136 , computer vision system 140 , route control system 142 , and obstacle avoidance system 144 .
转向系统132可操作来调整自动驾驶装置100的前进方向。例如在一个实施例中可以为方向盘系统。The steering system 132 is operable to adjust the heading of the automated driving device 100 . For example in one embodiment it could be a steering wheel system.
油门134用于控制引擎118的操作速度并进而控制自动驾驶装置100的速度。The throttle 134 is used to control the operating speed of the engine 118 and thus the speed of the autopilot 100 .
制动单元136用于控制自动驾驶装置100减速。制动单元136可使用摩擦力来减慢车轮121。在其他实施例中，制动单元136可将车轮121的动能转换为电流。制动单元136也可采取其他形式来减慢车轮121转速从而控制自动驾驶装置100的速度。The braking unit 136 is used to control the automatic driving device 100 to decelerate. The braking unit 136 may use friction to slow the wheels 121 . In other embodiments, the brake unit 136 can convert the kinetic energy of the wheel 121 into electric current. The braking unit 136 can also take other forms to slow down the rotation speed of the wheels 121 so as to control the speed of the automatic driving device 100 .
计算机视觉系统140可以处理和分析由相机130捕捉的图像以便识别自动驾驶装置100周边环境中的物体和/或特征。所述物体和/或特征可包括交通信号、道路边界和障碍物。计算机视觉系统140可使用物体识别算法、自动驾驶方法、运动中恢复结构(Structurefrom Motion，SFM)算法、视频跟踪和其他计算机视觉技术。在一些实施例中，计算机视觉系统140可以用于为环境绘制地图、跟踪物体、估计物体的速度等等。计算机视觉系统140可使用激光雷达获取的点云以及相机获取的周围环境的图像，定位障碍物的位置。Computer vision system 140 may process and analyze images captured by camera 130 to identify objects and/or features in the environment surrounding autonomous driving device 100 . The objects and/or features may include traffic signals, road boundaries and obstacles. The computer vision system 140 may use object recognition algorithms, autonomous driving methods, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, computer vision system 140 may be used to map the environment, track objects, estimate the velocity of objects, and the like. The computer vision system 140 can use the point cloud acquired by the lidar and the image of the surrounding environment acquired by the camera to locate the position of the obstacle.
路线控制系统142用于确定自动驾驶装置100的行驶路线。在一些实施例中，路线控制系统142可结合来自传感器138、GPS 122和一个或多个预定地图的数据以为自动驾驶装置100确定行驶路线。The route control system 142 is used to determine the driving route of the automatic driving device 100 . In some embodiments, route control system 142 may combine data from sensors 138 , GPS 122 , and one or more predetermined maps to determine a travel route for automated driving device 100 .
障碍物避免系统144用于识别、评估和避免或者以其他方式越过自动驾驶装置100的环境中的潜在障碍物。Obstacle avoidance system 144 is used to identify, evaluate, and avoid or otherwise overcome potential obstacles in the environment of automated driving device 100 .
当然，在一个实例中，控制系统106可以增加或替换地包括除了所示出和描述的那些以外的组件。或者也可以减少一部分上述示出的组件。Of course, in one example, control system 106 may additionally or alternatively include components other than those shown and described. Alternatively, some of the components shown above may be reduced.
自动驾驶装置100通过外围设备108与外部传感器、其他车辆、其他计算机系统或用户之间进行交互。外围设备108可包括无线通信系统146、车载电脑148、麦克风150和/或扬声器152。The autonomous driving device 100 interacts with external sensors, other vehicles, other computer systems, or users through peripherals 108 . Peripherals 108 may include wireless communication system 146 , on-board computer 148 , microphone 150 and/or speaker 152 .
在一些实施例中，外围设备108提供自动驾驶装置100的用户与用户接口116交互的手段。例如，车载电脑148可向自动驾驶装置100的用户提供信息。用户接口116还可操作车载电脑148来接收用户的输入。车载电脑148可以通过触摸屏进行操作。在其他情况中，外围设备108可提供用于自动驾驶装置100与位于车内的其它设备通信的手段。例如，麦克风150可从自动驾驶装置100的用户接收音频(例如，语音命令或其他音频输入)。类似地，扬声器152可向自动驾驶装置100的用户输出音频。In some embodiments, peripheral device 108 provides a means for a user of automated driving apparatus 100 to interact with user interface 116 . For example, on-board computer 148 may provide information to a user of automated driving device 100 . The user interface 116 may also operate the on-board computer 148 to receive user input. The on-board computer 148 can be operated through a touch screen. In other cases, peripheral device 108 may provide a means for automated driving device 100 to communicate with other devices located within the vehicle. For example, microphone 150 may receive audio (eg, voice commands or other audio input) from a user of autonomous driving device 100 . Similarly, speaker 152 may output audio to a user of autonomous driving device 100 .
无线通信系统146可以直接地或者经由通信网络来与一个或多个设备无线通信。例如，无线通信系统146可使用3G蜂窝通信，或者4G蜂窝通信，例如LTE，或者5G蜂窝通信。无线通信系统146可利用WiFi与无线局域网(wireless local area network，WLAN)通信。在一些实施例中，无线通信系统146可利用红外链路、蓝牙或ZigBee与设备直接通信。其他无线协议，例如各种车辆通信系统，例如，无线通信系统146可包括一个或多个专用短程通信(dedicated short range communications，DSRC)设备，这些设备可包括车辆和/或路边台站之间的公共和/或私有数据通信。Wireless communication system 146 may communicate wirelessly with one or more devices, either directly or via a communication network. For example, the wireless communication system 146 may use 3G cellular communications, or 4G cellular communications, such as LTE, or 5G cellular communications. The wireless communication system 146 can use WiFi to communicate with a wireless local area network (WLAN). In some embodiments, the wireless communication system 146 may communicate directly with the device using an infrared link, Bluetooth, or ZigBee. Other wireless protocols, such as various vehicle communication systems, for example, wireless communication system 146 may include one or more dedicated short range communications (DSRC) devices, which may include communication between vehicles and/or roadside stations. public and/or private data communications.
电源110可向自动驾驶装置100的各种组件提供电力。在一个实施例中，电源110可以为可再充电锂离子或铅酸电池。这种电池的一个或多个电池组可被配置为电源为自动驾驶装置100的各种组件提供电力。在一些实施例中，电源110和能量源119可一起实现，例如一些全电动车中那样。The power source 110 may provide power to various components of the automatic driving device 100 . In one embodiment, the power source 110 may be a rechargeable lithium-ion or lead-acid battery. One or more battery packs of such batteries may be configured as a power source to provide power to various components of the autonomous driving device 100 . In some embodiments, power source 110 and energy source 119 may be implemented together, such as in some all-electric vehicles.
自动驾驶装置100的部分或所有功能受计算机系统112控制。计算机系统112可包括至少一个处理器113，处理器113执行存储在例如数据存储装置114这样的非暂态计算机可读介质中的指令115。计算机系统112还可以是采用分布式方式控制自动驾驶装置100的个体组件或子系统的多个计算设备。Some or all of the functions of the automatic driving device 100 are controlled by the computer system 112 . Computer system 112 may include at least one processor 113 executing instructions 115 stored in a non-transitory computer-readable medium such as data storage device 114 . Computer system 112 may also be a plurality of computing devices that control individual components or subsystems of automated driving apparatus 100 in a distributed manner.
处理器113可以是任何常规的处理器，诸如商业可获得的中央处理器(centralprocessing unit，CPU)。替选地，该处理器可以是诸如ASIC或其它基于硬件的处理器的专用设备。尽管图1功能性地图示了处理器、存储器和在相同块中的计算机系统112的其它元件，但是本领域的普通技术人员应该理解该处理器、计算机、或存储器实际上可以包括可以或者可以不存储在相同的物理外壳内的多个处理器、计算机、或存储器。例如，存储器可以是硬盘驱动器或位于不同于计算机系统112的外壳内的其它存储介质。因此，对处理器或计算机的引用将被理解为包括对可以或者可以不并行操作的处理器或计算机或存储器的集合的引用。不同于使用单一的处理器来执行此处所描述的步骤，诸如转向组件和减速组件的一些组件每个都可以具有其自己的处理器，该处理器只执行与特定于组件的功能相关的计算。The processor 113 may be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor may be a special purpose device such as an ASIC or other hardware based processor. Although FIG. 1 functionally illustrates the processor, memory, and other elements of the computer system 112 in the same block, those of ordinary skill in the art will understand that the processor, computer, or memory may actually include Multiple processors, computers, or memories stored within the same physical enclosure. For example, memory may be a hard drive or other storage medium located in a different housing than computer system 112 . Accordingly, references to a processor or computer are to be understood to include references to collections of processors or computers or memories that may or may not operate in parallel. Rather than using a single processor to perform the steps described herein, some components, such as the steering and deceleration components, may each have their own processor that only performs calculations related to component-specific functions.
在此处所描述的各个方面中，处理器可以位于远离该自动驾驶装置并且与该自动驾驶装置进行无线通信。在其它方面中，此处所描述的过程中的一些操作在布置于自动驾驶装置内的处理器上执行而其它则由远程处理器执行，包括采取执行单一操纵的必要步骤。In various aspects described herein, the processor may be located remotely from the automated driving device and be in wireless communication with the automated driving device. In other aspects, some operations in the processes described herein are performed on a processor disposed within the automated driving device while others are performed by a remote processor, including taking the necessary steps to perform a single maneuver.
在一些实施例中，数据存储装置114可包含指令115(例如，程序逻辑)，指令115可被处理器113执行来执行自动驾驶装置100的各种功能，包括以上描述的那些功能。数据存储装置114也可包含额外的指令，包括向推进系统102、传感器系统104、控制系统106和外围设备108中的一个或多个发送数据、从其接收数据、与其交互和/或对其进行控制的指令。In some embodiments, data storage device 114 may contain instructions 115 (eg, program logic) executable by processor 113 to perform various functions of automatic driving device 100 , including those described above. Data storage 114 may also contain additional instructions, including sending data to, receiving data from, interacting with, and/or performing operations on, one or more of propulsion system 102, sensor system 104, control system 106, and peripherals 108. control instructions.
除了指令115以外，数据存储装置114还可存储数据，例如道路地图、路线信息，车辆的位置、方向、速度以及其他信息。这些信息可在自动驾驶装置100在自主、半自主和/或手动模式中操作期间被自动驾驶装置100和计算机系统112使用。In addition to instructions 115, data storage device 114 may also store data such as road maps, route information, the vehicle's position, direction, speed, and other information. This information may be used by the automatic driving device 100 and the computer system 112 during operation of the automatic driving device 100 in autonomous, semi-autonomous, and/or manual modes.
用户接口116，用于向自动驾驶装置100的用户提供信息或从其接收信息。可选地，用户接口116可包括在外围设备108的集合内的一个或多个输入/输出设备，例如无线通信系统146、车载电脑148、麦克风150和扬声器152。A user interface 116 for providing information to or receiving information from a user of the automatic driving device 100 . Optionally, user interface 116 may include one or more input/output devices within set of peripheral devices 108 , such as wireless communication system 146 , onboard computer 148 , microphone 150 , and speaker 152 .
计算机系统112可基于从各种子系统(例如，行进系统102、传感器系统104和控制系统106)以及从用户接口116接收的输入来控制自动驾驶装置100的功能。例如，计算机系统112可利用来自控制系统106的输入以便控制转向单元132来避免由传感器系统104和障碍物避免系统144检测到的障碍物。在一些实施例中，计算机系统112可操作来对自动驾驶装置100及其子系统的许多方面提供控制。Computer system 112 may control functions of automated driving device 100 based on input received from various subsystems (eg, travel system 102 , sensor system 104 , and control system 106 ) and from user interface 116 . For example, computer system 112 may utilize input from control system 106 in order to control steering unit 132 to avoid obstacles detected by sensor system 104 and obstacle avoidance system 144 . In some embodiments, computer system 112 is operable to provide control over many aspects of automated driving device 100 and its subsystems.
可选地，上述这些组件中的一个或多个可与自动驾驶装置100分开安装或关联。例如，数据存储装置114可以部分或完全地与自动驾驶装置100分开存在。上述组件可以按有线和/或无线方式来通信地耦合在一起。Optionally, one or more of the above-mentioned components may be separately installed or associated with the automatic driving device 100 . For example, the data storage device 114 may exist partially or completely separate from the automatic driving device 100 . The components described above may be communicatively coupled together in a wired and/or wireless manner.
可选地，上述组件只是一个示例，实际应用中，上述各个模块中的组件有可能根据实际需要增添或者删除，图1不应理解为对本申请实施例的限制。Optionally, the above-mentioned components are just an example. In practical applications, components in the above-mentioned modules may be added or deleted according to actual needs. FIG. 1 should not be construed as limiting the embodiment of the present application.
在道路行进的自动驾驶汽车，如上面的自动驾驶装置100，可以识别其周围环境内的物体以确定对当前速度的调整。所述物体可以是其它车辆、交通控制设备、或者其它类型的物体。在一些示例中，可以独立地考虑每个识别的物体，并且基于物体的各自的特性，诸如它的当前速度、加速度、与车辆的间距等，可以用来确定自动驾驶汽车所要调整的速度。A self-driving car traveling on a road, such as the self-driving device 100 above, can recognize objects in its surroundings to determine adjustments to the current speed. The objects may be other vehicles, traffic control devices, or other types of objects. In some examples, each identified object may be considered independently and based on the object's respective characteristics, such as its current speed, acceleration, distance to the vehicle, etc., may be used to determine the speed at which the autonomous vehicle is to adjust.
可选地，自动驾驶装置100或者与自动驾驶装置100相关联的计算设备(如图1的计算机系统112、计算机视觉系统140、数据存储装置114)可以基于所识别的物体的特性和周围环境的状态(例如，交通、雨、道路上的冰等等)来预测所述识别的物体的行为。可选地，每一个所识别的物体都依赖于彼此的行为，因此还可以将所识别的所有物体全部一起考虑来预测单个识别的物体的行为。自动驾驶装置100能够基于预测的所述识别的物体的行为来调整它的速度。换句话说，自动驾驶汽车能够基于所预测的物体的行为来确定车辆将需要调整到(例如，加速、减速、或者停止)什么稳定状态。在这个过程中，也可以考虑其它因素来确定自动驾驶装置100的速度，诸如，自动驾驶装置100在行驶的道路中的横向位置、道路的曲率、静态和动态物体的接近度等等。Optionally, the automatic driving device 100 or a computing device associated with the automatic driving device 100 (such as the computer system 112, the computer vision system 140, and the data storage device 114 of FIG. state (eg, traffic, rain, ice on the road, etc.) to predict the behavior of the identified objects. Optionally, each identified object is dependent on the behavior of the other, so all identified objects can also be considered together to predict the behavior of a single identified object. The autopilot 100 is able to adjust its speed based on the predicted behavior of the identified object. In other words, the self-driving car is able to determine what steady state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object. During this process, other factors may also be considered to determine the speed of the automatic driving device 100 , such as the lateral position of the automatic driving device 100 on the driving road, the curvature of the road, the proximity of static and dynamic objects, and so on.
除了提供调整自动驾驶汽车的速度的指令之外，计算设备还可以提供修改自动驾驶装置100的转向角的指令，以使得自动驾驶汽车遵循给定的轨迹和/或维持与自动驾驶汽车附近的物体(例如，道路上的相邻车道中的轿车)的安全横向和纵向距离。In addition to providing instructions to adjust the speed of the self-driving car, the computing device may also provide instructions to modify the steering angle of the self-driving car 100 so that the self-driving car follows a given trajectory and/or maintains contact with objects near the self-driving car. (for example, cars in adjacent lanes on the road) safe lateral and longitudinal distances.
上述自动驾驶装置100可以为轿车、卡车、摩托车、公共汽车、船、飞机、直升飞机、割草机、娱乐车、游乐场车辆、施工设备、电车、高尔夫球车、火车、和手推车等，本发明实施例不做特别的限定。The above-mentioned automatic driving device 100 may be cars, trucks, motorcycles, buses, ships, airplanes, helicopters, lawn mowers, recreational vehicles, playground vehicles, construction equipment, trams, golf carts, trains, and trolleys, etc. , the embodiments of the present invention are not particularly limited.
图1介绍了自动驾驶装置100的功能框图，下面介绍一种自动驾驶系统101。图2为本申请实施例提供的一种自动驾驶系统的结构示意图。图1和图2是从不同的角度来描述自动驾驶装置100。如图2所示，计算机系统101包括处理器103，处理器103和系统总线105耦合。处理器103可以是一个或者多个处理器，其中，每个处理器都可以包括一个或多个处理器核。显示适配器(video adapter)107，显示适配器可以驱动显示器109，显示器109和系统总线105耦合。系统总线105通过总线桥111和输入输出(I/O)总线113耦合。I/O接口115和I/O总线耦合。I/O接口115和多种I/O设备进行通信，比如输入设备117(如：键盘，鼠标，触摸屏等)，多媒体盘(media tray)121，例如CD-ROM，多媒体接口等。收发器123(可以发送和/或接受无线电通信信号)，摄像头155(可以捕捉景田和动态数字视频图像)和外部USB接口125。可选的，和I/O接口115相连接的接口可以是USB接口。FIG. 1 introduces a functional block diagram of an automatic driving device 100 , and an automatic driving system 101 is introduced below. Fig. 2 is a schematic structural diagram of an automatic driving system provided by an embodiment of the present application. FIG. 1 and FIG. 2 describe the automatic driving device 100 from different angles. As shown in FIG. 2 , computer system 101 includes processor 103 coupled to system bus 105 . The processor 103 may be one or more processors, where each processor may include one or more processor cores. A video adapter (video adapter) 107 can drive a display 109 , and the display 109 is coupled to the system bus 105 . The system bus 105 is coupled to an input-output (I/O) bus 113 through a bus bridge 111 . The I/O interface 115 is coupled to the I/O bus. The I/O interface 115 communicates with various I/O devices, such as an input device 117 (such as a keyboard, a mouse, a touch screen, etc.), a media tray 121 such as a CD-ROM, a multimedia interface, and the like. Transceiver 123 (which can send and/or receive radio communication signals), camera 155 (which can capture landscape and dynamic digital video images) and external USB interface 125 . Optionally, the interface connected to the I/O interface 115 may be a USB interface.
其中，处理器103可以是任何传统处理器，包括精简指令集计算(“RISC”)处理器、复杂指令集计算(“CISC”)处理器或上述的组合。可选的，处理器可以是诸如专用集成电路(“ASIC”)的专用装置。可选的，处理器103可以是神经网络处理器(Neural-networkProcessingUnit，NPU)或者是神经网络处理器和上述传统处理器的组合。可选的，处理器103挂载有一个神经网络处理器。Wherein, the processor 103 may be any conventional processor, including a Reduced Instruction Set Computing (“RISC”) processor, a Complex Instruction Set Computing (“CISC”) processor, or a combination thereof. Alternatively, the processor may be a special purpose device such as an application specific integrated circuit ("ASIC"). Optionally, the processor 103 may be a neural network processor (Neural-network Processing Unit, NPU) or a combination of a neural network processor and the above traditional processors. Optionally, the processor 103 is mounted with a neural network processor.
计算机系统101可以通过网络接口129和软件部署服务器149通信。网络接口129是硬件网络接口，比如，网卡。网络127可以是外部网络，比如因特网，也可以是内部网络，比如以太网或者虚拟私人网络。可选的，网络127还可以是无线网络，比如WiFi网络，蜂窝网络等。Computer system 101 can communicate with software deployment server 149 through network interface 129 . The network interface 129 is a hardware network interface, such as a network card. The network 127 can be an external network, such as the Internet, or an internal network, such as Ethernet or a virtual private network. Optionally, the network 127 may also be a wireless network, such as a WiFi network, a cellular network, and the like.
硬盘驱动接口和系统总线105耦合。硬件驱动接口和硬盘驱动器相连接。系统内存135和系统总线105耦合。运行在系统内存135的数据可以包括计算机系统101的操作系统137和应用程序143。A hard disk drive interface is coupled to the system bus 105 . The hardware drive interface is connected with the hard disk drive. System memory 135 is coupled to system bus 105 . Data running in system memory 135 may include operating system 137 and application programs 143 of computer system 101 .
操作系统包括壳(Shell)139和内核(kernel)141。壳139是介于使用者和操作系统之内核(kernel)间的一个接口。壳139是操作系统最外面的一层。壳139管理使用者与操作系统之间的交互：等待使用者的输入，向操作系统解释使用者的输入，并且处理各种各样的操作系统的输出结果。The operating system includes a shell (Shell) 139 and a kernel (kernel) 141 . Shell 139 is an interface between the user and the kernel of the operating system. Shell 139 is the outermost layer of the operating system. Shell 139 manages the interaction between the user and the operating system: waiting for user input, interpreting user input to the operating system, and processing various operating system output.
内核141由操作系统中用于管理存储器、文件、外设和系统资源的那些部分组成。直接与硬件交互，操作系统内核通常运行进程，并提供进程间的通信，提供CPU时间片管理、中断、内存管理、IO管理等等。Kernel 141 consists of those parts of the operating system that manage memory, files, peripherals, and system resources. Directly interacting with hardware, the operating system kernel usually runs processes and provides communication between processes, providing CPU time slice management, interrupts, memory management, IO management, and so on.
应用程序141包括自动驾驶相关程序，比如，管理自动驾驶装置和路上障碍物交互的程序，控制自动驾驶装置的行车路线或者速度的程序，控制自动驾驶装置100和路上其他自动驾驶装置交互的程序。应用程序141也存在于软件部署服务器(deploying server)149的系统上。在一个实施例中，在需要执行应用程序141时，计算机系统101可以从软件部署服务器149下载应用程序141。The application program 141 includes programs related to automatic driving, such as a program for managing the interaction between the automatic driving device and obstacles on the road, a program for controlling the driving route or speed of the automatic driving device, and a program for controlling the interaction between the automatic driving device 100 and other automatic driving devices on the road. The application program 141 also exists on the system of a software deploying server (deploying server) 149 . In one embodiment, when the application program 141 needs to be executed, the computer system 101 can download the application program 141 from the software deployment server 149 .
传感器153和计算机系统101关联。传感器153用于探测计算机系统101周围的环境。举例来说，传感器153可以探测动物，汽车，障碍物和人行横道等，进一步传感器还可以探测上述动物，汽车，障碍物和人行横道等物体周围的环境，比如：动物周围的环境，例如，动物周围出现的其他动物，天气条件，周围环境的光亮度等。可选的，如果计算机系统101位于自动驾驶装置上，传感器可以是摄像头(即相机)，激光雷达，红外线感应器，化学检测器，麦克风等。传感器153在激活时按照预设间隔感测信息并实时或接近实时地将所感测的信息提供给计算机系统101。可选的，传感器可以包括激光雷达，该激光雷达可以实时或接近实时地将获取的点云提供给计算机系统101。可选的，摄像头实时或接近实时地将获取的图像提供给计算机系统101。Sensor 153 is associated with computer system 101 . Sensors 153 are used to detect the environment around computer system 101 . For example, the sensor 153 can detect animals, automobiles, obstacles and crosswalks, etc., and further sensors can also detect the surrounding environment of objects such as the above-mentioned animals, automobiles, obstacles and crosswalks, such as: the environment around the animals, for example, around the animals other animals, weather conditions, the brightness of the surrounding environment, etc. Optionally, if the computer system 101 is located on the automatic driving device, the sensor may be a camera (ie camera), laser radar, infrared sensor, chemical detector, microphone and so on. The sensor 153 senses information at preset intervals when activated and provides the sensed information to the computer system 101 in real time or near real time. Optionally, the sensor may include a laser radar, and the laser radar may provide the acquired point cloud to the computer system 101 in real time or near real time. Optionally, the camera provides the acquired images to the computer system 101 in real time or near real time.
可选的，在本文所述的各种实施例中，计算机系统101可位于远离自动驾驶装置的地方，并且可与自动驾驶装置进行无线通信。收发器123可将自动驾驶任务、传感器153采集的传感器数据和其他数据发送给计算机系统101；还可以接收计算机系统101发送的控制指令。自动驾驶装置可执行收发器接收的来自计算机系统101的控制指令，并执行相应的驾驶操作。在其它方面，本文所述的一些过程在设置在自动驾驶车辆内的处理器上执行，其它由远程处理器执行，包括采取执行单个操纵所需的动作。Optionally, in various embodiments described herein, the computer system 101 may be located away from the automatic driving device, and may communicate wirelessly with the automatic driving device. The transceiver 123 can send the automatic driving tasks, sensor data collected by the sensor 153 and other data to the computer system 101 ; and can also receive control instructions sent by the computer system 101 . The automatic driving device can execute the control instructions from the computer system 101 received by the transceiver, and perform corresponding driving operations. In other aspects, some of the processes described herein are performed on a processor disposed within the self-driving vehicle and others are performed by a remote processor, including taking the actions required to perform a single maneuver.
可选的，自动驾驶装置在自动驾驶过程中通过多种传感器采集路况信息；根据当前路况以及导航信息，按照用户指示的目标驾驶风格进行驾驶。本申请实施例中，用户可以根据自己的需求选择相应地驾驶风格，自动驾驶装置按照用户选择的驾驶风格进行驾驶。举例来说，自动驾驶装置有激进、谨慎以及普通等多种驾驶风格，该自动驾驶装置在不同的驾驶风格下执行的驾驶行为不完全相同。可选的，用户可以将驾驶数据文件从便携设备或者服务器导入至自动驾驶装置，该自动驾驶装置上运行的自动驾驶系统结合该驾驶数据文件中的历史驾驶数据对驾驶行为进一步优化，进而改善该用户的乘车体验。下面介绍如何按照用户指示的目标驾驶风格进行驾驶的自动驾驶方法。Optionally, the automatic driving device collects road condition information through various sensors during the automatic driving process; according to the current road condition and navigation information, it drives according to the target driving style indicated by the user. In the embodiment of the present application, the user can select a corresponding driving style according to his own needs, and the automatic driving device drives according to the driving style selected by the user. For example, the automatic driving device has multiple driving styles such as aggressive, cautious, and normal, and the driving behavior performed by the automatic driving device under different driving styles is not exactly the same. Optionally, the user can import the driving data file from the portable device or server to the automatic driving device, and the automatic driving system running on the automatic driving device further optimizes the driving behavior in combination with the historical driving data in the driving data file, thereby improving the driving behavior. The user's ride experience. The following describes an automatic driving method for driving in accordance with a target driving style indicated by the user.
图3为本申请实施例提供的一种自动驾驶方法流程图，如图3所示，该方法可包括：Fig. 3 is a flow chart of an automatic driving method provided by the embodiment of the present application. As shown in Fig. 3, the method may include:
301、自动驾驶装置获取当前路况信息。301. The automatic driving device acquires current road condition information.
自动驾驶装置可在驾驶过程中通过多种传感器采集路况信息，并对当前采集到的各种路况信息进行整合以得到该当前路况信息。具体的，该自动驾驶装置在行驶过程中，可以通过自车安装的多种传感器收集交通流信息和路面情况，例如交通指示牌、红绿灯、车道线、周围车辆、行人以及障碍物信息等原始数据。本申请中，自车是指自动驾驶装置。自动驾驶装置安装的传感器可包括激光雷达，毫米波雷达，超声波雷达，单目或双目摄像头等。各路面信息可以反映了不同的路况。交通指示牌可以指示道路限速上限，限速下限，前方停止行车等等。红绿灯可以指示是否停车，左转或右转。车道线可以指示车辆行驶方向，转弯半径，两边车道方向，是否允许换道等。车辆，行人及障碍物可以指示障碍物相对自车的位置，车道信息，相对速度等等。自动驾驶装置获取当前路况信息可以是该自动驾驶装置对当前时刻收集到的所有原始数据(即原始路况信息)进行融合、聚类、抽象等加工处理以得到当前时刻下的路况信息，即当前路况信息。The automatic driving device can collect road condition information through various sensors during driving, and integrate various currently collected road condition information to obtain the current road condition information. Specifically, during the driving process, the automatic driving device can collect traffic flow information and road conditions through various sensors installed on the vehicle, such as traffic signs, traffic lights, lane lines, surrounding vehicles, pedestrians and obstacle information and other raw data . In this application, the self-vehicle refers to an automatic driving device. The sensors installed on the autonomous driving device may include lidar, millimeter-wave radar, ultrasonic radar, monocular or binocular cameras, etc. Each road surface information may reflect different road conditions. Traffic signs can indicate the upper limit of the road speed limit, the lower limit of the speed limit, stop driving ahead and so on. Traffic lights can indicate whether to stop, turn left or turn right. Lane lines can indicate the driving direction of the vehicle, the turning radius, the direction of the lanes on both sides, whether lane changing is allowed, etc. Vehicles, pedestrians and obstacles can indicate the position of obstacles relative to the vehicle, lane information, relative speed and so on. The acquisition of the current road condition information by the automatic driving device may be that the automatic driving device performs fusion, clustering, abstraction and other processing on all the raw data collected at the current moment (that is, the original road condition information) to obtain the current road condition information at the current moment, that is, the current road condition information.
302、自动驾驶装置根据当前路况信息，从数据库中查询是否存在与当前路况信息相匹配的目标驾驶控制参数。302. The automatic driving device queries the database whether there is a target driving control parameter matching the current road condition information according to the current road condition information.
该目标驾驶控制参数包括目标车辆的历史驾驶控制参数，该历史驾驶控制参数包括该目标车辆按照目标驾驶风格进行驾驶得到的驾驶控制参数。该数据库中存储有该目标车辆的历史驾驶控制参数，一种或多种路况信息，以及该当前路况信息与该目标驾驶控制参数的匹配关系。在实际应用中，数据库中可存储有多种路况信息以及这些路况信息相匹配的驾驶控制参数，通过查询该数据库来确定与当前路况信息相匹配的驾驶控制参数。The target driving control parameters include historical driving control parameters of the target vehicle, and the historical driving control parameters include driving control parameters obtained by driving the target vehicle according to the target driving style. The database stores historical driving control parameters of the target vehicle, one or more types of road condition information, and a matching relationship between the current road condition information and the target driving control parameters. In practical applications, various road condition information and driving control parameters matching the road condition information can be stored in the database, and the driving control parameters matching the current road condition information can be determined by querying the database.
该目标车辆可以为该自动驾驶装置，也可以不是该自动驾驶装置。该自动驾驶装置在执行步骤302之前，存储有或者已从其他设备获取到该历史驾驶控制参数以及该历史驾驶控制参数中的驾驶控制参数与路况信息的匹配关系。驾驶控制参数可以包括纵向速度、横向速度、加速度、转角等参数。在一些实施例中，历史驾驶控制参数可以是目标车辆在驾驶员手动驾驶的过程中采集到的驾驶控制参数，也可以是对该目标车辆在驾驶员手动驾驶的过程中采集到的驾驶控制参数进一步处理得到的驾驶控制参数。可选的，对自动驾驶装置在手动驾驶模式下的用户的驾驶控制参数进一步处理包括删除一些重复的驾驶控制参数等。The target vehicle may or may not be the automatic driving device. Before performing step 302, the automatic driving device has stored or acquired the historical driving control parameters and the matching relationship between the driving control parameters and road condition information in the historical driving control parameters. Driving control parameters may include parameters such as longitudinal speed, lateral speed, acceleration, and cornering angle. In some embodiments, the historical driving control parameters may be the driving control parameters collected by the target vehicle during the driver's manual driving, or the driving control parameters collected by the driver during the manual driving of the target vehicle The resulting driving control parameters are further processed. Optionally, the further processing of the user's driving control parameters of the automatic driving device in the manual driving mode includes deleting some repeated driving control parameters and the like.
303、若存在，则自动驾驶装置获取目标驾驶控制参数，并根据目标驾驶控制参数以目标驾驶风格进行驾驶。303. If yes, the automatic driving device acquires the target driving control parameters, and drives in the target driving style according to the target driving control parameters.
自动驾驶装置根据该目标驾驶控制参数以目标驾驶风格进行驾驶可以是该自动驾驶装置上的自动驾驶系统根据该目标驾驶控制参数对自车进行控制。在实际应用中，乘客可以根据自己的驾驶习惯选择相应的驾驶风格，自动驾驶装置根据与该驾驶风格相匹配的历史驾驶数据对当前执行的驾驶策略进一步优化。The automatic driving device driving with the target driving style according to the target driving control parameter may be that the automatic driving system on the automatic driving device controls the own vehicle according to the target driving control parameter. In practical applications, passengers can choose the corresponding driving style according to their own driving habits, and the automatic driving device further optimizes the current driving strategy based on the historical driving data that matches the driving style.
在一些实施例中，自动驾驶装置根据目标驾驶控制参数以目标驾驶风格进行驾驶可以是在该目标驾驶控制参数符合安全驾驶标准和交规的情况下，根据该目标驾驶控制参数以目标驾驶风格进行驾驶。在一些实施例中，在目标驾驶控制参数不符合安全驾驶标准或者交规的情况下，自动驾驶装置根据实时驾驶控制参数进行驾驶，该实时驾驶参数为该自动驾驶装置在当前决策出的驾驶控制参数。在实际应用中，自动驾驶装置在获取到与当前路况相匹配的目标驾驶控制参数之后，判断该目标驾驶控制参数是否符合安全驾驶标准和交规；若是，则根据该目标驾驶控制参数进行驾驶，若否，则根据实时驾驶控制参数进行驾驶。In some embodiments, the automatic driving device driving with the target driving style according to the target driving control parameters may be driving with the target driving style according to the target driving control parameters when the target driving control parameters comply with safe driving standards and traffic regulations . In some embodiments, when the target driving control parameters do not comply with safe driving standards or traffic regulations, the automatic driving device drives according to the real-time driving control parameters, which are the driving control parameters currently determined by the automatic driving device . In practical applications, after the automatic driving device obtains the target driving control parameters that match the current road conditions, it judges whether the target driving control parameters meet the safety driving standards and traffic regulations; if so, it drives according to the target driving control parameters, if If not, then drive according to the real-time driving control parameters.
304、若不存在，则自动驾驶装置根据实时驾驶控制参数以当前驾驶风格进行驾驶。304. If not, the automatic driving device drives with the current driving style according to the real-time driving control parameters.
该实时驾驶控制参数为该自动驾驶装置按照预设决策机制决策出的驾驶控制参数。具体的，该实时驾驶控制参数可以是该自动驾驶装置运行的自动驾驶系统当前在当前路况下决策出的驾驶控制参数。在实际应用中，若数据库中未存在与当前路况相匹配的目标驾驶控制参数时，则自动驾驶装置按照其运行的自动驾驶系统(对应于预设决策机制)决策出的实时驾驶控制参数进行驾驶。本申请中，当前驾驶风格对应于后文的默认驾驶风格。自动驾驶装置根据预设决策机制决策出的驾驶控制参数进行驾驶即是按照当前驾驶风格进行驾驶。目前，自动驾驶装置在自动驾驶模型下均是按照其运行的自动驾驶系统实时决策出的驾驶控制参数进行驾驶。也就是说，当前采用的自动驾驶技术中，自动驾驶装置在自动模式下执行的驾驶操作完全由自动驾驶系统控制，不会考虑乘客的驾驶习惯。The real-time driving control parameters are driving control parameters determined by the automatic driving device according to a preset decision-making mechanism. Specifically, the real-time driving control parameters may be driving control parameters currently determined by the automatic driving system operated by the automatic driving device under the current road conditions. In practical applications, if there is no target driving control parameter matching the current road conditions in the database, the automatic driving device will drive according to the real-time driving control parameters determined by its running automatic driving system (corresponding to the preset decision-making mechanism). . In this application, the current driving style corresponds to the default driving style hereinafter. Driving by the automatic driving device according to the driving control parameters determined by the preset decision-making mechanism is to drive according to the current driving style. At present, under the automatic driving model, the automatic driving device drives according to the driving control parameters determined in real time by its running automatic driving system. That is to say, in the current automatic driving technology, the driving operation performed by the automatic driving device in the automatic mode is completely controlled by the automatic driving system, and the driving habits of the passengers will not be considered.
本申请实施例中，自动驾驶装置在查询到与当前路况相匹配的目标驾驶控制参数后，按照该目标驾驶控制参数进行驾驶，而不是按照其当前决策出的驾驶控制参数进行驾驶；使得该自动驾驶装置能够利用以往的历史驾驶控制参数对其当前决策出的驾驶操作进行优化。由于目标驾驶控制参数是符合乘客的驾驶习惯的历史驾驶控制参数，使用这些历史驾驶控制参数对该自动驾驶装置的驾驶操作进行优化，可以更好的满足乘客的驾驶习惯。In the embodiment of the present application, after the automatic driving device inquires the target driving control parameters that match the current road conditions, it drives according to the target driving control parameters instead of driving according to the driving control parameters currently determined; The driving device can use the past historical driving control parameters to optimize its current decision-making driving operation. Since the target driving control parameters are historical driving control parameters that conform to the driving habits of the passengers, using these historical driving control parameters to optimize the driving operation of the automatic driving device can better meet the driving habits of the passengers.
图1的方法中未详述如何确定按照目标驾驶风格进行驾驶，下面描述自动驾驶装置确定按照目标驾驶风格进行驾驶的一些可选的实现方式。How to determine to drive according to the target driving style is not described in detail in the method of FIG. 1 , and some optional implementations for the automatic driving device to determine to drive according to the target driving style are described below.
在一个可选的实现方式中，确定按照目标驾驶风格进行驾驶的情况可以是：自动驾驶装置在接收到用户输入的第三指令或者来自第三终端的第四指令的情况下，确定按照该目标驾驶风格进行驾驶。该第三指令和该第四指令均用于指示该自动驾驶装置按照该目标驾驶风格进行驾驶。可选的，用户通过车载电脑或者自动驾驶装置上的其他输入接口输入该第三指令。该第三终端可以是手机、平板电脑等便携设备。在实际应用中，该第三终端通过无线或有线方式与自动驾驶装置进行通信，并向该自动驾驶装置发送该第四指令。可选的，自动驾驶装置支持多种驾驶风格，例如冒险、谨慎、默认等驾驶风格，用户可以通过第三指令或者第四指令选择该多种驾驶风格中的目标驾驶风格。可以理解，自动驾驶装置支持的多种驾驶风格中，除默认驾驶风格之外的每一种驾驶风格均对应一种手动驾驶模式下的历史驾驶数据(对应于下文的驾驶风格文件)。可选的，自动驾驶装置的驾驶风格数据库中包括多个驾驶数据文件，每个驾驶数据文件对应一个标签，每个标签表明其对应的驾驶数据文件代表的驾驶风格，乘客在使用自动驾驶系统时会进入驾驶风格选择界面，在该界面根据需求选择某种驾驶数据文件。其中，乘客可通过该驾驶风格选择界面选择某种驾驶数据文件。该驾驶风格选择界面可以是自动驾驶装置上的显示设备显示的界面，也可以是与该自动驾驶装置建立通信连接的终端显示的界面。自动驾驶装置按照默认驾驶风格进行驾驶可以是该自动驾驶装置上的自动驾驶系统完全根据当前路况以及导航信息进行驾驶，而不需要考虑手动驾驶模式下的历史驾驶数据。In an optional implementation manner, the determination of driving according to the target driving style may be: the automatic driving device determines to follow the target driving style when receiving the third instruction input by the user or the fourth instruction from the third terminal. Drive with your driving style. Both the third instruction and the fourth instruction are used to instruct the automatic driving device to drive according to the target driving style. Optionally, the user inputs the third instruction through the on-board computer or other input interfaces on the automatic driving device. The third terminal may be a portable device such as a mobile phone or a tablet computer. In practical applications, the third terminal communicates with the automatic driving device in a wireless or wired manner, and sends the fourth instruction to the automatic driving device. Optionally, the automatic driving device supports multiple driving styles, such as risky, cautious, and default driving styles, and the user can select a target driving style among the various driving styles through the third instruction or the fourth instruction. It can be understood that among the multiple driving styles supported by the automatic driving device, each driving style except the default driving style corresponds to a historical driving data in a manual driving mode (corresponding to the driving style file below). Optionally, the driving style database of the automatic driving device includes multiple driving data files, each driving data file corresponds to a label, and each label indicates the driving style represented by its corresponding driving data file, when the passenger uses the automatic driving system It will enter the driving style selection interface, where you can select a certain driving data file according to your needs. Wherein, the passenger can select a certain driving data file through the driving style selection interface. The driving style selection interface may be an interface displayed by a display device on the automatic driving device, or an interface displayed by a terminal establishing a communication connection with the automatic driving device. The driving of the automatic driving device according to the default driving style may be that the automatic driving system on the automatic driving device drives completely according to the current road conditions and navigation information, without considering the historical driving data in the manual driving mode.
在该实现方式中，自动驾驶装置存储有其按照目标驾驶风格进行驾驶的历史驾驶数据，用户仅需要从该自动驾驶装置支持的多种驾驶风格中选择所需的驾驶风格，操作简单。In this implementation, the automatic driving device stores historical driving data of its driving according to the target driving style, and the user only needs to select the required driving style from the multiple driving styles supported by the automatic driving device, and the operation is simple.
在一个可选的实现方式中，确定按照目标驾驶风格进行驾驶的情况可以是：在获得驾驶数据文件之后，确定按照该目标驾驶风格进行驾驶。该驾驶数据文件包括该自动驾驶装置按照该目标驾驶风格进行驾驶的历史路况信息、历史驾驶控制参数以及历史驾驶行为中的至少一项。历史路况信息、历史驾驶控制参数以及历史驾驶行为可以理解为历史驾驶数据。可选的，获得驾驶数据文件的方式可以是接收来自第一终端的驾驶数据文件；也可以是在接收到来自第二终端的第一指令后，从服务器获取该驾驶数据文件。其中，该第一指令用于指示该自动驾驶装置从该服务器获取该驾驶数据文件。该第一终端和该第二终端可以是手机、平板电脑等便携设备。可选的，第一终端与自动驾驶装置建立通信连接后，向该自动驾驶装置导入该驾驶数据文件。例如，第一终端通过数据线连接自动驾驶装置的USB接口，并通过该USB接口向该自动驾驶装置导入驾驶数据文件。可选的，服务器存储有至少一种驾驶数据文件，每种驾驶数据文件均包括用户在手动驾驶模式下驾驶某个自动驾驶装置的历史驾驶数据；自动驾驶装置可根据来自第二终端的指令，从该服务器获取相应的驾驶数据文件。可选的，自动驾驶装置获得的驾驶数据文件包括的历史驾驶数据为另一个车型与其相同的自动驾驶装置在手动驾驶模式下的历史驾驶数据，该自动驾驶装置可直接使用该驾驶数据文件中的历史驾驶控制参数优化其驾驶操作。可选的，自动驾驶装置获得的驾驶数据文件包括的历史驾驶数据为另一种型号的自动驾驶装置在手动驾驶模式下的历史驾驶数据，该自动驾驶装置对该驾驶数据文件中的历史驾驶控制参数进行转换以得到其可直接作为参考的历史驾驶控制参数。例如，第一自动驾驶装置对应第一车型，该第一自动驾驶装置获得的驾驶数据文件包括第二车型的第二自动驾驶装置在手动驾驶模式下的历史驾驶数据，该第一自动驾驶装置将该驾驶数据文件中的历史驾驶控制参数转换为第一车型对应的历史驾驶控制参数，其中，该第一车型和该第二车型不同。这样该第一自动驾驶装置可以直接使用转换后的历史驾驶控制参数来优化其驾驶操作。In an optional implementation manner, determining to drive according to the target driving style may be: after obtaining the driving data file, determining to drive according to the target driving style. The driving data file includes at least one of historical road condition information, historical driving control parameters and historical driving behaviors of the automatic driving device driving according to the target driving style. Historical road condition information, historical driving control parameters, and historical driving behavior can be understood as historical driving data. Optionally, the way to obtain the driving data file may be to receive the driving data file from the first terminal; it may also be to obtain the driving data file from the server after receiving the first instruction from the second terminal. Wherein, the first instruction is used to instruct the automatic driving device to obtain the driving data file from the server. The first terminal and the second terminal may be portable devices such as mobile phones and tablet computers. Optionally, after establishing a communication connection with the automatic driving device, the first terminal imports the driving data file into the automatic driving device. For example, the first terminal is connected to a USB interface of the automatic driving device through a data cable, and imports a driving data file to the automatic driving device through the USB interface. Optionally, the server stores at least one driving data file, each driving data file includes historical driving data of a user driving an automatic driving device in a manual driving mode; the automatic driving device can, according to instructions from the second terminal, Get the corresponding driving data file from the server. Optionally, the historical driving data included in the driving data file obtained by the automatic driving device is the historical driving data of another vehicle model and the same automatic driving device in manual driving mode, and the automatic driving device can directly use the data in the driving data file. Historic driving control parameters optimize its driving operation. Optionally, the historical driving data included in the driving data file obtained by the automatic driving device is the historical driving data of another type of automatic driving device in the manual driving mode, and the automatic driving device controls the historical driving data in the driving data file. parameters are transformed to obtain historical driving control parameters which can be directly used as reference. For example, the first automatic driving device corresponds to the first vehicle type, the driving data file obtained by the first automatic driving device includes the historical driving data of the second automatic driving device of the second model in the manual driving mode, and the first automatic driving device will The historical driving control parameters in the driving data file are converted into historical driving control parameters corresponding to the first vehicle type, wherein the first vehicle type is different from the second vehicle type. In this way, the first automatic driving device can directly use the converted historical driving control parameters to optimize its driving operation.
在该实现方式中，用户将驾驶数据文件导入至自动驾驶装置，以便于该自动驾驶装置根据该驾驶数据文件中的历史驾驶数据对自动驾驶模式下的驾驶操作进一步优化，可以满足不同用户的驾驶风格。In this implementation, the user imports the driving data file into the automatic driving device, so that the automatic driving device can further optimize the driving operation in the automatic driving mode according to the historical driving data in the driving data file, which can meet the needs of different users. style.
图1的方法中未详述如何获取与当前路况相匹配的目标驾驶控制参数，即未详述步骤302的实现方式。下面描述获取与当前路况相匹配的目标驾驶控制参数的实现方式。How to obtain the target driving control parameters matching the current road conditions is not described in detail in the method of FIG. 1 , that is, the implementation of step 302 is not described in detail. The implementation manner of obtaining the target driving control parameters matching the current road conditions is described below.
在一些实施例中，自动驾驶装置获取与当前路况相匹配的目标驾驶控制参数可以是：先确定历史路况信息中与当前路况信息相匹配的目标路况信息；再获取历史驾驶控制参数中与该目标路况信息相匹配的驾驶控制参数，以得到该目标驾驶控制参数。自动驾驶装置存储有该历史路况信息和该历史驾驶控制参数，或者，该自动驾驶装置在执行步骤302之前，从其他设备，例如云服务器，获取到该历史路况信息和该历史驾驶控制参数。可选的，自动驾驶装置的驾驶风格数据中存储有该历史路况信息和该历史驾驶控制参数。In some embodiments, the automatic driving device may obtain the target driving control parameters matching the current road conditions: first determine the target road condition information matching the current road condition information in the historical road condition information; and then obtain the target driving control parameters in the historical driving control parameters. driving control parameters matched with road condition information to obtain the target driving control parameters. The automatic driving device stores the historical road condition information and the historical driving control parameters, or the automatic driving device obtains the historical road condition information and the historical driving control parameters from other devices, such as a cloud server, before performing step 302 . Optionally, the historical road condition information and the historical driving control parameters are stored in the driving style data of the automatic driving device.
下面先介绍如何确定历史路况信息中与当前路况信息相匹配的目标路况信息。The following firstly introduces how to determine the target traffic information in the historical traffic information that matches the current traffic information.
可选的，自动驾驶装置确定历史路况信息中与当前路况信息相匹配的目标路况信息可以是：确定该历史路况信息中与该当前路况信息相似度最高且相似度超过相似度阈值的一项历史路况信息，作为与该当前路况信息相匹配的目标路况信息。该目标路况信息可以为该驾驶风格数据库中的一项历史路况信息。该当前路况信息与该目标路况信息包括的条目相同。也就是说，该当前路况信息与该目标路况信息包括的内容相同。举例来说，当前路况信息包括表征当前路况的第一类参数至第十类参数，目标路况信息也包括该第一类参数至该第十类参数。在实际应用中，驾驶风格数据库中包括多条历史路况信息，每条历史路况信息与当前路况信息包括的条目相同。表1展示了历史路况信息和实时路况信息(当前路况信息)的一个举例。Optionally, the determination by the automatic driving device of the target road condition information in the historical road condition information that matches the current road condition information may be: determining a historical item in the historical road condition information that has the highest similarity with the current road condition information and the similarity exceeds a similarity threshold. The traffic condition information is used as the target traffic condition information matched with the current traffic condition information. The target road condition information may be a piece of historical road condition information in the driving style database. The current traffic condition information includes the same items as the target traffic condition information. That is to say, the content of the current traffic condition information and the target traffic condition information is the same. For example, the current road condition information includes parameters of the first type to the tenth type representing the current road condition, and the target road condition information also includes the parameters of the first type to the tenth type. In practical applications, the driving style database includes multiple pieces of historical road condition information, and each piece of historical road condition information includes the same items as the current road condition information. Table 1 shows an example of historical traffic information and real-time traffic information (current traffic information).
表1Table 1
从表1可以看出，历史路况信息和当前路况信息包括的条目相同。自动驾驶装置在确定按照目标驾驶风格进行驾驶之后，可以将当前路况信息分别与驾驶风格数据中的每条历史路况信息进行匹配，从而找出与该当前路况信息相匹配的目标路况信息。该目标路况信息可以是该驾驶风格数据库中与该当前路况信息相似度最高的一条历史路况信息。可选的，对当前路况信息与驾驶风格数据库中的一条历史路况信息进行匹配的过程可以是：计算当前路况信息和该条历史路况信息中每一项数据的相似度，若每项数据的相似度均超过该相似度阈值，则确定该当前路况信息和该条历史路况信息相匹配。该相似度阈值可以是0.8、0.9、095等。可选的，每项数据对应的相似度阈值不同。举例来说，前车距对应第一阈值，导航方向偏角对应第二阈值，该第一阈值和该第二阈值不同。若驾驶风格数据库中包括两条或两条以上与当前路况信息相匹配的历史路况信息，则将与该当前路况信息相似度最高的一条历史路况信息作为该目标路况信息。It can be seen from Table 1 that the historical traffic information and the current traffic information include the same items. After determining to drive according to the target driving style, the automatic driving device can match the current road condition information with each piece of historical road condition information in the driving style data, so as to find the target road condition information matching the current road condition information. The target road condition information may be a piece of historical road condition information with the highest similarity to the current road condition information in the driving style database. Optionally, the process of matching the current road condition information with a piece of historical road condition information in the driving style database may be: calculating the similarity between the current road condition information and each item of data in the historical road condition information, if the similarity of each item of data degree exceeds the similarity threshold, it is determined that the current road condition information matches the piece of historical road condition information. The similarity threshold may be 0.8, 0.9, 095, etc. Optionally, each item of data corresponds to a different similarity threshold. For example, the front vehicle distance corresponds to a first threshold, and the navigation direction deviation corresponds to a second threshold, and the first threshold is different from the second threshold. If the driving style database includes two or more pieces of historical road condition information matching the current road condition information, the piece of historical road condition information with the highest similarity to the current road condition information is used as the target road condition information.
下面介绍如何获取历史驾驶控制参数中与该目标路况信息相匹配的驾驶控制参数。The following describes how to obtain the driving control parameters matching the target road condition information among the historical driving control parameters.
在一些实施例中，自动驾驶装置获取与当前路况相匹配的目标驾驶控制参数可以是获取历史驾驶控制参数中与该目标路况信息相匹配的驾驶控制参数，以得到该目标驾驶控制参数。可选的，自动驾驶装置可以存储有历史路况信息中各条历史路况与历史驾驶控制参数中各条驾驶控制参数的对应关系，利用该对应关系可以确定任一条历史路况信息对应的一条历史驾驶控制参数。表2为历史路况信息与历史驾驶控制参数的对应关系表。In some embodiments, the acquisition of the target driving control parameter matching the current road condition by the automatic driving device may be acquiring the driving control parameter matching the target road condition information in the historical driving control parameters to obtain the target driving control parameter. Optionally, the automatic driving device may store the corresponding relationship between each historical road condition in the historical road condition information and each driving control parameter in the historical driving control parameters, and use the corresponding relationship to determine a historical driving control parameter corresponding to any piece of historical road condition information. parameter. Table 2 is a correspondence table between historical road condition information and historical driving control parameters.
表2Table 2
表2的第二行至最后一行中，每行包含一条历史路况信息以及与该条历史路况信息相匹配的一条历史驾驶控制参数。也就是说，第一历史路况信息至第M历史路况信息依次与第一历史驾驶控制参数至第M历史驾驶控制参数相匹配。M为大于1的整数。在实际应用中，自动驾驶装置可先确定历史路况信息中与当前路况信息相匹配的一条历史路况信息，再确定历史驾驶控制参数中与该条历史路况信息相匹配的历史驾驶控制参数。举例来说，自动驾驶装置确定当前路况信息与第二历史路况信息相匹配，则确定该第二历史路况信息(即目标路况信息)对应的第二历史驾驶控制参数为与当前路况相匹配的目标驾驶控制参数。In the second row to the last row of Table 2, each row contains a piece of historical road condition information and a piece of historical driving control parameter matching the piece of historical road condition information. That is to say, the first to Mth historical road condition information are sequentially matched with the first to Mth historical driving control parameters. M is an integer greater than 1. In practical applications, the automatic driving device may first determine a piece of historical road condition information that matches the current road condition information, and then determine a historical driving control parameter that matches the piece of historical road condition information among the historical driving control parameters. For example, the automatic driving device determines that the current road condition information matches the second historical road condition information, and then determines that the second historical driving control parameter corresponding to the second historical road condition information (that is, the target road condition information) is the target that matches the current road condition driving control parameters.
在该实现方式中，自动驾驶装置可以快速、准确地获取与当前路况相匹配的驾驶控制参数。In this implementation manner, the automatic driving device can quickly and accurately acquire driving control parameters that match the current road conditions.
自动驾驶装置按照目标驾驶控制参数在当前路况下进行驾驶可以实现：沿当前道路行驶、向左侧道路换道、向右侧道路换道、停车、跟车、调头、泊车、紧急刹车、道内避障等驾驶行为。然而，当自动驾驶装置按照目标驾驶控制参数在当前路况下进行驾驶可实现的第二驾驶行为与自动驾驶系统根据当前路况确定的符合安全驾驶标准和交规的第一驾驶行为不同时，执行该第二驾驶行为很可能不符合安全驾驶标准或交规。下面介绍一种能有效避免按照目标驾驶控制参数在当前路况下进行驾驶不符合安全驾驶标准或交规的方式。The automatic driving device can drive under the current road conditions according to the target driving control parameters: drive along the current road, change lanes to the left road, change lanes to the right road, stop, follow the car, turn around, park, emergency brake, in-road Driving behavior such as obstacle avoidance. However, when the second driving behavior achievable by the automatic driving device driving under the current road conditions according to the target driving control parameters is different from the first driving behavior determined by the automatic driving system according to the current road conditions in compliance with safe driving standards and traffic regulations, the second driving behavior is executed. 2. The driving behavior may not comply with safe driving standards or traffic regulations. The following describes a method that can effectively avoid driving in accordance with the target driving control parameters under the current road conditions and does not comply with safe driving standards or traffic regulations.
可选的，自动驾驶装置在执行步骤303之前，执行如下操作：确定按照该默认驾驶风格在该当前路况下进行驾驶待执行的第一驾驶行为；确定驾驶风格数据库中与该当前路况相匹配的第二驾驶行为，该第二驾驶行为为该自动驾驶装置按照该目标驾驶风格在该当前路况下进行驾驶的历史驾驶行为；在该第一驾驶行为与该第二驾驶行为相同的情况下，获取与该当前路况相匹配的该目标驾驶控制参数。可以理解，若该第一驾驶行为与该第二驾驶行为不同，则不从历史驾驶控制参数中获取与当前路况相匹配的驾驶控制参数，而是按照默认驾驶风格进行驾驶。可选的，驾驶风格数据库中的历史驾驶行为的类别与自动驾驶系统根据当前路况可做出的驾驶行为(即系统驾驶行为)的类别相同。也就是说，历史驾驶行为的类别与系统驾驶行为的类别一致，每种类别由数字表示，例如：0表示沿当前道路行驶，1表示向左测道路换道，2表示向右侧道路换道，3表示停车，4表示跟车，5表示调头，6表示泊车，7表示紧急刹车，8表示道内避障等等。在实际应用中，若表示自动驾驶系统根据当前路况做出的驾驶行为的数字与表示与该当前路况匹配的历史驾驶行为的数字不同，则系统驾驶行为与历史驾驶行为不同。Optionally, before performing step 303, the automatic driving device performs the following operations: determine the first driving behavior to be executed for driving under the current road condition according to the default driving style; determine the driving behavior in the driving style database that matches the current road condition; The second driving behavior, the second driving behavior is the historical driving behavior of the automatic driving device driving under the current road condition according to the target driving style; when the first driving behavior is the same as the second driving behavior, obtain The target driving control parameter matched with the current road condition. It can be understood that if the first driving behavior is different from the second driving behavior, the driving control parameters matching the current road conditions are not obtained from the historical driving control parameters, but the driving is performed according to the default driving style. Optionally, the categories of the historical driving behaviors in the driving style database are the same as the categories of driving behaviors (ie, system driving behaviors) that the automatic driving system can make according to the current road conditions. That is to say, the category of historical driving behavior is consistent with the category of system driving behavior, and each category is represented by a number, for example: 0 means driving along the current road, 1 means changing lanes to the left measuring road, and 2 means changing lanes to the right road , 3 means stop, 4 means following the car, 5 means U-turn, 6 means parking, 7 means emergency braking, 8 means avoiding obstacles in the road, etc. In practical applications, if the number indicating the driving behavior of the automatic driving system based on the current road conditions is different from the number indicating the historical driving behavior matching the current road conditions, the system driving behavior is different from the historical driving behavior.
在该实现方式中，在当前路况匹配的历史驾驶行为与当前确定的在当前路况下待执行的驾驶行为相同的情况下，获取与该当前路况相匹配的驾驶控制参数；可以有效避免自动驾驶装置执行的驾驶行为不符合安全驾驶标准或交规，也可避免从历史驾驶控制参数中获取与当前路况相匹配的驾驶控制参数的操作。In this implementation, when the historical driving behavior matched by the current road condition is the same as the currently determined driving behavior to be executed under the current road condition, the driving control parameters matching the current road condition are obtained; the automatic driving device can effectively avoid The executed driving behavior does not comply with safe driving standards or traffic regulations, and the operation of obtaining driving control parameters that match current road conditions from historical driving control parameters can also be avoided.
下面描述如何确定与当前路况相匹配的第二驾驶行为。一种可选的实现方式如下：在该驾驶风格数据库中包括与该当前路况信息相匹配的目标路况信息的情况下，确定该驾驶风格数据库中该目标路况信息对应的该第二驾驶行为；该驾驶风格数据库包括至少一项历史路况信息，以及该至少一项历史路况信息与驾驶行为的对应关系。自动驾驶装置可以根据该对应关系，确定该目标路况信息对应的该第二驾驶行为。由于前述实施例已描述了确定与当前路况信息相匹配的目标路况信息的实现方式，下面主要描述如何确定驾驶风格数据库中该目标路况信息对应的第二驾驶行为。表3为一种历史路况信息与历史驾驶行为的对应关系表。The following describes how to determine the second driving behavior that matches the current road condition. An optional implementation manner is as follows: if the driving style database includes target road condition information matching the current road condition information, determine the second driving behavior corresponding to the target road condition information in the driving style database; The driving style database includes at least one piece of historical road condition information and the corresponding relationship between the at least one piece of historical road condition information and driving behavior. The automatic driving device may determine the second driving behavior corresponding to the target road condition information according to the corresponding relationship. Since the foregoing embodiments have described the implementation of determining the target road condition information matching the current road condition information, the following mainly describes how to determine the second driving behavior corresponding to the target road condition information in the driving style database. Table 3 is a correspondence table between historical road condition information and historical driving behavior.
表3table 3
表3第二行至最后一行中，每行包含一条历史路况信息以及与该条历史路况信息相匹配的一条历史驾驶行为。也就是说，第一历史路况信息至第M历史路况信息依次与第一历史驾驶行为至第M历史驾驶行为相匹配。M为大于1的整数。在实际应用中，自动驾驶装置可先确定历史路况信息中与当前路况信息相匹配的一条历史路况信息，再确定历史驾驶行为中与该条历史路况信息相匹配的一条历史驾驶行为。举例来说，若自动驾驶装置确定当前路况信息与第二历史路况信息相匹配，则该第二历史路况信息(即目标路况信息)对应的第二历史驾驶行为为与当前路况相匹配的第二驾驶行为。可选的，表3第二行至最后一行中任意两行包括的历史路况信息均不同，表3第二行至最后一行中任意两行包括的历史驾驶行为相同或不同。也就是说，不同的历史路况信息对应的历史驾驶行为可以相同。In the second row to the last row of Table 3, each row contains a piece of historical road condition information and a piece of historical driving behavior matching the piece of historical road condition information. That is to say, the first historical road condition information to the Mth historical road condition information are sequentially matched with the first historical driving behavior to the Mth historical driving behavior. M is an integer greater than 1. In practical applications, the automatic driving device may first determine a piece of historical road condition information that matches the current road condition information, and then determine a piece of historical driving behavior that matches the piece of historical road condition information among the historical driving behaviors. For example, if the automatic driving device determines that the current road condition information matches the second historical road condition information, the second historical driving behavior corresponding to the second historical road condition information (that is, the target road condition information) is the second historical driving behavior that matches the current road condition. driving behavior. Optionally, the historical road condition information contained in any two lines from the second to the last line of Table 3 are different, and the historical driving behaviors included in any two lines from the second to the last line of Table 3 are the same or different. That is to say, the historical driving behaviors corresponding to different historical road condition information may be the same.
可选的，自动驾驶装置可存储有历史路况信息与历史驾驶控制参数的对应关系、历史路况信息与历史驾驶行为的对应关系，以及历史驾驶控制参数与历史驾驶行为的对应关系。表4为一种历史路况信息、历史驾驶行为以及历史驾驶控制参数的对应关系表。可选的，自动驾驶装置获得得驾驶数据文件包括这三种对应关系。Optionally, the automatic driving device may store a correspondence between historical road condition information and historical driving control parameters, a correspondence between historical road condition information and historical driving behavior, and a corresponding relationship between historical driving control parameters and historical driving behavior. Table 4 is a correspondence table of historical road condition information, historical driving behavior, and historical driving control parameters. Optionally, the driving data file obtained by the automatic driving device includes these three correspondences.
表4Table 4
表4包含了历史路况信息与历史驾驶控制参数的对应关系，历史驾驶控制参数与历史驾驶行为的对应关系以及历史路况信息与历史驾驶行为的对应关系，共三种对应关系。可选的，自动驾驶装置可以存储有该表4或者表征该表4包含的三种对应关系的内容。应理解，自动驾驶装置根据这三种对应关系，可以快速、准确地确定任一种历史路况信息对应的历史驾驶行为，以及任一种历史路况信息对应的历史驾驶控制参数。Table 4 includes the corresponding relationship between historical road condition information and historical driving control parameters, the corresponding relationship between historical driving control parameters and historical driving behavior, and the corresponding relationship between historical road condition information and historical driving behavior. There are three corresponding relationships. Optionally, the automatic driving device may store the table 4 or content representing the three corresponding relationships contained in the table 4. It should be understood that the automatic driving device can quickly and accurately determine the historical driving behavior corresponding to any kind of historical road condition information and the historical driving control parameters corresponding to any kind of historical road condition information according to the three corresponding relationships.
在该实现方式中，自动驾驶装置可以快速、准确地获取与当前路况相匹配的驾驶控制行为。In this implementation manner, the automatic driving device can quickly and accurately acquire the driving control behavior that matches the current road conditions.
由上述描述可以看出，自动驾驶装置在获取与当前路况相匹配的目标驾驶控制参数之前，需要将当前路况信息与驾驶风格数据库中历史路况进行匹配(即路况匹配)以得到目标路况信息，以及将自动驾驶装置确定的在当前路况下待执行的第一驾驶行为与该目标路况信息对应的第二驾驶行为进行匹配(即驾驶行为匹配)。下面结合路况匹配和驾驶行为匹配的示意图，来进一步描述这两个匹配过程。It can be seen from the above description that before the automatic driving device obtains the target driving control parameters that match the current road conditions, it needs to match the current road condition information with the historical road conditions in the driving style database (that is, road condition matching) to obtain the target road condition information, and The first driving behavior determined by the automatic driving device to be executed under the current road condition is matched with the second driving behavior corresponding to the target road condition information (ie driving behavior matching). The following two matching processes are further described in conjunction with the schematic diagrams of road condition matching and driving behavior matching.
图4为本申请实施例提供的一种路况匹配和驾驶行为匹配的示意图。图4中，黑色矩形表示自车，箭头表示车辆的行驶方向。在图4的左半部分中，当前路况与历史路况中的目标路况匹配，自动驾驶系统在当前路况下决策的驾驶行为与该目标路况对应的历史驾驶行为匹配，自动驾驶装置获取与当前路况相匹配的目标驾驶控制参数并按照该目标驾驶控制参数进行驾驶。在图4的右半部分中，当前路况与历史路况中的参考路况匹配，自动驾驶系统在当前路况下决策的驾驶行为与该参考路况对应的历史驾驶行为不匹配，自动驾驶装置按照自动驾驶系统决策的驾驶行为进行驾驶。应理解，图4中的匹配过程仅是一种示例。从图4可以看出，自动驾驶装置在获取目标驾驶控制参数之前，需要完成路况匹配和驾驶行为匹配。FIG. 4 is a schematic diagram of road condition matching and driving behavior matching provided by an embodiment of the present application. In FIG. 4 , the black rectangle represents the own vehicle, and the arrow represents the traveling direction of the vehicle. In the left half of Fig. 4, the current road condition matches the target road condition in the historical road condition, the driving behavior determined by the automatic driving system under the current road condition matches the historical driving behavior corresponding to the target road condition, and the automatic driving device obtains the target road condition corresponding to the current road condition. matching target driving control parameters and driving according to the target driving control parameters. In the right half of Figure 4, the current road conditions match the reference road conditions in the historical road conditions, and the driving behavior determined by the automatic driving system under the current road conditions does not match the historical driving behavior corresponding to the reference road conditions. Decision-making driving behavior for driving. It should be understood that the matching process in Fig. 4 is only an example. It can be seen from Figure 4 that the automatic driving device needs to complete road condition matching and driving behavior matching before obtaining the target driving control parameters.
在该实现方式中，在当前路况匹配的历史驾驶行为与当前确定的在当前路况下待执行的驾驶行为相同的情况下，获取与该当前路况相匹配的驾驶控制参数；可以有效避免自动驾驶装置执行的驾驶行为不符合安全驾驶标准或交规。In this implementation, when the historical driving behavior matched by the current road condition is the same as the currently determined driving behavior to be executed under the current road condition, the driving control parameters matching the current road condition are obtained; the automatic driving device can effectively avoid The driving behavior performed does not comply with safe driving standards or traffic regulations.
可选的，自动驾驶装置在执行步骤303之前，可以检查在当前路况下按照目标驾驶控制参数是否符合安全驾驶标准和交规。可选的，自动驾驶装置上的仲裁器根据两个要素判断目标驾驶控制参数是否作为最后的输出，一个要素是交通规范，另一个要素是安全性。在这两个要素都满足的情况下，自动驾驶装置采用历史驾驶控制参数(即按照目标驾驶控制参数进行驾驶)，否则，采用自动驾驶系统输出的驾驶控制参数(即按照默认驾驶参数进行驾驶)。可选的，仲裁器的功能由计算机系统112实现。下面介绍如何检查在当前路况下按照目标驾驶控制参数进行驾驶是否符合安全驾驶标准和交规。Optionally, before performing step 303, the automatic driving device may check whether the target driving control parameters comply with the safe driving standards and traffic regulations under the current road conditions. Optionally, the arbitrator on the automatic driving device judges whether the target driving control parameter is the final output according to two elements, one element is traffic regulation, and the other element is safety. When both elements are satisfied, the automatic driving device adopts the historical driving control parameters (that is, drives according to the target driving control parameters), otherwise, uses the driving control parameters output by the automatic driving system (that is, drives according to the default driving parameters) . Optionally, the function of the arbitrator is implemented by the computer system 112 . The following describes how to check whether driving according to the target driving control parameters under the current road conditions complies with safe driving standards and traffic regulations.
1、交通规范检查：当前帧(即当前时刻)的交规由速度上限，下限，车辆朝向范围，车辆所在位置区间等一系列参数表示，以上参数根据当前路况数据计算得出。1. Traffic regulation inspection: The traffic regulations of the current frame (that is, the current moment) are represented by a series of parameters such as the upper speed limit, the lower limit, the vehicle orientation range, and the vehicle location interval. The above parameters are calculated based on the current road condition data.
车速检查：目标驾驶控制参数中的速度值在交规速度区间内；Vehicle speed check: the speed value in the target driving control parameter is within the traffic speed range;
车辆朝向检查：根据目标驾驶控制参数计算下一帧车辆相对车道的朝向，判断是否在朝向范围内；Vehicle orientation check: Calculate the orientation of the vehicle relative to the lane in the next frame according to the target driving control parameters, and judge whether it is within the orientation range;
车辆位置检查：根据目标驾驶控制参数计算下一帧车辆所在车道的相对位置，判断是否在位置区间内。Vehicle position check: Calculate the relative position of the vehicle lane in the next frame according to the target driving control parameters, and judge whether it is within the position interval.
2、安全性检查：安全性检查根据目标驾驶控制参数计算下一帧车辆与其他障碍物的相对距离。相对距离大于最小阈值则符合安全。最小阈值由当前车速和系统最大反应时间计算得出。该值表示自车在多大的距离范围内实施应急制动能保证自车安全。上述的交通规范检查和安全性检查仅是本申请实施例提供的一种示例，应理解其他检查目标驾驶控制参数是否符合安全驾驶标准和交规的方式也属于本申请的保护范围。下面介绍提供一个冲裁器的判断示例。表5展示了当前路况以及系统信息。表6展示了目标驾驶控制参数。2. Safety check: The safety check calculates the relative distance between the vehicle and other obstacles in the next frame according to the target driving control parameters. Relative distances greater than the minimum threshold are considered safe. The minimum threshold is calculated from the current vehicle speed and the maximum system reaction time. This value indicates how far the self-vehicle can implement emergency braking to ensure the safety of the self-vehicle. The above-mentioned traffic regulation inspection and safety inspection are only an example provided by the embodiment of the present application, and it should be understood that other methods of checking whether the target driving control parameters comply with the safe driving standards and traffic regulations also belong to the protection scope of the present application. The following introduces a judgment example of a puncher. Table 5 shows the current road conditions and system information. Table 6 shows the target driving control parameters.
表5table 5
表6Table 6
根据以上数据，冲裁器可以确定目标驾驶控制参数中的纵向速度未超过道路限速，不违反交规；前方障碍物相距10米，根据纵向车速和系统最大响应时间计算，未有安全风险。因此，冲裁器判断目标驾驶控制参数符合安全驾驶标准和交规，将该目标驾驶控制参数发送到控制系统106，以便于控制系统106按照该目标驾驶控制参数进行驾驶。可选的，若冲裁器判断目标驾驶控制参数不符合安全驾驶标准或者交规，则自动驾驶装置按照其自动驾驶系统决策的驾驶控制参数进行驾驶。应理解，自动驾驶装置按照其自动驾驶系统决策的驾驶控制参数进行驾驶必定符合安全驾驶标准和交规。According to the above data, the blanking device can determine that the longitudinal speed in the target driving control parameters does not exceed the road speed limit and does not violate traffic regulations; the obstacles ahead are 10 meters apart, calculated according to the longitudinal speed and the maximum response time of the system, there is no safety risk. Therefore, the puncher judges that the target driving control parameter complies with safe driving standards and traffic regulations, and sends the target driving control parameter to the control system 106, so that the control system 106 can drive according to the target driving control parameter. Optionally, if the puncher judges that the target driving control parameters do not comply with safe driving standards or traffic regulations, the automatic driving device drives according to the driving control parameters determined by its automatic driving system. It should be understood that the driving of an automatic driving device according to the driving control parameters determined by its automatic driving system must comply with safe driving standards and traffic regulations.
自动驾驶装置通过检查在当前路况下按照目标驾驶控制参数是否符合安全驾驶标准和交规，以便于其驾驶操作均符合安全驾驶标准和交规。The automatic driving device checks whether the target driving control parameters comply with the safe driving standards and traffic regulations under the current road conditions, so that its driving operation complies with the safe driving standards and traffic regulations.
前述实施例描述了自动驾驶装置结合历史驾驶数据实现自动驾驶方法的方式。为更清楚地描述如何结合自动驾驶装置在手动驾驶模式下的历史驾驶数据来优化自动驾驶系统的驾驶操作，下面通过一个具体示例进一步来描述。The above-mentioned embodiments have described how the automatic driving device implements the automatic driving method in combination with historical driving data. In order to more clearly describe how to combine the historical driving data of the automatic driving device in the manual driving mode to optimize the driving operation of the automatic driving system, a specific example will be used for further description below.
图5为本申请实施例提供的另一种自动驾驶方法流程图，如图5所示，该方法可包括：FIG. 5 is a flow chart of another automatic driving method provided in the embodiment of the present application. As shown in FIG. 5, the method may include:
501、自动驾驶装置采集当前路况信息。501. The automatic driving device collects current road condition information.
可选的，该自动驾驶装置通过多种传感器来采集路况信息，并对采集到的原始路况信息做加工处理，以得到可准确反映当前路况的该当前路况信息。Optionally, the automatic driving device collects road condition information through various sensors, and processes the collected original road condition information to obtain the current road condition information that can accurately reflect the current road condition.
502、自动驾驶装置上的自动驾驶系统根据当前路况决策出待执行第一驾驶行为。502. The automatic driving system on the automatic driving device determines the first driving behavior to be executed according to the current road condition.
503、自动驾驶装置上的自动驾驶系统根据当前路况决策出待执行默认驾驶控制参数。503. The automatic driving system on the automatic driving device determines the default driving control parameters to be executed according to the current road conditions.
步骤501至步骤503均为自动驾驶系统实现的操作。本申请中，默认驾驶控制参数与实时驾驶控制参数是同一概念，均是自动驾驶装置按照预设决策机制决策出的驾驶控制参数。Steps 501 to 503 are all operations implemented by the automatic driving system. In this application, default driving control parameters and real-time driving control parameters are the same concept, and both are driving control parameters determined by the automatic driving device according to a preset decision-making mechanism.
504、自动驾驶装置判断历史路况信息中是否存在与当前路况相匹配的目标路况信息。504. The automatic driving device judges whether there is target road condition information matching the current road condition in the historical road condition information.
若是，执行步骤505；若否，执行步骤510。If yes, go to step 505; if not, go to step 510.
505、自动驾驶装置确定历史驾驶行为中与目标路况信息相匹配的第二驾驶行为。505. The automatic driving device determines a second driving behavior that matches the target road condition information among historical driving behaviors.
506、自动驾驶装置判断第一驾驶行为和第二驾驶行为是否相同。506. The automatic driving device judges whether the first driving behavior is the same as the second driving behavior.
若是，执行步骤507；若否，执行步骤510。If yes, go to step 507; if not, go to step 510.
507、自动驾驶装置获取历史驾驶控制参数中与目标路况信息和/或第二驾驶行为相匹配的目标驾驶控制参数。507. The automatic driving device acquires a target driving control parameter that matches the target road condition information and/or the second driving behavior among historical driving control parameters.
508、自动驾驶装置判断按照目标驾驶控制参数进行驾驶是否满足安全驾驶标准和交规。508. The automatic driving device judges whether driving according to the target driving control parameters meets safe driving standards and traffic regulations.
若是，执行步骤509；若否，执行步骤510。If yes, go to step 509; if not, go to step 510.
509、自动驾驶装置按照目标驾驶控制参数进行驾驶。509. The automatic driving device drives according to the target driving control parameters.
510、自动驾驶装置按照默认驾驶控制参数进行驾驶。510. The automatic driving device drives according to default driving control parameters.
从图5可以看出，步骤501至步骤503、步骤510是自动驾驶装置按照自动驾驶系统决策的驾驶行为以及驾驶控制参数进行驾驶，对应默认驾驶风格；步骤504至步骤509是自动驾驶装置根据历史驾驶数据进行驾驶，对应目标驾驶风格。在该实施例中，自动驾驶装置在行驶时根据当前的路况数据，系统驾驶行为(即自动驾驶系统决策的驾驶行为)与历史路况数据，历史驾驶行为一一进行匹配；匹配成功后后，由仲裁器判断当前时刻对应的历史控制数据是否满足安全及交通规则，满足则根据历史控制数据向车辆驱动发送控制指令，不满足则向车辆驱动发送自动驾驶控制指令。It can be seen from Figure 5 that from step 501 to step 503 and step 510, the automatic driving device drives according to the driving behavior and driving control parameters determined by the automatic driving system, corresponding to the default driving style; from step 504 to step 509, the automatic driving device drives according to the historical Driving data for driving, corresponding to the target driving style. In this embodiment, the automatic driving device matches the current road condition data, the system driving behavior (that is, the driving behavior determined by the automatic driving system) with the historical road condition data and the historical driving behavior one by one when driving; after the matching is successful, the The arbitrator judges whether the historical control data corresponding to the current moment satisfies the safety and traffic rules. If it is satisfied, it will send a control command to the vehicle driver according to the historical control data. If it is not satisfied, it will send an automatic driving control command to the vehicle driver.
本申请实施例，自动驾驶装置结合历史驾驶控制对其驾驶操作进一步优化，在保证其驾驶操作符合安全驾驶标准和交规的前提下，可满足不同用户的个性化驾驶要求。In the embodiment of the present application, the automatic driving device further optimizes its driving operation in combination with historical driving control, and can meet the personalized driving requirements of different users on the premise of ensuring that its driving operation complies with safe driving standards and traffic regulations.
前述实施例描述了如何优化自动驾驶装置的驾驶操作的自动驾驶方法，下面来描述如何得到前述实施例中的驾驶数据文件的方法。The aforementioned embodiments describe how to optimize the automatic driving method of the driving operation of the automatic driving device, and the following describes how to obtain the driving data file in the aforementioned embodiments.
图6为本申请实施例提供的一种驾驶数据文件生成方法流程图，如图6所示，该方法可包括：Fig. 6 is a flow chart of a driving data file generation method provided by the embodiment of the present application. As shown in Fig. 6, the method may include:
601、自动驾驶装置获取历史路况信息和历史驾驶控制参数。601. The automatic driving device acquires historical road condition information and historical driving control parameters.
该历史路况信息和该历史驾驶控制参数分别为自动驾驶装置在驾驶员手动驾驶的过程中采集的路况信息以及驾驶控制参数，该历史路况信息与该历史驾驶控制参数在时间维度相对应。可选的，图6方法的执行主体为电子设备，例如云服务器，该电子设备可从自动驾驶装置获取历史路况信息和历史驾驶控制参数，并执行步骤602以及步骤603以得到驾驶数据文件。The historical road condition information and the historical driving control parameters are respectively road condition information and driving control parameters collected by the automatic driving device during manual driving by the driver, and the historical road condition information corresponds to the historical driving control parameters in the time dimension. Optionally, the execution body of the method in FIG. 6 is an electronic device, such as a cloud server, which can obtain historical road condition information and historical driving control parameters from the automatic driving device, and execute steps 602 and 603 to obtain driving data files.
602、自动驾驶装置根据该历史路况信息和该历史驾驶控制参数，确定历史驾驶行为。602. The automatic driving device determines historical driving behaviors according to the historical road condition information and the historical driving control parameters.
可选的，该历史路况信息包括N条路况信息，该历史驾驶控制参数包括N条驾驶控制参数，该N条路况信息与该N条驾驶控制参数一一对应；该根据该历史路况信息和该历史驾驶控制参数，确定历史驾驶行为包括：根据参考路况信息和参考驾驶控制参数，确定参考驾驶行为。其中，该参考驾驶行为包含于该历史驾驶行为；该参考路况信息包含于该N条路况信息，该参考驾驶控制参数包含于该N条驾驶控制参数且与该参考路况信息相对应，N为大于1的整数。可选的，自动驾驶装置可以根据一条历史路况信息以及与该条历史路况信息相对应的一条历史驾驶控制参数确定一个历史驾驶行为。可选的，自动驾驶装置可以根据多条历史路况信息以及与该多条历史路况信息相对应的多条历史驾驶控制参数确定一个历史驾驶行为。Optionally, the historical road condition information includes N pieces of road condition information, the historical driving control parameters include N pieces of driving control parameters, and the N pieces of road condition information are in one-to-one correspondence with the N pieces of driving control parameters; The historical driving control parameter and determining the historical driving behavior include: determining the reference driving behavior according to the reference road condition information and the reference driving control parameter. Wherein, the reference driving behavior is included in the historical driving behavior; the reference road condition information is included in the N pieces of road condition information, the reference driving control parameters are included in the N pieces of driving control parameters and correspond to the reference road condition information, and N is greater than Integer of 1. Optionally, the automatic driving device may determine a historical driving behavior according to a piece of historical road condition information and a piece of historical driving control parameter corresponding to the piece of historical road condition information. Optionally, the automatic driving device may determine a historical driving behavior according to multiple pieces of historical road condition information and multiple pieces of historical driving control parameters corresponding to the multiple pieces of historical road condition information.
可选的，自动驾驶装置在根据参考路况信息和参考驾驶控制参数确定参考驾驶行为之前可执行如下操作：根据该历史路况信息和该历史驾驶控制参数在时间维度的对应关系，建立目标数据库(即key-value数据库)；从该目标数据库中获取该参考路况信息和该参考驾驶控制参数。其中，该目标数据库包括该N条路况信息与该N条驾驶控制参数的一一对应关系。上述表3可以为该目标数据库的一种示例。Optionally, the automatic driving device may perform the following operations before determining the reference driving behavior according to the reference road condition information and the reference driving control parameters: according to the corresponding relationship between the historical road condition information and the historical driving control parameters in the time dimension, establish a target database (i.e. key-value database); obtain the reference road condition information and the reference driving control parameters from the target database. Wherein, the target database includes a one-to-one correspondence between the N pieces of road condition information and the N pieces of driving control parameters. The above Table 3 may be an example of the target database.
603、自动驾驶装置将该历史驾驶行为、该历史路况信息以及该历史驾驶控制参数作为一个整体存储，以得到驾驶数据文件。603. The automatic driving device stores the historical driving behavior, the historical road condition information, and the historical driving control parameters as a whole to obtain a driving data file.
可选的，自动驾驶装置将该历史驾驶行为按照该目标数据库的格式存储至该目标数据库，以得到该驾驶数据文件。其中，该历史驾驶行为按照时间顺序分别与该历史路况信息以及该历史驾驶控制参数相对应。表4可以为驾驶数据文件的一种示例。在实际应用中，自动驾驶装置可按照key-value数据库的格式存储历史路况信息、历史驾驶控制参数以及历史驾驶行为，此时每条数据包括历史路况信息，历史驾驶控制参数和历史驾驶行为，称为驾驶数据文件。Optionally, the automatic driving device stores the historical driving behavior in the target database according to the format of the target database, so as to obtain the driving data file. Wherein, the historical driving behavior respectively corresponds to the historical road condition information and the historical driving control parameters in chronological order. Table 4 may be an example of a driving data file. In practical applications, the automatic driving device can store historical road condition information, historical driving control parameters, and historical driving behavior in the format of a key-value database. At this time, each piece of data includes historical road condition information, historical driving control parameters, and historical driving behavior. for driving data files.
本申请实施例中，根据历史路况信息和历史驾驶控制参数确定历史驾驶行为，进而将历史驾驶行为、历史路况信息以及历史驾驶控制参数作为一个整体存储以得到驾驶数据文件；可以高效的生成包含一个用户驾驶风格的驾驶数据文件。In the embodiment of the present application, the historical driving behavior is determined according to the historical road condition information and historical driving control parameters, and then the historical driving behavior, historical road condition information and historical driving control parameters are stored as a whole to obtain the driving data file; it is possible to efficiently generate a file containing a A driving data file of the user's driving style.
下面首先描述自动驾驶装置如何获得历史路况信息以及历史驾驶控制参数的方式。在一个实施例中，自动驾驶装置可执行如下步骤来获得历史路况信息以及历史驾驶控制参数：The following firstly describes how the automatic driving device obtains historical road condition information and historical driving control parameters. In one embodiment, the automatic driving device may perform the following steps to obtain historical road condition information and historical driving control parameters:
第一步：自动驾驶装置在用户驾驶的过程中，通过安装的多种传感器，包括激光雷达，毫米波雷达，超声波雷达，单目或双目摄像头等等设备，收集交通流信息和路面信息，例如交通指示牌，红绿灯，车道线，周围车辆，行人和障碍物信息等原始数据。同时，自动驾驶装置记录每一类数据的收集时间，时间单位可以为妙，各类数据按照时间维度存储。各路面信息反映了不同的路况数据。举例来说，交通指示牌：道路限速上限，限速下限，前方停止行车等等；红绿灯：是否停车，左转或右转；车道线：车辆行驶方向，转弯半径，两边车道方向，是否允许换道等；车辆，行人及障碍物：相对自车的位置，车道信息，相对速度等等。Step 1: During the driving process of the user, the automatic driving device collects traffic flow information and road surface information through various sensors installed, including lidar, millimeter wave radar, ultrasonic radar, monocular or binocular cameras, etc. For example, raw data such as traffic signs, traffic lights, lane lines, surrounding vehicles, pedestrians and obstacles. At the same time, the automatic driving device records the collection time of each type of data. The time unit can be better, and all kinds of data are stored according to the time dimension. Each road surface information reflects different road condition data. For example, traffic signs: road speed limit upper limit, speed limit lower limit, stop driving ahead, etc.; traffic lights: whether to stop, turn left or right; lane lines: vehicle driving direction, turning radius, direction of lanes on both sides, whether to allow Lane changing, etc.; vehicles, pedestrians and obstacles: relative to the position of the vehicle, lane information, relative speed, etc.
第二步：自动驾驶装置将收集到的所有原始数据通过融合、聚类等操作，抽象出各时刻下的路况信息，按照时间单位存储于存储器中，此为历史路况数据(也成为了历史路况信息)。举例来说，这一过程可采用聚类算法，包括K均值(K-Means)聚类算法，DBSCAN算法，Density-Peek Clustering算法对采集的点云数据进行聚类，从而确定各障碍物的位置。表7展示了自动驾驶装置对收集的原始数据进行处理得到的历史路况信息的一个示例。Step 2: The automatic driving device abstracts all the collected raw data through operations such as fusion and clustering, and abstracts the road condition information at each moment, and stores them in the memory according to the time unit. This is historical road condition data (also known as historical road condition information). For example, this process can use clustering algorithms, including K-Means (K-Means) clustering algorithm, DBSCAN algorithm, Density-Peek Clustering algorithm to cluster the collected point cloud data, so as to determine the position of each obstacle . Table 7 shows an example of historical road condition information obtained by processing the collected raw data by the automatic driving device.
表7Table 7
表7的第二行至最后一行中每行包括一条历史路况信息，其中，任意两条历史路况信息不同或不同。在实际应用中，历史路况信息中包括多条历史路况信息，每条历史路况信息表征一种路况。表7中，历史路况信息按照时间顺序存储，相邻两条历史路况信息的时间间隔为20s。表7仅为一种示例，在实际应用中，相邻两条历史路况信息的时间间隔可以是1s、2s、5s、10s、15s等，本申请实施例不作限定。Each row in the second row to the last row of Table 7 includes a piece of historical traffic information, wherein any two pieces of historical traffic information are different or different. In practical applications, the historical road condition information includes multiple pieces of historical road condition information, and each piece of historical road condition information represents a kind of road condition. In Table 7, the historical traffic information is stored in chronological order, and the time interval between two adjacent historical traffic information is 20s. Table 7 is just an example. In practical applications, the time interval between two pieces of adjacent historical road condition information may be 1s, 2s, 5s, 10s, 15s, etc., which is not limited in this embodiment of the present application.
第三步：自动驾驶装置通过传感器收集数据的同时，利用GPS导航系统和自车内的控制收集器(例如IMU和车内控制装置传感器)采集用户驾车时的控制数据，并按照同样的时间单位将控制数据存放于存储器。Step 3: While the automatic driving device collects data through the sensor, it uses the GPS navigation system and the control collector in the car (such as IMU and the sensor of the car control device) to collect the control data of the user while driving, and uses the same time unit Store control data in memory.
可选的，GPS导航系统收集自车定位信息，包括当前所在车道和坐标点，根据每两个时间帧的位置距离计算前一帧的车速。IMU是测量自车三轴姿态角(或角速率)以及加速度的装置。一个IMU包含了三个单轴的加速度计和三个单轴的陀螺，加速度计检测物体在载体坐标系统独立三轴的加速度信号，而陀螺检测载体相对于导航坐标系的角速度信号，测量自车在三维空间中的角速度和加速度，并以此解算出自车的姿态。控制传感器，如轮速传感器，也用于收集车辆速度和加速度数据。以上传感器收集的数据类型包括：纵向车速，加速度/减速度，角速度等。此数据为历史控制数据，也称为历史驾驶控制参数。表8展示了历史控制数据的一个示例。Optionally, the GPS navigation system collects the location information of the own vehicle, including the current lane and coordinate points, and calculates the vehicle speed in the previous frame according to the position distance between every two time frames. The IMU is a device that measures the three-axis attitude angle (or angular rate) and acceleration of the vehicle. An IMU contains three single-axis accelerometers and three single-axis gyroscopes. The accelerometer detects the acceleration signal of the object in the carrier coordinate system on three axes independently, while the gyroscope detects the angular velocity signal of the carrier relative to the navigation coordinate system, and measures the self-vehicle Angular velocity and acceleration in three-dimensional space, and use this to calculate the attitude of the vehicle. Control sensors, such as wheel speed sensors, are also used to collect vehicle speed and acceleration data. The types of data collected by the above sensors include: longitudinal vehicle speed, acceleration/deceleration, angular velocity, etc. This data is historical control data, also known as historical driving control parameters. Table 8 shows an example of historical control data.
表8Table 8
表8的第二行至最后一行中每行包括一条历史控制数据(即历史驾驶控制参数)。由于自动驾驶装置存储历史控制数据的时间单位与存储历史路况信息的时间单位相同，每一条历史路况信息分别对应一个历史控制数据。也就是说，各条历史路况信息与各条历史控制数据对应的时间点相同。例如，表7中第二行的历史路况信息与表8中第二行的历史控制数据对应同一个时间点(即时间帧)。Each row in the second row to the last row of Table 8 includes a piece of historical control data (ie, historical driving control parameters). Since the time unit for storing historical control data in the automatic driving device is the same as the time unit for storing historical road condition information, each piece of historical road condition information corresponds to a piece of historical control data. That is to say, each piece of historical road condition information corresponds to the same time point as each piece of historical control data. For example, the historical road condition information in the second row in Table 7 and the historical control data in the second row in Table 8 correspond to the same time point (ie, time frame).
第四步：当用户结束驾驶时，自动驾驶装置的存储器中收集了大量的历史路况数据和历史控制数据，将历史路况数据和历史控制数据按照时间维度的对应关系，建立一个key-value数据库。上述表2可以为key-value数据库的一个示例，该数据库中每一条数据包括一条历史路况信息和一条历史驾驶控制参数。针对该key-value数据库执行以下两项步骤：Step 4: When the user finishes driving, a large amount of historical road condition data and historical control data are collected in the memory of the automatic driving device, and a key-value database is established according to the corresponding relationship between the historical road condition data and historical control data in the time dimension. The above Table 2 may be an example of a key-value database, and each piece of data in the database includes a piece of historical road condition information and a piece of historical driving control parameter. Perform the following two steps against the key-value database:
步骤一：通过人工或自动驾驶装置自动删除重复和/或无效的部分数据条目。Step 1: Automatically delete duplicate and/or invalid partial data entries by manual or automatic driving device.
1)无效数据条目：某一项参数值为空或者与正常参数范围偏差较大。导致该问题的原因多为传感器输出失真。举例来说，某一条数据中的障碍物车辆速度为30，下一帧数据跳为40，则可断定感知数据出现失真，删除该条错误数据。1) Invalid data entry: A certain parameter value is empty or deviates greatly from the normal parameter range. The cause of this problem is mostly sensor output distortion. For example, if the obstacle vehicle speed in a certain piece of data is 30, and the next frame of data jumps to 40, it can be concluded that the perception data is distorted, and the wrong piece of data is deleted.
2)重复数据条目：此类数据条目根据相似度判断，若多项数据条目的所有参数值相似度在95％以上，保留其中一条数据，删除其余数据。可选的，若任意两条数据的历史路况数据和/或历史控制数据中相同类型数据相比相似度都在95％以上，则可以删除其中一条数据，保留另一条。举例来说，数据库中第一条数据和第十条数据中相同类型的数据相比相似度都在95％以上，则删除该第一条数据或该第十条数据。又举例来说，数据库中第二条数据的历史路况信息部分与第九条数据的历史路况信息部分相比，相同类型的数据的相似度均超过90％，删除该第二条数据或该第九条数据。表9和表10均为key-value数据库包括的部分数据。2) Duplicate data entry: This type of data entry is judged according to the similarity. If the similarity of all parameter values of multiple data entries is above 95%, one of the data is retained and the rest is deleted. Optionally, if any two pieces of data have a similarity of more than 95% in historical traffic data and/or historical control data of the same type, one piece of data can be deleted and the other piece of data can be kept. For example, if the similarity between the first piece of data and the same type of data in the tenth piece of data in the database is more than 95%, the first piece of data or the tenth piece of data is deleted. For another example, if the historical road condition information part of the second piece of data in the database is compared with the historical road condition information part of the ninth piece of data, the similarity of the same type of data exceeds 90%, and the second piece of data or the first piece of data should be deleted. Nine pieces of data. Table 9 and Table 10 are part of the data included in the key-value database.
表9Table 9
表10Table 10
表9的第二行和表10的第二行组成key-value数据库中的一条数据，表9的第三行和表10的第三行也组成key-value数据库中的一条数据。The second row of Table 9 and the second row of Table 10 constitute a piece of data in the key-value database, and the third row of Table 9 and the third row of Table 10 also constitute a piece of data in the key-value database.
从表9和表10可以看出，第100帧中的路况数据和控制数据和120帧中的路况数据和控制相似度都在95％以上，可删除其一。It can be seen from Table 9 and Table 10 that the similarity between the road condition data and control data in the 100th frame and the road condition data and control data in the 120th frame is above 95%, and one of them can be deleted.
步骤二：筛选后的数据精简成一个新的key-value数据库。该新的key-value数据库中的历史路况信息和历史控制数据分别为自动驾驶装置执行步骤601获取的历史路况信息和历史驾驶控制参数。可以理解，自动驾驶装置依次执行上述第一步至第四部以及步骤一至步骤二可以获得历史路况信息和历史驾驶控制参数。该新的key-value数据库中任意两条数据不同，并且key-value数据库中一条数据由历史路况数据和历史控制数据两部分组成，可参阅表2。Step 2: The filtered data is reduced to a new key-value database. The historical road condition information and historical control data in the new key-value database are respectively the historical road condition information and historical driving control parameters acquired by the automatic driving device in step 601 . It can be understood that the automatic driving device can obtain historical road condition information and historical driving control parameters by sequentially executing the first step to the fourth step and the first step to the second step. Any two pieces of data in the new key-value database are different, and one piece of data in the key-value database consists of two parts: historical traffic data and historical control data, see Table 2.
自动驾驶装置通过执行上述步骤，可以准确、快速地获取其在手动驾驶模式下的历史路况信息以及历史驾驶控制参数。另外，通过删除目标数据库中无效或重复的条目，可以有效地对该目标数据库进行精简和改善，以便于后续利用该目标数据库中的数据准确地确定历史驾驶行为。By performing the above steps, the automatic driving device can accurately and quickly obtain its historical road condition information and historical driving control parameters in the manual driving mode. In addition, by deleting invalid or repeated entries in the target database, the target database can be effectively streamlined and improved, so that the data in the target database can be used to accurately determine historical driving behaviors.
下面介绍一下如何生成驾驶数据文件的方式。The following describes how to generate driving data files.
该key-value数据库的每条数据作为输入，经过深度学习网络，学习出驾驶员的驾驶行为。具体如下：将key-value数据库中的每条数据输入至训练得到的驾驶行为预测网络进行处理，得到每条数据对应的历史驾驶行为。该驾驶行为预测网络可以是卷积神经网络，也可以是其他类型的神经网络。图7为本申请实施例提供的一种通过神经网络学习得到驾驶行为的示意图。其中，key-value数据库中的每一条数据作为该驾驶行为预测网络的输入，即输入的维度与该数据中的数据种类相等。可选的，采用CNN(卷积神经网络)作为训练模型，因输入数据具有局部相关性，例如车速，距离等数据对输出影响权重较大。该驾驶行为预测网络的输出为自动驾驶系统的行为决策空间，该决策空间为离散值，代表自动驾驶系统在某一时刻计算出的驾驶行为，包括道内行驶，换道，泊车，调头，停车等等。图8为本申请实施例提供的另一种通过神经网络学习得到驾驶行为的示意图。图8中两条路况数据和控制数据，通过训练学习出的结果都为换道(changelane)。在实际应用中，将key-value数据库中的每条数据均输入至该驾驶行为预测网络进行处理，得到每条数据对应的历史驾驶行为。最终，得到的驾驶行为数据按照key-value数据库的格式，同样存储在数据库中，此时每条数据包括历史路况数据，历史控制数据和驾驶行为数据，称为驾驶数据文件。Each piece of data in the key-value database is used as input, and the driver's driving behavior is learned through the deep learning network. The details are as follows: input each piece of data in the key-value database to the trained driving behavior prediction network for processing, and obtain the historical driving behavior corresponding to each piece of data. The driving behavior prediction network can be a convolutional neural network or other types of neural networks. FIG. 7 is a schematic diagram of a driving behavior learned through a neural network provided by an embodiment of the present application. Among them, each piece of data in the key-value database is used as the input of the driving behavior prediction network, that is, the dimension of the input is equal to the type of data in the data. Optionally, CNN (Convolutional Neural Network) is used as the training model, because the input data has local correlation, such as vehicle speed, distance and other data have a greater influence on the output weight. The output of the driving behavior prediction network is the behavior decision space of the automatic driving system, which is a discrete value, representing the driving behavior calculated by the automatic driving system at a certain moment, including driving in the lane, changing lanes, parking, turning around, parking and many more. FIG. 8 is a schematic diagram of another driving behavior learned through a neural network according to an embodiment of the present application. The two road condition data and control data in Fig. 8, the results learned through training are both lane changes (changelane). In practical applications, each piece of data in the key-value database is input to the driving behavior prediction network for processing, and the historical driving behavior corresponding to each piece of data is obtained. Finally, the obtained driving behavior data is also stored in the database in the format of a key-value database. At this time, each piece of data includes historical road condition data, historical control data and driving behavior data, which is called a driving data file.
针对不同驾驶员，重复以上步骤可获得大量驾驶数据文件，并可对文件以驾驶风格分类，可分为谨慎，正常和激进等不同类型。驾驶风格一般通过根据跟车距离，加减速幅度等等因素分类。例如跟车距离1-2个车位为正常；跟车距离3-4个车位为谨慎；跟车距离小于1个车位为激进。这样自动驾驶装置就可以获取不同类型的驾驶数据文件，以便于乘客选择不同的驾驶风格。For different drivers, a large number of driving data files can be obtained by repeating the above steps, and the files can be classified according to driving style, which can be divided into different types such as cautious, normal and aggressive. Driving styles are generally classified according to factors such as following distance, acceleration and deceleration range, and so on. For example, the following distance of 1-2 parking spaces is normal; the following distance of 3-4 parking spaces is cautious; the following distance of less than 1 parking space is radical. In this way, the automatic driving device can obtain different types of driving data files, so that passengers can choose different driving styles.
可选的，自动驾驶装置在获得驾驶数据文件之后，将该驾驶数据文件上传至服务器，或者，将该驾驶数据文件发送至目标终端，或者，将该驾驶数据文件存储至存储器。Optionally, after obtaining the driving data file, the automatic driving device uploads the driving data file to the server, or sends the driving data file to the target terminal, or stores the driving data file in the memory.
在该实现方式中，将驾驶数据文件上传至服务器或者将驾驶数据文件发送至目标终端，以便于用户将该驾驶数据文件从该服务器或该目标终端加载至自动驾驶装置，进而使得该自动驾驶装置按照自己的驾驶习惯进行驾驶。In this implementation, the driving data file is uploaded to the server or sent to the target terminal, so that the user loads the driving data file from the server or the target terminal to the automatic driving device, and then the automatic driving device Drive according to your own driving habits.
下面结合自动驾驶装置的结构来描述如何进行自动驾驶的过程。图9为本申请实施例提供的一种自动驾驶装置的结构示意图，如图9所示，该自动驾驶装置包括：传感器901、存储器902、处理器903以及总线904；其中，传感器901、存储器902、处理器903通过总线904实现彼此之间的通信连接。The following describes the process of how to perform automatic driving in combination with the structure of the automatic driving device. FIG. 9 is a schematic structural diagram of an automatic driving device provided in an embodiment of the present application. As shown in FIG. 9 , the automatic driving device includes: a sensor 901, a memory 902, a processor 903, and a bus 904; . The processors 903 are connected to each other through the bus 904 .
传感器901，用于采集当前路况信息；The sensor 901 is used to collect current road condition information;
存储器902，用于存储代码；memory 902, for storing codes;
处理器903通过读取该存储器中存储的该代码以用于执行如下操作：根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数；若存在，则获取该目标驾驶控制参数，并根据该目标驾驶控制参数以目标驾驶风格进行驾驶；该目标驾驶控制参数包括目标车辆的历史驾驶控制参数，该历史驾驶控制参数包括该目标车辆按照该目标驾驶风格进行驾驶得到的驾驶控制参数；若不存在，则根据实时驾驶控制参数以当前驾驶风格进行驾驶；该实时驾驶控制参数为该自动驾驶装置按照预设决策机制决策出的驾驶控制参数。The processor 903 is used to perform the following operations by reading the code stored in the memory: according to the current road condition information, query whether there is a target driving control parameter matching the current road condition information from the database; if yes, obtain The target driving control parameters, and driving with a target driving style according to the target driving control parameters; the target driving control parameters include historical driving control parameters of the target vehicle, and the historical driving control parameters include driving of the target vehicle according to the target driving style The obtained driving control parameter; if it does not exist, then drive with the current driving style according to the real-time driving control parameter; the real-time driving control parameter is the driving control parameter determined by the automatic driving device according to the preset decision-making mechanism.
可选的，传感器901对应于图1中的传感器系统104；处理器903对应于图1中的处理器113；存储器902对应于图1中的存储器114。在一些实施例中，传感器901可采集原始的路况信息，处理器903可对该原始的路况信息做加工处理以得到该当前路况信息。可选的，处理器903可通过控制系统106来控制自动驾驶装置按照实时驾驶控制参数或目标驾驶控制参数进行驾驶。Optionally, the sensor 901 corresponds to the sensor system 104 in FIG. 1 ; the processor 903 corresponds to the processor 113 in FIG. 1 ; and the memory 902 corresponds to the memory 114 in FIG. 1 . In some embodiments, the sensor 901 can collect original road condition information, and the processor 903 can process the original road condition information to obtain the current road condition information. Optionally, the processor 903 may control the automatic driving device to drive according to real-time driving control parameters or target driving control parameters through the control system 106 .
在具体实现过程中，传感器901具体用于执行步骤301中所提到的方法以及可以等同替换的方法；处理器903具体用于执行步骤302至步骤304中所提到的方法以及可以等同替换的方法。In the specific implementation process, the sensor 901 is specifically used to execute the method mentioned in step 301 and the method that can be equivalently replaced; the processor 903 is specifically used to execute the method mentioned in step 302 to step 304 and the method that can be equivalently replaced method.
在一个可选的实现方式中，该自动驾驶装置还包括：In an optional implementation, the automatic driving device also includes:
通信接口905，用于获取或接收驾驶数据文件；A communication interface 905, used to obtain or receive driving data files;
处理器903，还用于判断该驾驶数据文件是否包括该目标车辆按照该目标驾驶风格进行驾驶的历史路况信息、历史驾驶控制参数以及历史驾驶行为中的至少一项，若是，则执行该根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数的步骤。The processor 903 is further configured to determine whether the driving data file includes at least one of historical road condition information, historical driving control parameters, and historical driving behavior of the target vehicle driven according to the target driving style, and if so, execute the The current road condition information is a step of inquiring whether there is a target driving control parameter matching the current road condition information from the database.
可选的，通信接口905对应于图1中的用户接口116。例如，处理器113控制无线通信系统146从云服务器获取该驾驶数据文件。Optionally, the communication interface 905 corresponds to the user interface 116 in FIG. 1 . For example, the processor 113 controls the wireless communication system 146 to obtain the driving data file from the cloud server.
在该实现方式中，在获得驾驶数据文件之后，确定按照该目标驾驶风格进行驾驶；可以保证在按照目标驾驶风格进行驾驶之前已得到按照目标驾驶风格进行驾驶所需的历史驾驶数据，安全性高。In this implementation, after the driving data file is obtained, it is determined to drive according to the target driving style; it can be guaranteed that the historical driving data required for driving according to the target driving style has been obtained before driving according to the target driving style, and the safety is high .
在一个可选的实现方式中，通信接口905，用于接收用户输入的第三指令或者来自第三终端的第四指令；In an optional implementation manner, the communication interface 905 is configured to receive a third instruction input by a user or a fourth instruction from a third terminal;
处理器903，具体用于在通信接口905接收到该第三指令或者该第四指令的情况下，确定按照该目标驾驶风格进行驾驶；该第三指令和该第四指令均用于指示该自动驾驶装置按照该目标驾驶风格进行驾驶。The processor 903 is specifically configured to determine to drive according to the target driving style when the communication interface 905 receives the third instruction or the fourth instruction; both the third instruction and the fourth instruction are used to instruct the automatic The driving device drives according to the target driving style.
可选的，通信接口905为图1中的用户接口116或车载电脑148。例如，用户接口116中的无线通信系统146接收该第四指令。又例如，自动驾驶装置通过车载电脑148接收用户输入的第三指令。Optionally, the communication interface 905 is the user interface 116 or the vehicle computer 148 in FIG. 1 . For example, wireless communication system 146 in user interface 116 receives the fourth instruction. For another example, the automatic driving device receives the third instruction input by the user through the on-board computer 148 .
在该实现方式中，用户可以快速、方便地指示自动驾驶装置按照目标驾驶风格进行驾驶，用户体验好。In this implementation manner, the user can quickly and conveniently instruct the automatic driving device to drive according to the target driving style, and the user experience is good.
下面结合驾驶数据文件生成装置的结构来描述如何生成驾驶数据文件的过程。图10为本申请实施例提供的一种驾驶数据文件生成装置的结构示意图，如图10所示，该驾驶数据文件生成装置包括：存储器1001、处理器1002以及总线1003；存储器1001用于存储代码、历史路况信息以及历史驾驶控制参数；其中，存储器1001、处理器1002通过总线1003实现彼此之间的通信连接；处理器1002通过读取该存储器中存储的该代码以用于执行如下操作：从存储器1001中获取历史路况信息和历史驾驶控制参数；该历史路况信息和该历史驾驶控制参数分别为自动驾驶装置在驾驶员手动驾驶的过程中采集的路况信息以及驾驶控制参数，该历史路况信息与该历史驾驶控制参数在时间维度相对应；根据该历史路况信息和该历史驾驶控制参数，确定历史驾驶行为；将该历史驾驶行为、该历史路况信息以及该历史驾驶控制参数作为一个整体存储，以得到驾驶数据文件。该驾驶数据文件生成装置可以是自动驾驶装置，也可以是其他可执行数据处理的计算机设备，例如服务器等。The process of how to generate a driving data file will be described below in conjunction with the structure of the driving data file generating device. Fig. 10 is a schematic structural diagram of a driving data file generation device provided by an embodiment of the present application. As shown in Fig. 10, the driving data file generation device includes: a memory 1001, a processor 1002, and a bus 1003; the memory 1001 is used to store code , historical road condition information, and historical driving control parameters; wherein, the memory 1001 and the processor 1002 are connected to each other through the bus 1003; the processor 1002 is used to perform the following operations by reading the code stored in the memory: Obtain historical road condition information and historical driving control parameters in the memory 1001; the historical road condition information and the historical driving control parameters are respectively the road condition information and driving control parameters collected by the automatic driving device during the driver's manual driving, and the historical road condition information and The historical driving control parameters correspond to the time dimension; according to the historical road condition information and the historical driving control parameters, determine the historical driving behavior; store the historical driving behavior, the historical road condition information and the historical driving control parameters as a whole, to Get the driving data file. The driving data file generation device may be an automatic driving device, or other computer equipment capable of data processing, such as a server.
在具体实现过程中，处理器1002具体用于执行步骤601至步骤603中所提到的方法以及可以等同替换的方法。In a specific implementation process, the processor 1002 is specifically configured to execute the methods mentioned in step 601 to step 603 and methods that may be equivalently replaced.
在一个可选的实现方式中，驾驶数据文件生成装置还包括：In an optional implementation, the driving data file generation device also includes:
处理器1002，还用于根据该历史路况信息和该历史驾驶控制参数在时间维度的对应关系，建立目标数据库；该目标数据库包括该N条路况信息与该N条驾驶控制参数的一一对应关系；The processor 1002 is further configured to establish a target database according to the corresponding relationship between the historical road condition information and the historical driving control parameters in the time dimension; the target database includes the one-to-one correspondence between the N pieces of road condition information and the N pieces of driving control parameters ;
处理器1002，具体用于从该目标数据库中获取该参考路况信息和该参考驾驶控制参数。The processor 1002 is specifically configured to acquire the reference road condition information and the reference driving control parameters from the target database.
在该实现方式中，根据历史路况信息和历史驾驶控制参数在时间维度的对应关系，建立目标数据库，以便于根据历史路况信息和历史驾驶控制参数确定历史驾驶行为，操作简单。In this implementation, the target database is established according to the corresponding relationship between the historical road condition information and the historical driving control parameters in the time dimension, so as to determine the historical driving behavior according to the historical road condition information and the historical driving control parameters, and the operation is simple.
在一个可选的实现方式中，驾驶数据文件生成装置还包括：In an optional implementation, the driving data file generation device also includes:
通信接口1003，用于接收来自自动驾驶装置的历史路况信息与历史驾驶控制参数，或者，从服务器获取历史路况信息与历史驾驶控制参数。The communication interface 1003 is used to receive historical road condition information and historical driving control parameters from the automatic driving device, or obtain historical road condition information and historical driving control parameters from a server.
应理解以上定位装置以及自动驾驶装置中的各个单元的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。例如，以上各个单元可以为单独设立的处理元件，也可以集成在终端的某一个芯片中实现，此外，也可以以程序代码的形式存储于控制器的存储元件中，由处理器的某一个处理元件调用并执行以上各个单元的功能。此外各个单元可以集成在一起，也可以独立实现。这里的处理元件可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤或以上各个单元可以通过处理器元件中的硬件的集成逻辑电路或者软件形式的指令完成。该处理元件可以是通用处理器，例如中央处理器(英文：central processing unit，简称：CPU)，还可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(英文：application-specific integrated circuit，简称：ASIC)，或，一个或多个微处理器(英文：digital signal processor，简称：DSP)，或，一个或者多个现场可编程门阵列(英文：field-programmable gate array，简称：FPGA)等。It should be understood that the above division of each unit in the positioning device and the automatic driving device is only a division of logical functions, and may be fully or partially integrated into a physical entity or physically separated during actual implementation. For example, each of the above units can be a separate processing element, or can be integrated into a certain chip of the terminal, and can also be stored in the storage element of the controller in the form of program code, and processed by one of the processors. The components call and execute the functions of the above units. In addition, each unit can be integrated together or implemented independently. The processing element here may be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step of the above-mentioned method or each of the above-mentioned units can be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software. The processing element may be a general-purpose processor, such as a central processing unit (English: central processing unit, CPU for short), and may also be one or more integrated circuits configured to implement the above method, for example: one or more specific integrated circuits circuit (English: application-specific integrated circuit, referred to as ASIC), or, one or more microprocessors (English: digital signal processor, referred to as: DSP), or, one or more field programmable gate arrays (English: field-programmable gate array, referred to as: FPGA), etc.
在一些实施例中，所公开的方法可以实施为以机器可读格式被编码在计算机可读存储介质上的或者被编码在其它非瞬时性介质或者制品上的计算机程序指令。图11示意性地示出根据这里展示的至少一些实施例而布置的示例计算机程序产品的概念性局部视图，该示例计算机程序产品包括用于在计算设备上执行计算机进程的计算机程序。在一个实施例中，示例计算机程序产品1100是使用信号承载介质1101来提供的。该信号承载介质1101可以包括一个或多个程序指令1102，其当被一个或多个处理器运行时可以提供以上针对图9-图10描述的功能或者部分功能。因此，例如，参考图9中所示的实施例，方框901-905的一个或多个的功能的实现可以由与信号承载介质1101相关联的一个或多个指令来承担。此外，图11中的程序指令1102也描述示例指令。In some embodiments, the disclosed methods can be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of manufacture. Figure 11 schematically illustrates a conceptual partial view of an example computer program product comprising a computer program for executing a computer process on a computing device, arranged in accordance with at least some embodiments presented herein. In one embodiment, the example computer program product 1100 is provided using a signal bearing medium 1101 . The signal bearing medium 1101 may include one or more program instructions 1102 which, when executed by one or more processors, may provide the functions or part of the functions described above with respect to FIGS. 9-10 . Thus, for example, with reference to the embodiment shown in FIG. 9 , implementation of the functionality of one or more of blocks 901 - 905 may be undertaken by one or more instructions associated with signal bearing medium 1101 . Additionally, program instructions 1102 in FIG. 11 also describe example instructions.
在一些实施例中，上述程序指令1102被处理器执行时实现：获取当前路况信息；获取当前路况信息；根据该当前路况信息，从数据库中查询是否存在与该当前路况信息相匹配的目标驾驶控制参数；若存在，则获取该目标驾驶控制参数，并根据该目标驾驶控制参数以目标驾驶风格进行驾驶；该目标驾驶控制参数包括目标车辆的历史驾驶控制参数，该历史驾驶控制参数包括该目标车辆按照该目标驾驶风格进行驾驶得到的驾驶控制参数；若不存在，则根据实时驾驶控制参数以当前驾驶风格进行驾驶；该实时驾驶控制参数为该自动驾驶装置按照预设决策机制决策出的驾驶控制参数。In some embodiments, when the above-mentioned program instructions 1102 are executed by the processor, it is possible to: obtain current road condition information; obtain current road condition information; query from the database whether there is a target driving control that matches the current road condition information according to the current road condition information parameter; if it exists, then obtain the target driving control parameter, and drive with the target driving style according to the target driving control parameter; the target driving control parameter includes the historical driving control parameters of the target vehicle, and the historical driving control parameters include the target vehicle The driving control parameter obtained by driving according to the target driving style; if it does not exist, then driving with the current driving style according to the real-time driving control parameter; the real-time driving control parameter is the driving control determined by the automatic driving device according to the preset decision-making mechanism parameter.
在一些实施例中，上述程序指令1102被处理器执行时实现：获取历史路况信息和历史驾驶控制参数；该历史路况信息和该历史驾驶控制参数分别为自动驾驶装置在驾驶员手动驾驶的过程中采集的路况信息以及驾驶控制参数，该历史路况信息与该历史驾驶控制参数在时间维度相对应；根据该历史路况信息和该历史驾驶控制参数，确定历史驾驶行为；将该历史驾驶行为、该历史路况信息以及该历史驾驶控制参数作为一个整体存储，以得到驾驶数据文件。In some embodiments, when the above-mentioned program instructions 1102 are executed by the processor, it is possible to: obtain historical road condition information and historical driving control parameters; Collected road condition information and driving control parameters, the historical road condition information corresponds to the historical driving control parameters in the time dimension; according to the historical road condition information and the historical driving control parameters, determine the historical driving behavior; the historical driving behavior, the historical The road condition information and the historical driving control parameters are stored as a whole to obtain a driving data file.
在一些示例中，信号承载介质1101可以包含计算机可读介质1103，诸如但不限于，硬盘驱动器、紧密盘(CD)、数字视频光盘(DVD)、数字磁带、存储器、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等等。在一些实施方式中，信号承载介质1101可以包含计算机可记录介质1104，诸如但不限于，存储器、读/写(R/W)CD、R/W DVD、等等。在一些实施方式中，信号承载介质1101可以包含通信介质1105，诸如但不限于，数字和/或模拟通信介质(例如，光纤电缆、波导、有线通信链路、无线通信链路、等等)。因此，例如，信号承载介质1101可以由无线形式的通信介质1105(例如，遵守IEEE802.11标准或者其它传输协议的无线通信介质)来传达。一个或多个程序指令1102可以是，例如，计算机可执行指令或者逻辑实施指令。在一些示例中，诸如针对图1描述的处理器可以被配置为，响应于通过计算机可读介质1103、计算机可记录介质1104、和/或通信介质1105中的一个或多个传达到处理器的程序指令1102，提供各种操作、功能、或者动作。应该理解，这里描述的布置仅仅是用于示例的目的。因而，本领域技术人员将理解，其它布置和其它元素(例如，机器、接口、功能、顺序、和功能组等等)能够被取而代之地使用，并且一些元素可以根据所期望的结果而一并省略。另外，所描述的元素中的许多是可以被实现为离散的或者分布式的组件的、或者以任何适当的组合和位置来结合其它组件实施的功能实体。In some examples, signal bearing medium 1101 may comprise computer readable medium 1103 such as, but not limited to, a hard drive, compact disc (CD), digital video disc (DVD), digital tape, memory, read-only memory (Read Only Memory) -Only Memory, ROM) or Random Access Memory (Random Access Memory, RAM) and so on. In some implementations, signal bearing media 1101 may comprise computer recordable media 1104 such as, but not limited to, memory, read/write (R/W) CDs, R/W DVDs, and the like. In some implementations, signal bearing media 1101 may include communication media 1105 such as, but not limited to, digital and/or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.). Thus, for example, the signal bearing medium 1101 may be conveyed by a wireless form of communication medium 1105 (eg, a wireless communication medium complying with the IEEE 802.11 standard or other transmission protocol). One or more program instructions 1102 may be, for example, computer-executable instructions or logic-implemented instructions. In some examples, a processor such as that described with respect to FIG. Program instructions 1102 provide various operations, functions, or actions. It should be understood that the arrangements described herein are for example purposes only. Accordingly, those skilled in the art will appreciate that other arrangements and other elements (e.g., machines, interfaces, functions, sequences, and groups of functions, etc.) can be used instead, and some elements may be omitted altogether depending on the desired result. . In addition, many of the described elements are functional entities that may be implemented as discrete or distributed components, or implemented in conjunction with other components in any suitable combination and location.
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
本发明是根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present invention is described according to the flowcharts and/or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person familiar with the technical field can easily think of various equivalents within the technical scope disclosed in the present invention. Modifications or replacements shall all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910691859.4ACN110471411A (en) | 2019-07-26 | 2019-07-26 | Automatic Pilot method and servomechanism |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910691859.4ACN110471411A (en) | 2019-07-26 | 2019-07-26 | Automatic Pilot method and servomechanism |
| Publication Number | Publication Date |
|---|---|
| CN110471411Atrue CN110471411A (en) | 2019-11-19 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910691859.4APendingCN110471411A (en) | 2019-07-26 | 2019-07-26 | Automatic Pilot method and servomechanism |
| Country | Link |
|---|---|
| CN (1) | CN110471411A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989622A (en)* | 2019-12-25 | 2020-04-10 | 腾讯科技（深圳）有限公司 | Automatic driving control method, device, storage medium and computer equipment |
| CN111506067A (en)* | 2020-04-20 | 2020-08-07 | 上海电子信息职业技术学院 | smart model car |
| CN111522348A (en)* | 2020-05-27 | 2020-08-11 | 杭州野乐科技有限公司 | Self-walking control method and system for scooter |
| CN111612140A (en)* | 2020-04-01 | 2020-09-01 | 广东中科臻恒信息技术有限公司 | Automatic driving safety discrimination method, equipment and storage medium based on road side unit |
| CN111619576A (en)* | 2020-06-03 | 2020-09-04 | 中国第一汽车股份有限公司 | Control method, device, equipment and storage medium |
| CN112214026A (en)* | 2020-10-26 | 2021-01-12 | 广州小鹏自动驾驶科技有限公司 | Driving obstacle detection method and device, vehicle and readable medium |
| CN112654548A (en)* | 2020-05-09 | 2021-04-13 | 华为技术有限公司 | Method and device for adaptively optimizing automatic driving system |
| WO2021098222A1 (en)* | 2019-11-20 | 2021-05-27 | 华为技术有限公司 | Vehicle driving control method and related device |
| WO2021129156A1 (en)* | 2019-12-28 | 2021-07-01 | 华为技术有限公司 | Control method, device and system of intelligent car |
| CN113159105A (en)* | 2021-02-26 | 2021-07-23 | 北京科技大学 | Unsupervised driving behavior pattern recognition method and data acquisition monitoring system |
| CN113178074A (en)* | 2021-04-26 | 2021-07-27 | 蔚来汽车科技(安徽)有限公司 | Traffic flow machine learning modeling system and method applied to vehicle |
| CN113238237A (en)* | 2021-07-12 | 2021-08-10 | 天津天瞳威势电子科技有限公司 | Library position detection method and device |
| CN113495555A (en)* | 2020-03-20 | 2021-10-12 | 际络科技(上海)有限公司 | Driving rule extraction device and method, formulation device and method, and storage medium |
| CN113704116A (en)* | 2021-08-30 | 2021-11-26 | 阿波罗智联(北京)科技有限公司 | Data processing method, device, electronic equipment and medium for automatic driving vehicle |
| CN113968224A (en)* | 2021-12-06 | 2022-01-25 | 武汉路特斯汽车有限公司 | Control method and control system for automatically adjusting driving mode and vehicle |
| WO2022022344A1 (en)* | 2020-07-31 | 2022-02-03 | 华为技术有限公司 | Automatic driving control method and apparatus |
| CN115391313A (en)* | 2022-04-19 | 2022-11-25 | 中国第一汽车股份有限公司 | Data processing method, data processing device, storage medium and electronic equipment |
| CN115534981A (en)* | 2022-12-05 | 2022-12-30 | 广汽埃安新能源汽车股份有限公司 | Automatic driving mode adjusting method and device for vehicle |
| CN115716477A (en)* | 2022-09-08 | 2023-02-28 | 广汽埃安新能源汽车有限公司 | Driving mode switching method and device, electronic equipment and storage medium |
| WO2023103692A1 (en)* | 2021-12-07 | 2023-06-15 | 阿里巴巴达摩院(杭州)科技有限公司 | Decision planning method for autonomous driving, electronic device, and computer storage medium |
| CN119828464A (en)* | 2024-12-26 | 2025-04-15 | 交通运输部公路科学研究所 | Cooperative control method and system for intelligent driving test equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106143490A (en)* | 2015-04-07 | 2016-11-23 | 上海汽车集团股份有限公司 | Adaptive cruise control method and device |
| CN106184223A (en)* | 2016-09-28 | 2016-12-07 | 北京新能源汽车股份有限公司 | Automatic driving control method and device and automobile |
| CN106875511A (en)* | 2017-03-03 | 2017-06-20 | 深圳市唯特视科技有限公司 | A kind of method for learning driving style based on own coding regularization network |
| CN107329466A (en)* | 2017-08-28 | 2017-11-07 | 北京华清智能科技有限公司 | A kind of automatic Pilot compact car |
| CN108357496A (en)* | 2018-02-12 | 2018-08-03 | 北京小马智行科技有限公司 | Automatic Pilot control method and device |
| CN108891422A (en)* | 2018-07-09 | 2018-11-27 | 深圳市易成自动驾驶技术有限公司 | Control method, device and the computer readable storage medium of intelligent vehicle |
| CN109383523A (en)* | 2017-08-07 | 2019-02-26 | 奥迪股份公司 | Auxiliary driving method and system for vehicle |
| CN109703567A (en)* | 2019-01-25 | 2019-05-03 | 安徽酷哇机器人有限公司 | Control method for vehicle |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106143490A (en)* | 2015-04-07 | 2016-11-23 | 上海汽车集团股份有限公司 | Adaptive cruise control method and device |
| CN106184223A (en)* | 2016-09-28 | 2016-12-07 | 北京新能源汽车股份有限公司 | Automatic driving control method and device and automobile |
| CN106875511A (en)* | 2017-03-03 | 2017-06-20 | 深圳市唯特视科技有限公司 | A kind of method for learning driving style based on own coding regularization network |
| CN109383523A (en)* | 2017-08-07 | 2019-02-26 | 奥迪股份公司 | Auxiliary driving method and system for vehicle |
| CN107329466A (en)* | 2017-08-28 | 2017-11-07 | 北京华清智能科技有限公司 | A kind of automatic Pilot compact car |
| CN108357496A (en)* | 2018-02-12 | 2018-08-03 | 北京小马智行科技有限公司 | Automatic Pilot control method and device |
| CN108891422A (en)* | 2018-07-09 | 2018-11-27 | 深圳市易成自动驾驶技术有限公司 | Control method, device and the computer readable storage medium of intelligent vehicle |
| CN109703567A (en)* | 2019-01-25 | 2019-05-03 | 安徽酷哇机器人有限公司 | Control method for vehicle |
| Title |
|---|
| 李曙光: "《法大研究生》", 31 July 2017, 北京：中国政法大学出版社* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021098222A1 (en)* | 2019-11-20 | 2021-05-27 | 华为技术有限公司 | Vehicle driving control method and related device |
| CN110989622A (en)* | 2019-12-25 | 2020-04-10 | 腾讯科技（深圳）有限公司 | Automatic driving control method, device, storage medium and computer equipment |
| CN110989622B (en)* | 2019-12-25 | 2022-06-03 | 腾讯科技（深圳）有限公司 | Automatic driving control method, device, storage medium and computer equipment |
| WO2021129156A1 (en)* | 2019-12-28 | 2021-07-01 | 华为技术有限公司 | Control method, device and system of intelligent car |
| US12319292B2 (en) | 2019-12-28 | 2025-06-03 | Shenzhen Yinwang Intelligent Technologies Co., Ltd. | Intelligent vehicle control method, apparatus, and control system |
| CN113495555A (en)* | 2020-03-20 | 2021-10-12 | 际络科技(上海)有限公司 | Driving rule extraction device and method, formulation device and method, and storage medium |
| CN111612140A (en)* | 2020-04-01 | 2020-09-01 | 广东中科臻恒信息技术有限公司 | Automatic driving safety discrimination method, equipment and storage medium based on road side unit |
| CN111612140B (en)* | 2020-04-01 | 2023-08-25 | 广东中科臻恒信息技术有限公司 | Automatic driving safety judging method, equipment and storage medium based on road side unit |
| CN111506067A (en)* | 2020-04-20 | 2020-08-07 | 上海电子信息职业技术学院 | smart model car |
| CN112654548A (en)* | 2020-05-09 | 2021-04-13 | 华为技术有限公司 | Method and device for adaptively optimizing automatic driving system |
| CN112654548B (en)* | 2020-05-09 | 2022-04-05 | 华为技术有限公司 | Method and device for adaptively optimizing automatic driving system |
| CN111522348A (en)* | 2020-05-27 | 2020-08-11 | 杭州野乐科技有限公司 | Self-walking control method and system for scooter |
| CN111619576B (en)* | 2020-06-03 | 2021-06-25 | 中国第一汽车股份有限公司 | Control method, device, equipment and storage medium |
| CN111619576A (en)* | 2020-06-03 | 2020-09-04 | 中国第一汽车股份有限公司 | Control method, device, equipment and storage medium |
| CN114056346A (en)* | 2020-07-31 | 2022-02-18 | 华为技术有限公司 | A kind of automatic driving driving control method and device |
| WO2022022344A1 (en)* | 2020-07-31 | 2022-02-03 | 华为技术有限公司 | Automatic driving control method and apparatus |
| CN112214026A (en)* | 2020-10-26 | 2021-01-12 | 广州小鹏自动驾驶科技有限公司 | Driving obstacle detection method and device, vehicle and readable medium |
| CN113159105B (en)* | 2021-02-26 | 2023-08-08 | 北京科技大学 | Driving behavior unsupervised mode identification method and data acquisition monitoring system |
| CN113159105A (en)* | 2021-02-26 | 2021-07-23 | 北京科技大学 | Unsupervised driving behavior pattern recognition method and data acquisition monitoring system |
| CN113178074B (en)* | 2021-04-26 | 2025-06-17 | 蔚来汽车科技(安徽)有限公司 | Traffic flow machine learning modeling system and method applied to vehicles |
| CN113178074A (en)* | 2021-04-26 | 2021-07-27 | 蔚来汽车科技(安徽)有限公司 | Traffic flow machine learning modeling system and method applied to vehicle |
| US20220343637A1 (en)* | 2021-04-26 | 2022-10-27 | Nio Technology (Anhui) Co., Ltd | Traffic flow machine-learning modeling system and method applied to vehicles |
| EP4083959A1 (en)* | 2021-04-26 | 2022-11-02 | Nio Technology (Anhui) Co., Ltd | Traffic flow machine-learning modeling system and method applied to vehicles |
| US12254680B2 (en)* | 2021-04-26 | 2025-03-18 | Nio Technology (Anhui) Co., Ltd | Traffic flow machine-learning modeling system and method applied to vehicles |
| CN113238237B (en)* | 2021-07-12 | 2021-10-01 | 天津天瞳威势电子科技有限公司 | A storage location detection method and device |
| CN113238237A (en)* | 2021-07-12 | 2021-08-10 | 天津天瞳威势电子科技有限公司 | Library position detection method and device |
| CN113704116A (en)* | 2021-08-30 | 2021-11-26 | 阿波罗智联(北京)科技有限公司 | Data processing method, device, electronic equipment and medium for automatic driving vehicle |
| CN113968224B (en)* | 2021-12-06 | 2024-04-26 | 宁波路特斯机器人有限公司 | Control method and control system for automatically adjusting driving mode and vehicle |
| CN113968224A (en)* | 2021-12-06 | 2022-01-25 | 武汉路特斯汽车有限公司 | Control method and control system for automatically adjusting driving mode and vehicle |
| WO2023103692A1 (en)* | 2021-12-07 | 2023-06-15 | 阿里巴巴达摩院(杭州)科技有限公司 | Decision planning method for autonomous driving, electronic device, and computer storage medium |
| CN115391313A (en)* | 2022-04-19 | 2022-11-25 | 中国第一汽车股份有限公司 | Data processing method, data processing device, storage medium and electronic equipment |
| CN115716477A (en)* | 2022-09-08 | 2023-02-28 | 广汽埃安新能源汽车有限公司 | Driving mode switching method and device, electronic equipment and storage medium |
| CN115534981B (en)* | 2022-12-05 | 2023-03-07 | 广汽埃安新能源汽车股份有限公司 | Automatic driving mode adjusting method and device for vehicle |
| CN115534981A (en)* | 2022-12-05 | 2022-12-30 | 广汽埃安新能源汽车股份有限公司 | Automatic driving mode adjusting method and device for vehicle |
| CN119828464A (en)* | 2024-12-26 | 2025-04-15 | 交通运输部公路科学研究所 | Cooperative control method and system for intelligent driving test equipment |
| CN119828464B (en)* | 2024-12-26 | 2025-09-23 | 交通运输部公路科学研究所 | A collaborative control method and system for intelligent driving test equipment |
| Publication | Publication Date | Title |
|---|---|---|
| CN110471411A (en) | Automatic Pilot method and servomechanism | |
| EP3858697B1 (en) | Obstacle avoidance method and device | |
| CN111123952B (en) | Trajectory planning method and device | |
| CN112230642B (en) | Road drivable area reasoning method and device | |
| US12371025B2 (en) | Autonomous lane change method and apparatus, and storage medium | |
| CN113498529B (en) | Target tracking method and device | |
| CN112512887B (en) | Driving decision selection method and device | |
| CN112672942B (en) | Vehicle lane changing method and related equipment | |
| WO2021052213A1 (en) | Method and device for adjusting accelerator pedal characteristic | |
| WO2021102955A1 (en) | Path planning method for vehicle and path planning apparatus for vehicle | |
| WO2022205211A1 (en) | Method and apparatus for controlling vehicle running and vehicle | |
| CN113968242B (en) | Automatic driving scene generation method, device and system | |
| WO2021212379A1 (en) | Lane line detection method and apparatus | |
| US12409849B2 (en) | Method and apparatus for passing through barrier gate crossbar by vehicle | |
| CN112543877A (en) | Positioning method and positioning device | |
| WO2022062825A1 (en) | Vehicle control method, device, and vehicle | |
| CN113954858A (en) | A method for planning a driving route of a vehicle and a smart car | |
| WO2022061702A1 (en) | Method, apparatus, and system for driving alerts | |
| CN115042821B (en) | Vehicle control method, vehicle control device, vehicle and storage medium | |
| US20230256970A1 (en) | Lane Change Track Planning Method and Apparatus | |
| CN113859265A (en) | Reminding method and device in driving process | |
| CN115675504A (en) | Vehicle warning method and related equipment | |
| CN114556251B (en) | Method and device for determining vehicle passable space | |
| CN120435700A (en) | Key information acquisition method and device and intelligent driving equipment |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | Application publication date:20191119 | |
| WD01 | Invention patent application deemed withdrawn after publication |