CN112113593A - Method and system for testing sensor configuration of a vehicle - Google Patents

Abstract

The invention provides a method and a system for testing a sensor configuration of a vehicle. The method may include and the system may be operable to: building a virtual road environment; driving a virtual vehicle having a preset sensor configuration in a virtual road environment; collecting measurement signals obtained by the configured sensors in the virtual road environment; and analyzing the measurement signal to determine whether the sensor configuration meets the measurement requirements. By employing the method and system provided according to the invention, a complex virtual road environment can be created for testing and the performance of the sensor configuration can be tested in the virtual road environment, thereby saving time and cost for performing the test.

Description

Translated fromChinese

用于测试车辆的传感器配置的方法和系统Method and system for testing sensor configuration of a vehicle

技术领域technical field

本发明涉及安装在车辆上的传感器，更具体地，涉及用于测试车辆的传感器配置的方法和系统。The present invention relates to sensors mounted on vehicles, and more particularly, to methods and systems for testing sensor configurations of vehicles.

背景技术Background technique

传感器在汽车上的应用不断扩大，它们在汽车电子稳定性控制系统、车道偏离警告系统和盲点探测系统等各个方面都得到了广泛使用。长期以来，自动驾驶一直是旨在提高汽车运输安全性和效率的研究工作的主题。近年来，越来越复杂的传感器(例如，激光雷达、毫米波雷达、摄像头、超声波传感器等)使自动驾驶系统更接近现实。在每辆汽车、尤其是自动驾驶汽车上安装的传感器的数目和种类可能非常得多。为了测试这些传感器以及它们的组合是否能够正确地且最佳地工作，测试人员通常基于历史测试结果、历史经验和其他研究结果来在真实汽车的不同位置中安装不同的传感器。随后，在不同的场景和环境中(例如，在白天、黑夜、晴天、雨天等)进行测试，以得到最佳的解决方案。由于存在将影响最终测试结果的许多变量，测试人员将不得不重复测试许多次以得到各种情况下的测试结果。然而，如果要调整传感器配置，则测试人员必须手动调整安装在汽车上的传感器(例如，调整各传感器的安装位置、调整各传感器的数目和组合、调整电缆布线等)。显然，这种测试将耗费大量的时间和费用。The use of sensors in automobiles continues to expand, and they are widely used in various aspects of automotive electronic stability control systems, lane departure warning systems, and blind spot detection systems. Autonomous driving has long been the subject of research efforts aimed at improving the safety and efficiency of automotive transportation. In recent years, increasingly sophisticated sensors (eg, lidar, millimeter-wave radar, cameras, ultrasonic sensors, etc.) have brought autonomous driving systems closer to reality. The number and variety of sensors installed in each car, especially self-driving cars, can be very large. To test whether these sensors and their combinations work correctly and optimally, testers typically install different sensors in different locations in real cars based on historical test results, historical experience, and other research results. Then, test in different scenarios and environments (eg, day, night, sunny, rainy, etc.) to get the best solution. Since there are many variables that will affect the final test results, the tester will have to repeat the test many times to get the test results for each situation. However, if the sensor configuration is to be adjusted, the tester must manually adjust the sensors installed in the vehicle (eg, adjust the installation position of each sensor, adjust the number and combination of each sensor, adjust the cable routing, etc.). Obviously, such testing would be time-consuming and expensive.

因此，希望提供一种能够以高效的方式来测试安装在车辆上的传感器的技术。Therefore, it is desirable to provide a technique that can test sensors mounted on vehicles in an efficient manner.

发明内容SUMMARY OF THE INVENTION

提供本发明内容以便以简化形式介绍将在以下具体实施方式中进一步的描述一些概念。本发明内容并非旨在标识所要求保护的主题的关键特征或必要特征，也不旨在用于帮助确定所要求保护的主题的范围。This Summary is provided to introduce some concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

根据本发明的一个实施例，提供了一种用于测试车辆的传感器配置的方法，该方法包括：搭建虚拟道路环境；使具有预设好的传感器配置的虚拟车辆在该虚拟道路环境中行驶；采集由经配置的传感器在该虚拟道路环境中获得的测量信号；以及分析该测量信号以确定该传感器配置是否满足测量要求。According to an embodiment of the present invention, a method for testing a sensor configuration of a vehicle is provided, the method comprising: building a virtual road environment; making a virtual vehicle with a preset sensor configuration drive in the virtual road environment; acquiring measurement signals obtained by the configured sensors in the virtual road environment; and analyzing the measurement signals to determine whether the sensor configuration meets measurement requirements.

根据本发明的一个实施例，提供了一种用于测试车辆的传感器配置的系统，该系统包括：环境搭建单元，其用于搭建虚拟道路环境；车辆仿真单元，其用于提供在该虚拟道路环境中行驶的虚拟车辆；传感器配置单元，其用于对安装在虚拟车辆上的传感器进行配置；采集单元，其用于采集由经配置的传感器在该虚拟道路环境中获得的测量信号；以及分析单元，其用于分析该测量信号以确定该传感器的配置是否满足测量要求。According to an embodiment of the present invention, there is provided a system for testing a sensor configuration of a vehicle, the system comprising: an environment construction unit for constructing a virtual road environment; a vehicle simulation unit for providing an environment on the virtual road a virtual vehicle driving in an environment; a sensor configuration unit for configuring sensors mounted on the virtual vehicle; an acquisition unit for collecting measurement signals obtained by the configured sensors in the virtual road environment; and an analysis A unit for analyzing the measurement signal to determine whether the configuration of the sensor meets the measurement requirements.

根据本发明的一个实施例，提供了一种用于测试车辆的传感器配置的装置，该装置包括：存储器，该存储器存储计算机程序；以及耦合至该存储器的处理器，该计算机程序在由该处理器执行时实现以下步骤：搭建虚拟道路环境；使具有预设好的传感器配置的虚拟车辆在该虚拟道路环境中行驶；采集由经配置的传感器在该虚拟道路环境中获得的测量信号；以及分析该测量信号以确定该传感器配置是否满足测量要求。According to one embodiment of the present invention, there is provided an apparatus for testing a sensor configuration of a vehicle, the apparatus comprising: a memory storing a computer program; and a processor coupled to the memory, the computer program being executed by the processor When the device is executed, the following steps are implemented: building a virtual road environment; driving a virtual vehicle with a preset sensor configuration in the virtual road environment; collecting measurement signals obtained by the configured sensors in the virtual road environment; and analyzing The measurement signal determines whether the sensor configuration meets measurement requirements.

根据本发明的一个实施例，提供了一种非瞬态计算机可读介质，该非瞬态计算机可读介质存储计算机程序，该计算机程序在由处理器执行时执行根据本发明的方法。According to one embodiment of the present invention, there is provided a non-transitory computer readable medium storing a computer program which, when executed by a processor, performs the method according to the present invention.

通过采用根据本发明提供的用于测试车辆的传感器配置的方法和系统，可以获得以下优点：By adopting the method and system for testing the sensor configuration of a vehicle provided according to the present invention, the following advantages can be obtained:

(1)能够创建复杂的虚拟道路环境以用于测试并且在该虚拟道路环境中测试传感器配置的性能，由此节省进行测试的时间和成本；(1) The ability to create complex virtual road environments for testing and to test the performance of sensor configurations in the virtual road environment, thereby saving time and cost in conducting tests;

(2)能够以高效的方式获得最优的传感器配置以供真车测试；(2) The optimal sensor configuration can be obtained in an efficient manner for real vehicle testing;

(3)能够减轻测试人员的工作负担并且提高工作效率和工作质量。(3) It can reduce the work load of testers and improve work efficiency and work quality.

通过阅读下面的详细描述并参考相关联的附图，这些及其他特点和优点将变得显而易见。应该理解，前面的概括说明和下面的详细描述只是说明性的，不会对所要求保护的各方面形成限制。These and other features and advantages will become apparent upon reading the following detailed description with reference to the associated drawings. It is to be understood that both the foregoing general description and the following detailed description are illustrative only and not restrictive of the claimed aspects.

附图说明Description of drawings

为了能详细地理解本发明的上述特征所用的方式，可以参照各实施例来对以上简要概述的内容进行更具体的描述，其中一些方面在附图中示出。然而应该注意，附图仅示出了本发明的某些典型方面，故不应被认为限定其范围，因为该描述可以允许有其它等同有效的方面。In order that the manner in which the above-described features of the present invention can be understood in detail, what has been briefly summarized above may be described in more detail with reference to various embodiments, some aspects of which are illustrated in the accompanying drawings. It is to be noted, however, that the appended drawings illustrate only certain typical aspects of the invention and are therefore not to be considered limiting of its scope, for the description may admit to other equally effective aspects.

图1示出了根据本发明的一个实施例创建的示例性虚拟道路环境。Figure 1 illustrates an exemplary virtual road environment created in accordance with one embodiment of the present invention.

图2示出了根据本发明的一个实施例的安装在虚拟车辆上的各种传感器的配置。FIG. 2 shows the configuration of various sensors installed on a virtual vehicle according to one embodiment of the present invention.

图3示出了根据本发明的一个实施例的虚拟车辆在虚拟道路环境中行驶的示意图。FIG. 3 shows a schematic diagram of a virtual vehicle driving in a virtual road environment according to an embodiment of the present invention.

图4示出了根据本发明的一个实施例的用于测试车辆的传感器配置的方法的流程图。FIG. 4 shows a flowchart of a method for testing a sensor configuration of a vehicle according to one embodiment of the present invention.

图5示出了根据本发明的一个实施例的用于测试车辆的传感器配置的系统的框图。5 shows a block diagram of a system for testing a sensor configuration of a vehicle in accordance with one embodiment of the present invention.

图6示出了根据本发明的示例性计算设备的框图。6 shows a block diagram of an exemplary computing device in accordance with the present invention.

具体实施方式Detailed ways

下面结合附图详细描述本发明，本发明的特点将在以下的具体描述中得到进一步的显现。The present invention will be described in detail below in conjunction with the accompanying drawings, and the features of the present invention will be further revealed in the following detailed description.

目前，测试安装在车辆、特别是自动驾驶车辆上的传感器配置的性能是一项费时费力的任务。本发明旨在提供一种能够以高效的方式在软件仿真环境中测试传感器配置的技术。利用该技术，能够首先以较低的时间、人力、物力成本获得理想的、优选最佳的传感器配置，然后再在真车上进行测试，从而极大地减轻测试人员的工作负担并且提高工作效率和工作质量。Currently, testing the performance of sensor configurations installed on vehicles, especially autonomous vehicles, is a time-consuming and labor-intensive task. The present invention aims to provide a technique for testing sensor configurations in a software simulation environment in an efficient manner. Using this technology, the ideal and optimal sensor configuration can be obtained with lower cost of time, manpower and material resources, and then tested on a real vehicle, thereby greatly reducing the workload of testers and improving work efficiency and efficiency. quality of work.

在本发明中，传感器配置指的是安装在车辆上的传感器的类型、数目、安装位置、参数、和/或各种传感器的组合。例如，一个示例性配置可包括安装在车辆前保险杠中间位置的一个激光雷达、安装在前车灯处的两个毫米波雷达、安装在车顶上的一个激光雷达和一个摄像头、安装在后保险杠中间位置的一个摄像头、安装在后车灯处的两个超声波雷达。应当注意，该示例性配置仅是解说性的，本发明中的传感器配置可包括任何类型的、任何数目的、安装在车辆任何位置处的、具有任何设定参数的传感器及传感器的组合。In the present invention, sensor configuration refers to the type, number, installation location, parameter, and/or combination of various sensors installed on the vehicle. For example, an exemplary configuration may include one lidar mounted in the middle of the vehicle's front bumper, two millimeter wave radars mounted at the headlights, one lidar and one camera mounted on the roof, rear mounted A camera in the middle of the bumper, two ultrasonic radars installed at the rear lights. It should be noted that this exemplary configuration is merely illustrative, and that the sensor configuration in the present invention may include any type, any number of sensors, and combinations of sensors installed anywhere in the vehicle, with any set parameters.

为了在软件仿真环境中测试各种传感器配置的性能，首先要搭建虚拟道路环境。虚拟道路环境可包括对真实环境进行仿真的行驶环境以及用户自定义的仿真行驶环境。虚拟道路环境的构建可以通过手动创建的方式来构建，也可以通过数据导入的方式来构建。在一个实施例中，虚拟道路环境可包括道路信息，例如，道路标志、车道线、障碍物、道路边缘、桥梁、电线杆、高架结构、隧道、交通指示牌、树木等。在另一个实施例中，为了能够模拟各种交通场景，虚拟道路环境还可包括交通信息，诸如各种交通参与者(例如，行人、自行车、同向和相向行驶的各种车辆等)以及各种交通事件(例如，交通拥堵、随机交通流等)。在又一实施例中，虚拟道路环境可进一步包括天气信息(例如，晴天、雨天、雾天、雪天等)和时间信息(例如，白天、黑夜等)。应当理解，上述虚拟道路环境能够根据需要来改变。例如，道路信息可以跟随着仿真车辆的行驶由直线道路逐渐过渡到弯曲道路，天气可以由晴天转为下雨，或者可以将不同的交通参与者和交通事件添加到虚拟道路环境中。因此，本发明中的方案能够提供多样化的仿真环境，实现对传感器配置的全面测试。To test the performance of various sensor configurations in a software simulation environment, a virtual road environment is first built. The virtual road environment may include a driving environment simulating a real environment and a user-defined simulated driving environment. The construction of the virtual road environment can be constructed by manual creation or by data import. In one embodiment, the virtual road environment may include road information such as road signs, lane lines, obstacles, road edges, bridges, utility poles, elevated structures, tunnels, traffic signs, trees, and the like. In another embodiment, in order to be able to simulate various traffic scenarios, the virtual road environment may also include traffic information, such as various traffic participants (eg, pedestrians, bicycles, various vehicles traveling in the same direction and in the opposite direction, etc.) and various traffic events (eg, traffic jams, random traffic flow, etc.). In yet another embodiment, the virtual road environment may further include weather information (eg, sunny, rainy, foggy, snowy, etc.) and time information (eg, day, night, etc.). It should be understood that the virtual road environment described above can be changed as desired. For example, road information can gradually transition from a straight road to a curved road following the driving of the simulated vehicle, the weather can change from sunny to rainy, or different traffic participants and traffic events can be added to the virtual road environment. Therefore, the solution in the present invention can provide a variety of simulation environments and realize a comprehensive test of the sensor configuration.

在本发明的一个实施例中，可以使用诸如Unreal Engine(虚幻引擎)之类的开发工具来创建虚拟道路环境。例如，可以首先由采集设备对实际道路的车道线、车道标志、建筑物、交通标志、行人和车辆等进行采集。然后，可以将真实的地图数据导入，从而在真实的地图数据上建立虚拟道路环境。仿真系统还可以设置有预定数据库，在该预定数据库中存储预设的环境模型，用户可以根据需要选择环境模型，以模拟传感器配置在各种交通状况和各种天气条件下的性能。In one embodiment of the present invention, a development tool such as Unreal Engine may be used to create the virtual road environment. For example, the lane lines, lane signs, buildings, traffic signs, pedestrians and vehicles of the actual road can be collected by the collection device first. Then, the real map data can be imported to establish a virtual road environment on the real map data. The simulation system can also be provided with a predetermined database, in which a preset environment model is stored, and the user can select the environment model as required to simulate the performance of the sensor configuration under various traffic conditions and various weather conditions.

图1示出了根据本发明创建的示例性虚拟道路环境100。该虚拟道路环境100可包括车道线、护栏、树木、路灯、交通标志等。此外，虚拟道路环境100还可包括各种天气信息和时间信息以及各种交通参与者。Figure 1 shows an exemplaryvirtual road environment 100 created in accordance with the present invention. Thevirtual road environment 100 may include lane lines, guardrails, trees, street lights, traffic signs, and the like. In addition, thevirtual road environment 100 may also include various weather information and time information and various traffic participants.

众所周知，传感器好比是车辆、特别是自动驾驶车辆的“眼睛”。例如，在自动驾驶车辆上可能会安装多个不同种类的传感器，以实现检测诸如车辆前进方向上的障碍物之类的特定对象。当前，在自动驾驶车辆上采用的传感器可包括摄像头、激光雷达、毫米波雷达、超声波雷达等。这些传感器的用途和优缺点各不相同。例如，摄像头可以采集车辆行驶环境的图像(例如，车道线图像、道路标志图像、周围车辆图像等)，成本较低，但是在极端恶劣环境下会失效，难以测距并且感知距离较近。激光雷达可以通过发射激光束来探测车辆与其他物体之间的距离，实现周边环境3D建模，测距精度好，响应快，但是成本高，恶劣天气下效果一般。毫米波雷达可以通过发射电磁波来确定车辆与其他物体之间的距离，不受天气影响，测距精度高，感知距离范围广，但是无法识别道路指示牌，难以识别行人。超声波传感器可以检测车辆周围的物体，结构简单，成本低，体积小，但是感知距离较近，应用局限较大。一般而言，由于各种传感器的用途和优缺点不同，通常会在自动驾驶车辆的不同位置处安装不同类型和不同数目的传感器，以满足在各种情况下准确检测车辆周边环境的要求。在本发明的仿真环境下，可以为虚拟仿真车辆提供仿真传感器以模拟各种传感器。例如，根据传感器厂商提供的参数，可以建立传感器模型以提供虚拟传感器(例如，虚拟摄像头、虚拟激光雷达、虚拟毫米波雷达、虚拟超声波传感器等)。这些虚拟传感器可以在虚拟道路环境中提供各种传感信号，就如同真实传感器在真实道路环境中所提供的那样。在一个实施例中，可以在虚拟仿真车辆上安装单个虚拟传感器，以检测该传感器的性能。在另一个实施例中，可以在虚拟仿真车辆上配置多个虚拟传感器，以确定这些传感器的组合的性能。As we all know, sensors are like the "eyes" of a vehicle, especially an autonomous vehicle. For example, several different kinds of sensors may be installed on an autonomous vehicle to detect specific objects such as obstacles in the direction of the vehicle. Currently, sensors used in autonomous vehicles can include cameras, lidars, millimeter-wave radars, ultrasonic radars, and more. The uses and advantages and disadvantages of these sensors vary. For example, a camera can collect images of the vehicle's driving environment (eg, lane line images, road sign images, surrounding vehicle images, etc.), with low cost, but it will fail in extremely harsh environments, it is difficult to measure distances and the perception distance is relatively short. Lidar can detect the distance between vehicles and other objects by emitting laser beams, and realize 3D modeling of the surrounding environment. Millimeter-wave radar can determine the distance between vehicles and other objects by emitting electromagnetic waves. It is not affected by weather, has high ranging accuracy, and has a wide range of perception distances. However, it cannot identify road signs and it is difficult to identify pedestrians. Ultrasonic sensors can detect objects around the vehicle, with simple structure, low cost, and small size, but the sensing distance is short, and the application is limited. Generally speaking, due to the different uses, advantages and disadvantages of various sensors, different types and numbers of sensors are usually installed in different locations of autonomous vehicles to meet the requirements of accurately detecting the surrounding environment of the vehicle in various situations. In the simulation environment of the present invention, simulation sensors can be provided for the virtual simulation vehicle to simulate various sensors. For example, a sensor model can be built to provide virtual sensors (eg, virtual cameras, virtual lidars, virtual millimeter-wave radars, virtual ultrasonic sensors, etc.) according to the parameters provided by the sensor manufacturers. These virtual sensors can provide various sensing signals in the virtual road environment, just as real sensors provide in the real road environment. In one embodiment, a single virtual sensor may be mounted on the virtual simulated vehicle to monitor the performance of that sensor. In another embodiment, multiple virtual sensors may be configured on a virtual simulated vehicle to determine the performance of a combination of these sensors.

图2示出了根据本发明的一个实施例的安装在虚拟车辆上的各种虚拟传感器。如图所示，可以在虚拟车辆200的车头中间安装激光雷达210，在车头两侧安装两个毫米波雷达220、230，在车身两侧安装超声波传感器240、270，在车顶安装摄像头280，在车尾两侧安装超声波传感器250、260，以及在车尾中间安装摄像头290。应当注意，图2仅给出了一个示例性传感器配置。在实际的操作中，可以将任何虚拟传感器及其组合安装在虚拟车辆200的任何位置处以模拟该传感器配置的性能。Figure 2 illustrates various virtual sensors mounted on a virtual vehicle according to one embodiment of the present invention. As shown in the figure, alidar 210 can be installed in the middle of the front of thevirtual vehicle 200, two millimeter-wave radars 220 and 230 can be installed on both sides of the front of the vehicle,ultrasonic sensors 240 and 270 can be installed on both sides of the vehicle body, and acamera 280 can be installed on the roof.Ultrasonic sensors 250 and 260 are installed on both sides of the rear of the vehicle, and acamera 290 is installed in the middle of the rear of the vehicle. It should be noted that Figure 2 shows only one exemplary sensor configuration. In actual operation, any virtual sensor and combination thereof can be installed anywhere on thevirtual vehicle 200 to simulate the performance of that sensor configuration.

图3示出了根据本发明的一个实施例的虚拟车辆在虚拟道路环境300中行驶的示意图。如图所示，安装有各种虚拟传感器的虚拟车辆310在虚拟道路环境300中行驶，以测试传感器配置的性能。根据需要，可以改变虚拟道路环境。例如，可以改变天气、改变白天黑夜、改变道路状况、添加交通参与者(例如，虚拟车辆320)等等。FIG. 3 shows a schematic diagram of a virtual vehicle driving in avirtual road environment 300 according to an embodiment of the present invention. As shown, avirtual vehicle 310 equipped with various virtual sensors is driven in avirtual road environment 300 to test the performance of the sensor configuration. The virtual road environment can be changed as needed. For example, the weather may be changed, day and night may be changed, road conditions may be changed, traffic participants (eg, virtual vehicles 320) may be added, and the like.

以下结合图4和图5来详细描述本发明的用于测试车辆的传感器配置的方法和系统。图4示出了根据本发明的一个实施例的用于测试车辆的传感器配置的方法400的流程图。图5示出了根据本发明的一个实施例的用于测试车辆的传感器配置的系统500的框图。方法400可以在至少一个处理器(例如，图6的处理器604)内实现，该处理器可以位于计算机系统、远程服务器、或其组合中。当然，在本发明的各个方面，方法400还可以由能够执行相关操作的任何合适的装置来实现。系统500的所有功能块(包括在系统500中的各个单元)可通过硬件、软件、硬件和软件的组合来实现。本领域技术人员应当理解，图5中描述的功能块可被组合成单个功能块或者划分成多个子功能块。这些功能块可以通过有线或无线的方式连接。The method and system for testing a sensor configuration of a vehicle of the present invention will be described in detail below with reference to FIGS. 4 and 5 . FIG. 4 shows a flowchart of amethod 400 for testing a sensor configuration of a vehicle according to one embodiment of the present invention. FIG. 5 shows a block diagram of asystem 500 for testing a sensor configuration of a vehicle in accordance with one embodiment of the present invention.Method 400 may be implemented within at least one processor (eg, processor 604 of FIG. 6), which may be located in a computer system, a remote server, or a combination thereof. Of course, in various aspects of the present invention, themethod 400 may also be implemented by any suitable apparatus capable of performing the relevant operations. All functional blocks of the system 500 (each unit included in the system 500) can be implemented by hardware, software, a combination of hardware and software. Those skilled in the art will understand that the functional blocks depicted in FIG. 5 may be combined into a single functional block or divided into multiple sub-functional blocks. These functional blocks can be wired or wirelessly connected.

方法400可始于步骤410。在步骤410中，方法400可包括搭建虚拟道路环境，以模拟各种真实世界道路环境。虚拟道路环境的搭建可以由环境搭建单元510来执行。如上所述，虚拟道路环境可包括道路信息(例如，道路标志、车道线、障碍物、道路边缘、桥梁、电线杆、高架结构、隧道、交通指示牌、树木等)、交通信息(例如，行人、自行车、车辆、设定好的或随机的交通流等)、天气信息(例如，晴天、雨天、雾天等)和时间信息(例如，白天、黑夜等)并且能够根据需要来改变。在一个实施例中，可以使用诸如Unreal Engine(虚幻引擎)之类的开发工具来创建虚拟道路环境。Method 400 may begin atstep 410 . Instep 410, themethod 400 may include constructing a virtual road environment to simulate various real world road environments. The construction of the virtual road environment may be performed by theenvironment construction unit 510 . As described above, the virtual road environment may include road information (eg, road signs, lane lines, obstacles, road edges, bridges, utility poles, elevated structures, tunnels, traffic signs, trees, etc.), traffic information (eg, pedestrians , bicycles, vehicles, programmed or random traffic flow, etc.), weather information (eg, sunny, rainy, foggy, etc.) and time information (eg, day, night, etc.) and can be changed as desired. In one embodiment, a development tool such as Unreal Engine may be used to create the virtual road environment.

在步骤420中，方法400可包括使具有预设好的传感器配置的虚拟车辆在虚拟道路环境中行驶。该步骤可以由车辆仿真单元520和传感器配置单元530来执行。车辆仿真单元520可用于提供参数化的仿真车辆，其能够将仿真车辆可视化，模拟车辆的动力系统，从而使仿真车辆能够在虚拟道路环境中行驶。传感器配置单元530可用于提供各种虚拟传感器(例如，摄像头、激光雷达、毫米波雷达、超声波传感器等)、设置每个虚拟传感器的参数、设置安装在虚拟车辆上的传感器的类型、数目和安装位置等。Instep 420, themethod 400 may include driving a virtual vehicle with a preset sensor configuration in a virtual road environment. This step may be performed by thevehicle simulation unit 520 and thesensor configuration unit 530 . Thevehicle simulation unit 520 can be used to provide a parametric simulated vehicle, which can visualize the simulated vehicle, simulate the power system of the vehicle, and thereby enable the simulated vehicle to drive in a virtual road environment. Thesensor configuration unit 530 may be used to provide various virtual sensors (eg, cameras, lidars, millimeter-wave radars, ultrasonic sensors, etc.), set the parameters of each virtual sensor, set the type, number, and installation of sensors installed on the virtual vehicle location etc.

在步骤430中，方法400可包括采集由经设置的传感器在虚拟道路环境中获得的测量信号。该步骤可由采集单元540来执行。例如，采集单元540获得由摄像头在虚拟道路环境中采集到的仿真车辆周围的图像信号，获得由激光雷达在虚拟道路环境中采集到的仿真车辆与其他物体之间的距离，等等。Instep 430, themethod 400 may include acquiring measurement signals obtained by the provided sensors in the virtual road environment. This step may be performed by theacquisition unit 540 . For example, theacquisition unit 540 obtains image signals around the simulated vehicle collected by the camera in the virtual road environment, obtains the distance between the simulated vehicle and other objects collected by the lidar in the virtual road environment, and so on.

在步骤440中，方法400可包括分析测量信号以确定所设置的传感器配置是否满足测量要求。该步骤可由分析单元550来执行。In step 440, themethod 400 may include analyzing the measurement signal to determine whether the set sensor configuration meets the measurement requirements. This step may be performed by theanalysis unit 550 .

在一个实施例中，确定是否满足测量要求可包括确定传感器是否具有所声称的检测能力。例如，假定毫米波雷达的供应商宣称具有100m的探测距离。在本发明的仿真环境中，可以通过传感器配置单元530来将毫米波雷达设置在虚拟车辆的车头中间，使虚拟车辆在各种虚拟道路环境中行驶(例如，在虚拟道路环境中在虚拟车辆周围100米内设置障碍物)，采集由毫米波雷达获得的测量信号，分析该测量信号以确定该毫米波雷达是否可在各种虚拟道路环境中检测到100m范围内的障碍物。In one embodiment, determining whether the measurement requirements are met may include determining whether the sensor has a claimed detection capability. For example, assume that the supplier of the millimeter-wave radar claims a detection range of 100 m. In the simulation environment of the present invention, the millimeter-wave radar can be set in the middle of the front of the virtual vehicle through thesensor configuration unit 530, so that the virtual vehicle is driven in various virtual road environments (for example, around the virtual vehicle in the virtual road environment Set obstacles within 100 meters), collect the measurement signal obtained by the millimeter-wave radar, analyze the measurement signal to determine whether the millimeter-wave radar can detect obstacles within 100m in various virtual road environments.

在一个实施例中，确定是否满足测量要求可包括确定经配置的传感器是否能够检测到特定物体。例如，激光雷达具有特定的视角(例如，30°的垂直探测角)。如果在车头位置处设置得离地面过低，则在距离前方车辆较近且前方车辆是诸如大卡车之类的高底盘车辆时，可能检测不到该前方车辆。或者，如果设置得离地面过高，则也可能检测不到离地面较近的物体。在本发明的仿真环境中，可以通过传感器配置单元530来将激光雷达设置在车头的特定位置处。如果采集到的测量信号错误地指示没有检测到物体(即，不满足测量要求)，则可以更改激光雷达的安装位置以进行重新测量，直至获得最佳的安装位置。In one embodiment, determining whether the measurement requirements are met may include determining whether the configured sensor is capable of detecting a particular object. For example, lidar has a specific viewing angle (eg, a vertical detection angle of 30°). If the head position is set too low from the ground, the vehicle in front may not be detected when the vehicle in front is close and the vehicle in front is a high-riding vehicle such as a large truck. Alternatively, if it is set too high above the ground, objects closer to the ground may not be detected. In the simulation environment of the present invention, the lidar can be set at a specific position on the front of the vehicle through thesensor configuration unit 530 . If the acquired measurement signal erroneously indicates that no object was detected (i.e., the measurement requirements are not met), the lidar mounting position can be changed for re-measurement until the optimal mounting position is obtained.

在一个实施例中，测量要求可包括针对特定目标的阈值检出率(例如，95％)。方法400可进一步包括改变虚拟道路环境以确定传感器配置在各种虚拟道路环境下检测到特定目标的检出率是否大于阈值检出率。如上所述，各种传感器的优缺点各不相同。在真实车辆中，往往需要安装多个数目的多种类型的传感器以便弥补各自的缺点，从而以最小的成本实现较佳的检测效果。在本发明的仿真环境中，可以通过传感器配置单元530来将不同数目的不同类型的传感器安装在虚拟车辆的不同位置处，随后使该虚拟车辆在各种虚拟道路环境中行驶，通过分析由这些传感器采集到的测量信号来确定是否检测到特定目标。例如，可以在不同的虚拟道路环境中设置障碍物，总共测试100次。如果100次测试中超过95次测试指示检测到该障碍物，则认为该传感器配置满足测量要求。在另一示例中，可以在虚拟道路环境中设置正在变道的前方车辆，总共测试100次。如果100次测试中超过95次测试成功检测出前方车辆正在变道，则认为该传感器配置满足测量要求。在一个实施例中，可以将在各种虚拟道路环境下检测到特定目标的检出率最高的传感器配置指示为最佳的传感器配置。在另一实施例中，可以综合考虑检出率和传感器的总成本，由此得到“最佳”的传感器配置，即使该传感器配置在检出率方面不是最高的。在获得最佳的传感器配置之后，就可以将该配置拿到真车上进行测试，以验证该传感器配置在实际道路环境下的性能是否符合要求。In one embodiment, the measurement requirements may include a threshold detection rate (eg, 95%) for a particular target. Themethod 400 may further include changing the virtual road environment to determine whether a detection rate at which the sensor configuration detects a particular target under various virtual road environments is greater than a threshold detection rate. As mentioned above, various sensors have different advantages and disadvantages. In a real vehicle, it is often necessary to install a large number of various types of sensors in order to make up for their respective shortcomings, so as to achieve a better detection effect with a minimum cost. In the simulation environment of the present invention, different numbers of sensors of different types can be installed at different positions of a virtual vehicle through thesensor configuration unit 530, and then the virtual vehicle is driven in various virtual road environments, and by analyzing the Measurement signals collected by sensors to determine whether a specific target has been detected. For example, obstacles can be set up in different virtual road environments for a total of 100 tests. The sensor configuration is considered to meet the measurement requirements if more than 95 out of 100 tests indicate that the obstacle is detected. In another example, a vehicle ahead that is changing lanes may be set up in a virtual road environment for a total of 100 tests. If more than 95 tests out of 100 tests successfully detect that the vehicle ahead is changing lanes, the sensor configuration is considered to meet the measurement requirements. In one embodiment, the sensor configuration with the highest detection rate for detecting a specific target in various virtual road environments may be indicated as the optimal sensor configuration. In another embodiment, the detection rate and the total cost of the sensor may be considered together, resulting in an "optimal" sensor configuration, even if the sensor configuration is not the highest in terms of detection rate. After the optimal sensor configuration is obtained, the configuration can be tested on a real vehicle to verify that the performance of the sensor configuration in the actual road environment meets the requirements.

相比于真车测试，在本发明提供的仿真环境下，可以容易地改变道路状况、交通参与者、天气和时间因素，方便地在虚拟车辆上的不同位置处安装不同数目的不同类型的传感器以便进行测试，在获得最佳的传感器配置之后再拿到真车上进行测试，从而极大地缩短了测试工作的时间并且节省了测试工作的成本，显著提高了工作效率。Compared with real vehicle testing, in the simulation environment provided by the present invention, road conditions, traffic participants, weather and time factors can be easily changed, and different numbers of sensors of different types can be conveniently installed at different positions on the virtual vehicle In order to carry out the test, after obtaining the best sensor configuration, it can be taken to the real vehicle for testing, which greatly shortens the time of the test work and saves the cost of the test work, and significantly improves the work efficiency.

图6示出了根据本发明的一个实施例的示例性计算设备的框图，该计算设备是可应用于本发明的各方面的硬件设备的一个示例。6 illustrates a block diagram of an exemplary computing device, which is one example of a hardware device applicable to aspects of the present invention, according to one embodiment of the present invention.

参考图6，现在将描述一种计算设备600，该计算设备是可应用于本发明的各方面的硬件设备的一个示例。计算设备600可以是可被配置成用于实现处理和/或计算的任何机器，可以是但并不局限于工作站、服务器、桌面型计算机、膝上型计算机、平板计算机、个人数字处理、智能手机、车载计算机或者它们的任何组合。前述的各种方法/装置/服务器/客户端设备可全部或者至少部分地由计算设备600或者类似设备或系统来实现。6, acomputing device 600 will now be described, which is one example of a hardware device applicable to aspects of the present invention.Computing device 600 can be any machine that can be configured to perform processing and/or computation, and can be, but is not limited to, workstations, servers, desktops, laptops, tablets, personal digital processors, smartphones , an on-board computer, or any combination of these. The aforementioned various methods/apparatuses/servers/client devices may be implemented in whole or at least in part by thecomputing device 600 or similar device or system.

计算设备600可包括可经由一个或多个接口和总线602连接或通信的组件。例如，计算设备600可包括总线602、一个或多个处理器604、一个或多个输入设备606以及一个或多个输出设备608。该一个或多个处理器604可以是任何类型的处理器并且可包括但不限于一个或多个通用处理器和/或一个或多个专用处理器(例如，专门的处理芯片)。输入设备606可以是任何类型的能够向计算设备输入信息的设备并且可以包括但不限于鼠标、键盘、触摸屏、麦克风和/或远程控制器。输出设备608可以是任何类型的能够呈现信息的设备并且可以包括但不限于显示器、扬声器、视频/音频输出终端、振动器和/或打印机。计算设备600也可以包括非瞬态存储设备610或者与所述非瞬态存储设备相连接，所述非瞬态存储设备可以是非瞬态的并且能够实现数据存储的任何存储设备，并且所述非瞬态存储设备可以包括但不限于磁盘驱动器、光存储设备、固态存储器、软盘、软磁盘、硬盘、磁带或任何其它磁介质、光盘或任何其它光介质、ROM(只读存储器)、RAM(随机存取存储器)、高速缓冲存储器和/或任何存储芯片或盒式磁带、和/或计算机可从其读取数据、指令和/或代码的任何其它介质。非瞬态存储设备610可从接口分离。非瞬态存储设备610可具有用于实施上述方法和步骤的数据/指令/代码。计算设备600也可包括通信设备612。通信设备612可以是任何类型的能够实现与内部装置通信和/或与网络通信的设备或系统并且可以包括但不限于调制解调器、网卡、红外通信设备、无线通信设备和/或芯片组，例如蓝牙设备、IEEE 1302.11设备、WiFi设备、WiMax设备、蜂窝通信设备和/或类似设备。Computing device 600 may include components that may connect or communicate withbus 602 via one or more interfaces. For example,computing device 600 may include abus 602 , one or more processors 604 , one ormore input devices 606 , and one ormore output devices 608 . The one or more processors 604 may be any type of processor and may include, but are not limited to, one or more general-purpose processors and/or one or more special-purpose processors (eg, specialized processing chips).Input device 606 may be any type of device capable of inputting information to a computing device and may include, but is not limited to, a mouse, keyboard, touch screen, microphone, and/or remote controller.Output device 608 may be any type of device capable of presenting information and may include, but is not limited to, displays, speakers, video/audio output terminals, vibrators, and/or printers.Computing device 600 may also include or be connected to anon-transitory storage device 610, which may be any storage device that is non-transitory and capable of data storage, and that is non-transitory. Transient storage devices may include, but are not limited to, magnetic disk drives, optical storage devices, solid state memory, floppy disks, floppy disks, hard disks, magnetic tape or any other magnetic medium, optical disks or any other optical medium, ROM (read only memory), RAM (random memory) fetch memory), cache memory, and/or any memory chip or tape cartridge, and/or any other medium from which a computer may read data, instructions, and/or code. Thenon-transitory storage device 610 may be detached from the interface. Thenon-transitory storage device 610 may have data/instructions/code for implementing the methods and steps described above.Computing device 600 may also includecommunication device 612 .Communication device 612 may be any type of device or system capable of communicating with internal devices and/or with a network and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication devices, and/or chipsets, such as Bluetooth devices , IEEE 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices and/or similar devices.

当计算设备600被用作车载设备时，它也可以与外部设备(例如，GPS接收机、用于感测不同环境数据的传感器(诸如加速度传感器、车轮速度传感器、陀螺仪等))连接。以这种方式，计算设备600例如可接收定位数据和表明车辆形式状况的传感器数据。当计算设备600被用作车载设备时，它也可以与用于控制车辆的行驶和操作的其它设备(例如，发动机系统、雨刮器、防抱死制动系统等)连接。When thecomputing device 600 is used as an in-vehicle device, it can also be connected to external devices (eg, GPS receivers, sensors for sensing different environmental data such as acceleration sensors, wheel speed sensors, gyroscopes, etc.). In this manner,computing device 600 may receive, for example, positioning data and sensor data indicative of the condition of the vehicle. When computingdevice 600 is used as an in-vehicle device, it may also interface with other devices (eg, engine systems, wipers, anti-lock braking systems, etc.) used to control the driving and operation of the vehicle.

此外，非瞬态存储设备610可以具有地图信息和软件组件，从而处理器604可实现路线引导处理。此外，输出设备606可以包括用于显示地图、显示车辆的定位标记以及显示表明车辆行驶状况的图像的显示器。输出设备606也可以包括扬声器或耳机接口以用于音频引导。Additionally, thenon-transitory storage device 610 may have map information and software components so that the processor 604 may implement the routing process. In addition, theoutput device 606 may include a display for displaying a map, displaying locator markings of the vehicle, and displaying images indicative of the driving conditions of the vehicle.Output device 606 may also include a speaker or headphone interface for audio guidance.

总线602可以包括但不限于工业标准结构(ISA)总线、微通道结构(MCA)总线、增强型ISA(EISA)总线、视频电子标准协会(VESA)局部总线和外部设备互连(PCI)总线。特别地，对于车载设备，总线602也可包括控制器局域网(CAN)总线或者为汽车上的应用所设计的其它结构。Bus 602 may include, but is not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus. In particular, for in-vehicle devices, thebus 602 may also include a controller area network (CAN) bus or other structure designed for applications in automobiles.

计算设备600还可包括工作存储器614，该工作存储器614可以是任何类型的能够存储有利于处理器604的工作的指令和/或数据的工作存储器并且可以包括但不限于随机存取存储器和/或只读存储设备。Computing device 600 may also include workingmemory 614, which may be any type of working memory capable of storing instructions and/or data that facilitates the operation of processor 604 and may include, but is not limited to, random access memory and/or read-only storage device.

软件组件可位于工作存储器614中，这些软件组件包括但不限于操作系统616、一个或多个应用程序618、驱动程序和/或其它数据和代码。用于实现上述方法和步骤的指令可包含在所述一个或多个应用程序618中，并且前述各种装置/服务器/客户端设备的模块/单元/组件可通过处理器604读取和执行所述一个或多个应用程序618的指令来实现。Software components may be located in workingmemory 614, including, but not limited to,operating system 616, one ormore application programs 618, drivers, and/or other data and code. Instructions for implementing the methods and steps described above may be contained in the one ormore application programs 618, and the modules/units/components of the various devices/servers/client devices described above may be read and executed by the processor 604. One or more of the instructions of theapplication 618 are implemented.

也应该认识到可根据具体需求而做出变化。例如，也可使用定制硬件、和/或特定组件可在硬件、软件、固件、中间件、微代码、硬件描述语音或其任何组合中实现。此外，可采用与其它计算设备、例如网络输入/输出设备等的连接。例如，可通过具有汇编语言或硬件编程语言(例如，VERILOG、VHDL、C++)的编程硬件(例如，包括现场可编程门阵列(FPGA)和/或可编程逻辑阵列(PLA)的可编程逻辑电路)利用根据本发明的逻辑和算法来实现所公开的方法和设备的部分或全部。It should also be recognized that variations may be made according to specific needs. For example, custom hardware may also be used, and/or certain components may be implemented in hardware, software, firmware, middleware, microcode, hardware description voice, or any combination thereof. Additionally, connections to other computing devices, such as network input/output devices, etc., may be employed. For example, programmable logic circuits (eg, programmable logic circuits including field programmable gate arrays (FPGA) and/or programmable logic arrays (PLA)) may be programmed with assembly language or hardware programming languages (eg, VERILOG, VHDL, C++). ) utilize logic and algorithms in accordance with the present invention to implement some or all of the disclosed methods and apparatus.

尽管目前为止已经参考附图描述了本发明的各方面，但是上述方法、系统和设备仅是示例，并且本发明的范围不限于这些方面，而是仅由所附权利要求及其等同物来限定。各种组件可被省略或者也可被等同组件替代。另外，也可以在与本发明中描述的顺序不同的顺序实现所述步骤。此外，可以按各种方式组合各种组件。也重要的是，随着技术的发展，所描述的组件中的许多组件可被之后出现的等同组件所替代。Although aspects of the present invention have so far been described with reference to the accompanying drawings, the above-described methods, systems, and apparatus are merely examples, and the scope of the present invention is not limited to these aspects, but only by the appended claims and their equivalents . Various components may be omitted or may be replaced by equivalent components. Additionally, the steps may also be performed in an order different from that described in this disclosure. Furthermore, the various components can be combined in various ways. It is also important that, as technology develops, many of the components described may be replaced by equivalent components that appear later.

Claims (15)

1. A method for testing a sensor configuration of a vehicle, the method comprising:

building a virtual road environment;

driving a virtual vehicle having a preset sensor configuration in the virtual road environment;

collecting measurement signals obtained by configured sensors in the virtual road environment; and

analyzing the measurement signal to determine whether the sensor configuration meets measurement requirements.

2. The method of claim 1, wherein the virtual road environment is changeable on demand.

3. The method of claim 1, wherein the virtual road environment comprises at least one of: road signs, lane lines, obstacles, road edges, bridges, utility poles, overhead structures, tunnels, traffic signs, trees, weather, time, or traffic participants.

4. The method of claim 1, wherein the sensor configuration comprises a type, number, mounting location, parameters, and/or a combination of sensors.

5. The method of claim 4, wherein the type of sensor comprises a lidar, a millimeter wave radar, a camera, and/or an ultrasonic sensor.

6. The method of claim 1, wherein if the measurement signal indicates that the sensor configuration does not meet the measurement requirements, then altering the sensor configuration for re-measurement.

7. The method of claim 1, wherein the measurement requirement comprises a threshold detection rate for a particular target, the method further comprising:

changing the virtual road environment to determine whether the sensor configuration detects a detection rate of the particular target greater than the threshold detection rate under various virtual road environments.

8. The method of claim 1, further comprising: different sensor configurations are used in the virtual road environment for testing to obtain an optimal sensor configuration.

9. A system for testing a sensor configuration of a vehicle, the system comprising:

an environment construction unit for constructing a virtual road environment;

a vehicle simulation unit for providing a virtual vehicle traveling in the virtual road environment;

a sensor configuration unit for configuring a sensor mounted on the virtual vehicle;

an acquisition unit for acquiring measurement signals obtained in the virtual road environment by the configured sensors; and

an analysis unit for analyzing the measurement signal to determine whether the configuration of the sensor meets measurement requirements.

10. The system of claim 9, wherein the virtual road environment is changeable as needed.

11. The system of claim 9, wherein the virtual road environment comprises at least one of: road signs, lane lines, obstacles, road edges, bridges, utility poles, overhead structures, traffic signs, tunnels, trees, weather, time, or traffic participants.

12. The system of claim 9, wherein the sensor configuration comprises a type, number, mounting location, parameters, and/or a combination of sensors.

13. The system of claim 9, wherein the analysis unit is further configured to determine an optimal sensor configuration.

14. An apparatus for testing a sensor configuration of a vehicle, the apparatus comprising:

a memory storing a computer program; and

a processor coupled to the memory, the computer program when executed by the processor implementing the steps of:

building a virtual road environment;

driving a virtual vehicle having a preset sensor configuration in the virtual road environment;

collecting measurement signals obtained by configured sensors in the virtual road environment; and

analyzing the measurement signal to determine whether the sensor configuration meets measurement requirements.

15. A non-transitory computer readable medium storing a computer program which, when executed by a processor, performs the method of any one of claims 1-8.

Images