技术领域technical field
本发明实施例涉及通信技术领域，尤其涉及一种车辆控制方法、装置及相关计算机程序产品。The embodiments of the present invention relate to the field of communication technologies, and in particular, to a vehicle control method, device and related computer program products.
背景技术Background technique
目前，随着人们对高效生活的追求，机动车辆作为便利、快捷的交通工具，被人们广泛使用，而，随着机动车辆使用率的激增，道路交通越来越拥挤，道路交通事故也在逐渐增多。为了减少道路交通事故的发生，在驾驶系统领域，通常使用DSRC(DedicatedShortRange Communication，专用短程通信技术)技术，提供车与车之间、车与路之间以及车与智能交通系统的信息交互，使车辆持续感知周围的环境，并控制车身采取相应的措施，从而能够有效的减少事故的发生。At present, with people's pursuit of efficient life, motor vehicles are widely used as a convenient and fast means of transportation. However, with the sharp increase in the utilization rate of motor vehicles, road traffic is becoming more and more congested, and road traffic accidents are gradually increasing. increase. In order to reduce the occurrence of road traffic accidents, in the field of driving systems, DSRC (Dedicated Short Range Communication) technology is usually used to provide information interaction between vehicles, between vehicles and roads, and between vehicles and intelligent transportation systems, so that The vehicle continuously perceives the surrounding environment and controls the body to take corresponding measures, which can effectively reduce the occurrence of accidents.
具体的，在1000米的距离之内，DSRC模块之间能够通过其通信协议，实时获取相互之间对应车辆的状态，进而根据车辆在当前时刻的实时状态，计算自车与对方车辆之间是否存在碰撞风险，并发出碰撞告警，采取减速、刹车或者变道等措施，以避免碰撞。Specifically, within a distance of 1000 meters, the DSRC modules can obtain the status of the corresponding vehicles in real time through their communication protocols, and then calculate whether the relationship between the own vehicle and the other vehicle is based on the real-time status of the vehicle at the current moment. There is a risk of collision, and a collision warning is issued, and measures such as slowing down, braking, or changing lanes are taken to avoid collisions.
从上述描述可以看出，自身车辆的DSRC模块，实质上是与其他车辆的DSRC模块进行信息交互，因此，该方式实施的前提是，所有车辆均设置有DSRC模块。此外，自身车辆的DSRC模块，不仅需要不断检测自身车辆的位置与速度，而且还需要与所有距离范围内的其他车辆的DSRC模块通信，并不断的计算，由此可见，DSRC模块的检测和通信过程相对复杂，而且计算量也相对较大。综上，通过DSRC模块实施车间通信，进而减少事故发生的方法，成本较高，而且适用性较差。It can be seen from the above description that the DSRC module of the own vehicle essentially exchanges information with the DSRC modules of other vehicles. Therefore, the premise of implementing this method is that all vehicles are equipped with DSRC modules. In addition, the DSRC module of the self-vehicle not only needs to continuously detect the position and speed of the own vehicle, but also needs to communicate with the DSRC modules of other vehicles within all distances and perform continuous calculations. It can be seen that the detection and communication of the DSRC module The process is relatively complex, and the amount of calculation is relatively large. To sum up, the method of implementing inter-vehicle communication through the DSRC module to reduce accidents has high cost and poor applicability.
发明内容Contents of the invention
本发明实施例提供了一种车辆控制方法、装置及相关计算机程序产品，以解决现有技术成本高，且适用性差的问题。Embodiments of the present invention provide a vehicle control method, device and related computer program products to solve the problems of high cost and poor applicability in the prior art.
第一方面，本发明实施例提供了一种车辆控制方法，该方法在实施时，本车以自身为参照，获取障碍物T1时刻的状态参数，即，障碍物在T1时刻的朝向信息，和障碍物相对于本车的位置信息，然后，本车获取障碍物在T1时刻之前N个时刻的状态参数，进而，结合该N个历史状态参数，以及T1时刻的状态参数，计算得到障碍物T2时刻的状态参数，并根据障碍物T2时刻的状态参数控制本车的行为。其中，本实施例中，T2时刻是T1时刻之后的时刻，且T1时刻可以理解为当前时刻，那么，T2时刻作为T1时刻之后的时刻，即为将来的时刻。In the first aspect, the embodiment of the present invention provides a vehicle control method. When the method is implemented, the vehicle uses itself as a reference to obtain the state parameters of the obstacle at T1 time, that is, the orientation information of the obstacle at T1 time, and The position information of the obstacle relative to the own vehicle, and then, the own vehicle obtains the state parameters of the obstacle at N moments before the time T1, and then combines the N historical state parameters and the state parameters at the time T1 to calculate the obstacle T2 The state parameters of the time, and control the behavior of the vehicle according to the state parameters of the obstacle T2 time. Wherein, in this embodiment, the time T2 is the time after the time T1, and the time T1 can be understood as the current time, then the time T2 is regarded as the time after the time T1, that is, the time in the future.
也就是说，本方案以本车作为参照物，获取障碍物相对于本车的当前状态，并结合障碍物持续一段时间的历史状态，能够预测障碍物即将发生的行为，进而能够以障碍物即将发生的行为控制本车的行为，减少道路交通事故。此外，需要说明的是，由于需要结合障碍物持续一段时间的历史状态，所以，本方案中，N是大于1的正整数。That is to say, this scheme takes the own vehicle as a reference object, obtains the current state of the obstacle relative to the own vehicle, and combines the historical state of the obstacle for a period of time to predict the upcoming behavior of the obstacle, and then can use the impending behavior of the obstacle The behavior that occurs controls the behavior of the vehicle and reduces road traffic accidents. In addition, it should be noted that, in this solution, N is a positive integer greater than 1 because it is necessary to combine the historical state of the obstacle for a period of time.
结合第一方面，在第一方面第一种可能的实现方式中，本车根据障碍物T1时刻和前N个时刻的状态参数，计算T2时刻的状态参数，实质上是根据T1时刻之前的一段历史行为轨迹，预测T2时刻的状态。因此，本实施例中，本车在获知障碍物T1时刻和前N个时刻的状态参数之后，可以将T1时刻的状态参数和N个时刻的状态参数转换为障碍物的轨迹线，该轨迹线表示的是障碍物的一段历史行为轨迹，进而根据该段历史行为轨迹确定障碍物未来的状态。In combination with the first aspect, in the first possible implementation of the first aspect, the vehicle calculates the state parameters at T2 according to the state parameters at time T1 of the obstacle and the state parameters at the previous N moments, which is essentially based on a period before time T1 Historical behavior trajectory, predicting the state at T2 time. Therefore, in this embodiment, after knowing the state parameters of the obstacle at time T1 and the previous N times, the vehicle can convert the state parameters at time T1 and the state parameters at N times into the trajectory of the obstacle. It represents a historical behavior trajectory of the obstacle, and then determines the future state of the obstacle according to the historical behavior trajectory.
由此可见，通过历史行为轨迹预测未来状态的方式，能够直观的判断出障碍物T2时刻的状态，不仅准确度高，而且能够简单明了的确定本车下一刻的行为。It can be seen that the way of predicting the future state through the historical behavior trajectory can intuitively judge the state of the obstacle at T2, which not only has high accuracy, but also can simply and clearly determine the behavior of the vehicle at the next moment.
结合第一方面，在第一方面第二种可能的实现方式中，具体的，本方案可以预先训练模型，该模型用于计算障碍物处于某个状态时的概率值。因此，本实施例中，在获知障碍物T1时刻的状态参数时，可以假设障碍物在T2时刻可能会在的方位，并预测相应方位对应的预测状态参数，分别将每个预测状态参数以及T1时刻的状态参数代入模型，分别计算得到每个预测状态参数初始概率值，形成第一概率组。进而，提取T1时刻之前N个时刻对应的概率组，其中，N个概率组是该障碍物分别在N个时刻对应的预测状态参数的最终概率值，然后，针对每个方位，根据其对应的第一概率组中的概率值，和N个概率组中的概率值计算，得到第二概率组，即，障碍物T2时刻每个预测状态参数的最终概率值，并选择最终概率值最大的预测状态参数作为T2时刻的状态参数。In combination with the first aspect, in the second possible implementation manner of the first aspect, specifically, this solution may pre-train a model, and the model is used to calculate the probability value when the obstacle is in a certain state. Therefore, in this embodiment, when the state parameters of the obstacle at time T1 are obtained, it is possible to assume the possible orientation of the obstacle at time T2, and predict the predicted state parameters corresponding to the corresponding orientations, and each predicted state parameter and T1 The state parameters at each moment are substituted into the model, and the initial probability values of each predicted state parameter are calculated separately to form the first probability group. Furthermore, the probability groups corresponding to N moments before T1 are extracted, where the N probability groups are the final probability values of the predicted state parameters corresponding to the obstacle at N moments respectively, and then, for each orientation, according to its corresponding Calculate the probability value in the first probability group and the probability value in the N probability groups to obtain the second probability group, that is, the final probability value of each predicted state parameter at the time of obstacle T2, and select the prediction with the largest final probability value The state parameter is used as the state parameter at T2 time.
也就是说，本方案为了及时、准确的预测障碍物下一刻的行为，本方案中，每隔一定时间段获取一次障碍物的状态参数，并根据预先训练的模型，计算障碍物下一刻的状态参数，从而预测障碍物下一刻的行为，不仅操作简单，计算量小，而且所预测的状态参数准确度也较高。That is to say, in order to timely and accurately predict the behavior of the obstacle at the next moment, in this solution, the state parameters of the obstacle are obtained every certain period of time, and the state of the obstacle at the next moment is calculated according to the pre-trained model Parameters, so as to predict the behavior of the obstacle at the next moment, not only the operation is simple, the calculation amount is small, but the accuracy of the predicted state parameters is also high.
结合第一方面，在第一方面第三种可能的实现方式中，通常，车辆和行人在行动时，应当遵守交通规则，因此，本车在获取障碍物T1时刻的状态参数时，同时，还可以检测障碍物的转向灯信息，进而根据转向灯信息判断障碍物转向的方向。In combination with the first aspect, in the third possible implementation of the first aspect, generally, vehicles and pedestrians should abide by the traffic rules when they are acting. Therefore, when the vehicle obtains the state parameters of the obstacle T1, at the same time, it also The turn signal information of obstacles can be detected, and then the direction in which the obstacle turns can be judged based on the turn signal information.
采用本实现方式，以障碍物的转向灯信息，以及其历史状态参数为依据，预测障碍物将来的行为轨迹，能够相对准确的判断障碍物的行为轨迹，不仅处理过程简单，而且能够更加有效的避免道路交通事故的发生。Using this implementation method, based on the turning signal information of the obstacle and its historical state parameters, the future behavior trajectory of the obstacle can be predicted, and the behavior trajectory of the obstacle can be judged relatively accurately. Not only the processing process is simple, but also more effective Avoid road traffic accidents.
结合第一方面，在第一方面第四种可能的实现方式中，本车在获取障碍物T1时刻的状态参数之前，还可以先定位自身的精确位置，具体的，可以结合预先输入的地图，定位本车在地图上的初始位置，然后，可以通过摄像头等设备采集初始位置周围的环境特征，并检测所采集的环境特征与地图上相应位置的信息匹配度，筛选出匹配度最高的区域，从而能够根据匹配度最高的区域调整初始位置，得到本车的精确位置。In combination with the first aspect, in the fourth possible implementation of the first aspect, before the vehicle obtains the state parameters of the obstacle T1, it can also locate its own precise position. Specifically, it can combine the pre-input map, Locate the initial position of the vehicle on the map, and then collect the environmental features around the initial position through cameras and other equipment, and detect the matching degree between the collected environmental features and the information of the corresponding position on the map, and filter out the area with the highest matching degree. Therefore, the initial position can be adjusted according to the area with the highest matching degree, and the precise position of the vehicle can be obtained.
其中，需要指出的是，本方案中，为了使本车的定位更加精确，在首次确定匹配度最高的区域之后，还可以在该区域内再次采集特征，并重复上述检测和调整的步骤，并在重复几次之后，得到本车的精确位置。Among them, it should be pointed out that in this solution, in order to make the localization of the vehicle more accurate, after determining the area with the highest matching degree for the first time, the features can be collected again in this area, and the above steps of detection and adjustment can be repeated, and After repeating several times, the precise position of the vehicle is obtained.
由此可见，采用本实现方式，不仅能够精确的定位本车的位置，进而基于本车的精确位置，能够进一步准确的获取本车周围的环境信息，进而为计算障碍物即将发生的行为提供精确的参数依据。It can be seen that with this implementation method, not only can the position of the vehicle be accurately located, but also based on the precise position of the vehicle, the environmental information around the vehicle can be further accurately obtained, thereby providing accurate information for calculating the upcoming behavior of obstacles. based on the parameters.
第二方面，本发明实施例还提供了一种车辆控制装置，该装置包括用于执行第一方面及第一方面各实现方式的中方法步骤的模块和单元，具体的，本发明实施例此处不再赘述。In the second aspect, the embodiment of the present invention also provides a vehicle control device, the device includes modules and units for performing the method steps in the first aspect and each implementation manner of the first aspect, specifically, this embodiment of the present invention I won't repeat them here.
第三方面，本申请还提供了一种车辆控制设备，包括：处理器和存储器；其中，处理器可以执行存储器中所存储的程序或指令，从而实现以第一方面各种实现方式的车辆控制方法。In the third aspect, the present application also provides a vehicle control device, including: a processor and a memory; wherein, the processor can execute the programs or instructions stored in the memory, so as to realize the vehicle control in the various implementation modes of the first aspect method.
第四方面，本发明实施例还提供了一种计算机程序产品，包括指令，当指令在计算机上运行时，使得计算机执行第一方面的方法。In a fourth aspect, an embodiment of the present invention further provides a computer program product, including instructions, and when the instructions are run on a computer, the computer is made to execute the method of the first aspect.
采用本发明实施例的车辆控制方法、装置及相关计算机程序产品，首先获取障碍物T1时刻的状态参数，然后，根据T1时刻的状态参数以及T1时刻之前N个时刻的状态参数，计算障碍物T2时刻的状态参数，进而，根据T2时刻的状态参数控制本车的行为。其中，本方案中，状态参数包括障碍物的朝向信息，和障碍物相对于本车的位置信息，T2时刻是T1时刻之后的时刻，N是大于1的正整数。由此可见，本发明实施例的技术方案，通过障碍物在T1时刻及其之前N个时刻的历史状态参数，计算出其在T1时刻之后的状态参数，不仅计算量小，而且执行过程更为简单，此外，本方案在实施过程中，本车无需与障碍物进行通信，因此，也无需安装DSRC模块，所以，与现有技术相比，本方案更加节省成本，适用性更好。Using the vehicle control method, device and related computer program products of the embodiments of the present invention, first obtain the state parameters of the obstacle at T1 time, and then calculate the obstacle T2 according to the state parameters at T1 time and the state parameters at N times before T1 time The state parameters at time T2, and then control the behavior of the vehicle according to the state parameters at T2 time. Wherein, in this solution, the state parameters include the orientation information of the obstacle and the position information of the obstacle relative to the own vehicle, the time T2 is the time after the time T1, and N is a positive integer greater than 1. It can be seen that the technical solution of the embodiment of the present invention calculates the state parameters of the obstacle after the time T1 through the historical state parameters of the obstacle at the time T1 and N times before it, not only the amount of calculation is small, but also the execution process is more efficient. Simple. In addition, during the implementation of this solution, the vehicle does not need to communicate with obstacles, so there is no need to install a DSRC module. Therefore, compared with the existing technology, this solution is more cost-effective and has better applicability.
附图说明Description of drawings
为了更清楚地说明本发明实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings that need to be used in the embodiments will be briefly introduced below. Obviously, for those of ordinary skill in the art, without paying creative labor Below, other drawings can also be obtained from these drawings.
图1为本发明实施例提供的车辆控制方法的方法流程图；Fig. 1 is a method flowchart of a vehicle control method provided by an embodiment of the present invention;
图2为本发明实施例提供的道路模型示意图；Fig. 2 is a schematic diagram of a road model provided by an embodiment of the present invention;
图3为本发明实施例提供的车辆行为的第一种实施方式的道路模型示意图；FIG. 3 is a schematic diagram of a road model of a first embodiment of vehicle behavior provided by an embodiment of the present invention;
图4为本发明实施例提供的车辆行为的第二种实施方式的道路模型示意图；FIG. 4 is a schematic diagram of a road model of a second embodiment of vehicle behavior provided by an embodiment of the present invention;
图5为本发明实施例提供的车辆行为的第三种实施方式的道路模型示意图；FIG. 5 is a schematic diagram of a road model of a third embodiment of vehicle behavior provided by an embodiment of the present invention;
图6为本发明实施例提供的车辆行为的第四种实施方式的道路模型示意图；FIG. 6 is a schematic diagram of a road model of a fourth embodiment of vehicle behavior provided by an embodiment of the present invention;
图7为本发明实施例提供的车辆控制方法的示例图；FIG. 7 is an example diagram of a vehicle control method provided by an embodiment of the present invention;
图8为本发明实施例提供的车辆控制装置的结构示意图；FIG. 8 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present invention;
图9为本发明实施例提供的车辆控制设备的结构示意图。Fig. 9 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present invention.
具体实施方式Detailed ways
下面结合附图，对本发明的实施例进行描述。Embodiments of the present invention will be described below in conjunction with the accompanying drawings.
其中，根据对现有技术的描述可知，采用DSRC技术获取障碍物的状态信息，本车只能获取到障碍物当前时刻的信息，对于障碍物即将发生的行为动作，无法得知，而，很大部分道路交通事故，是由于本车错误的判断障碍物即将发生的行为动作而发生的，因此，采用DSRC技术规避道路交通事故的作用极其有限。Among them, according to the description of the prior art, it can be seen that the state information of the obstacle is obtained by using the DSRC technology, and the vehicle can only obtain the information of the current moment of the obstacle, and it is impossible to know the upcoming behavior of the obstacle. Most road traffic accidents occur due to the vehicle's wrong judgment of the imminent behavior of obstacles. Therefore, the use of DSRC technology to avoid road traffic accidents is extremely limited.
有鉴于此，本发明实施例提供了一种车辆控制方法，能够预测障碍物即将发生的行为，进而根据障碍物即将发生的行为控制本车的行为，以规避道路交通事故的发生。参见图1，图1为本发明实施例提供的车辆控制方法的方法流程图，本实施例的方法包括以下步骤：In view of this, the embodiment of the present invention provides a vehicle control method, which can predict the upcoming behavior of obstacles, and then control the behavior of the own vehicle according to the upcoming behavior of obstacles, so as to avoid the occurrence of road traffic accidents. Referring to FIG. 1, FIG. 1 is a method flow chart of a vehicle control method provided by an embodiment of the present invention. The method of this embodiment includes the following steps:
步骤S101，获取障碍物T1时刻的状态参数。Step S101, obtaining the state parameters of the obstacle T1.
其中，本发明实施例中，状态参数可以包括，障碍物的朝向信息，速度信息，以及障碍物相对于HV(Host Vehicle，本车)的位置信息等信息，而T1时刻可以是当前时刻。Wherein, in the embodiment of the present invention, the state parameter may include information such as the orientation information of the obstacle, the speed information, and the position information of the obstacle relative to the HV (Host Vehicle, own vehicle), and the time T1 may be the current time.
作为HV障碍物的对象可以包括，HV前方的行人、自行车和机动车等，本实施例中，HV可以通过加速度传感器，或者激光传感器等，检测每个对象的行驶速度，从而获取每个障碍物当前时刻的速度信息。此外，作为控制HV行为的参照物，障碍物的部分状态参数可以参照HV的状态和道路信息确定。为了便于确定HV和障碍物的相对关系，本实施例中，可以创建道路模型，并进一步以道路模型为坐标系，定位障碍物的朝向信息和相对于HV的位置信息。其中，道路模型是按照一定比例将实际道路缩小后的道路模拟图，并且，与实际位置相对应的，道路模型中标注交通灯，车道线以及减速牌等标志，同时，还呈现有HV与障碍物的相对位置。由此可见，道路模型能够直观的展示HV、道路和障碍之间的相对关系，并且能够为确定障碍物的位置信息，提供参考坐标系。Objects as HV obstacles can include pedestrians, bicycles, and motor vehicles in front of the HV. In this embodiment, the HV can detect the driving speed of each object through an acceleration sensor or a laser sensor, etc., so as to obtain the information of each obstacle. Speed information at the current moment. In addition, as a reference for controlling HV behavior, some state parameters of obstacles can be determined with reference to HV state and road information. In order to facilitate the determination of the relative relationship between the HV and the obstacle, in this embodiment, a road model can be created, and the orientation information of the obstacle and the position information relative to the HV can be located further using the road model as a coordinate system. Among them, the road model is a road simulation map that reduces the actual road according to a certain ratio, and, corresponding to the actual location, the road model is marked with signs such as traffic lights, lane lines, and deceleration signs, and at the same time, HV and obstacles are also displayed. relative position of the object. It can be seen that the road model can intuitively display the relative relationship between HV, road and obstacles, and can provide a reference coordinate system for determining the position information of obstacles.
具体的，HV可以通过预先设置的摄像头或者行车记录仪等设备，获取其周围的环境图像。其中，环境图像包括，HV所在车道的相关图像，以及HV周围障碍物的图像。在获取到环境图像之后，可以从车道的相关图像中，提取车道宽度，HV所在的具体车道，前方是否有交通灯，及当前交通灯的指示等参数，相应的，还可以根据HV周围障碍物的图像，获知其前方的障碍物，进而，根据上述信息创建道路模型。Specifically, the HV can obtain images of its surrounding environment through a pre-set camera or a driving recorder and other devices. Wherein, the environment image includes related images of the lane where the HV is located, and images of obstacles around the HV. After the environment image is obtained, parameters such as the width of the lane, the specific lane where the HV is located, whether there is a traffic light ahead, and the indication of the current traffic light can be extracted from the relevant images of the lane. image, learn the obstacles in front of it, and then create a road model based on the above information.
例如，请参见图2，图2为本发明实施例提供的道路模型示意图，图2所示的道路模型是三车道的道路模型，其中，道路前方设置有交通灯，RV(Remote Vehicle，他车)是相对于HV而言的，在本实施例中，RV1和RV2是两个障碍物，并且，图2所示的道路模型很明确的呈现了HV与RV1、RV2的位置关系。For example, referring to FIG. 2, FIG. 2 is a schematic diagram of a road model provided by an embodiment of the present invention. The road model shown in FIG. ) is relative to HV. In this embodiment, RV1 and RV2 are two obstacles, and the road model shown in FIG. 2 clearly presents the positional relationship between HV, RV1 and RV2.
由此可见，本发明实施例通过创建道路模型，能够很直观的展示HV与障碍物的位置关系，并且，还能够为障碍物状态参数的确定，提供参考坐标系，从而能够使HV的行为控制更加简单。It can be seen that the embodiment of the present invention can intuitively display the positional relationship between the HV and the obstacle by creating a road model, and can also provide a reference coordinate system for the determination of the obstacle state parameters, so that the behavior of the HV can be controlled more simple.
基于上述描述，在创建道路模型之后，可以以道路模型为坐标系，获取障碍物的朝向信息和相对于HV的位置信息。具体的，参考图2，本方案可以基于道路模型，以HV的位置为参考原点，读取障碍物当前时刻的坐标，得到障碍物的位置信息。当然，需要说明的是，在道路模型中，HV和障碍物的模型均占据一定面积，为了保证所得到的位置信息的准确性，本实施例中，可以以每个车辆模型的中心位置的坐标，表示相应车辆的位置。Based on the above description, after the road model is created, the orientation information of the obstacle and the position information relative to the HV can be obtained using the road model as a coordinate system. Specifically, referring to FIG. 2 , this solution can be based on the road model, with the position of the HV as the reference origin, and read the coordinates of the obstacle at the current moment to obtain the position information of the obstacle. Of course, it should be noted that in the road model, the HV and obstacle models both occupy a certain area. In order to ensure the accuracy of the obtained position information, in this embodiment, the coordinates of the center position of each vehicle model can be , indicating the position of the corresponding vehicle.
同样的，在计算障碍物的朝向信息时，可以以HV的纵向方向为参考，获取障碍物的车头到车尾方向的轴线，并将障碍物的车头方向作为该轴线的指向方向，从而得到障碍物的指向向量，通过计算障碍物的指向向量与参考方向的夹角，得到相应障碍物的朝向信息。Similarly, when calculating the orientation information of obstacles, the longitudinal direction of the HV can be used as a reference to obtain the axis from the front to the rear of the obstacle, and use the front direction of the obstacle as the direction of the axis to obtain the obstacle The pointing vector of the object, by calculating the angle between the pointing vector of the obstacle and the reference direction, the orientation information of the corresponding obstacle is obtained.
此外，需要说明的是，在获取上述状态参数的同时，如果障碍物是机动车，还可以检测当前障碍物是否开启转向灯，从而可以结合障碍物的各项状态参数及转向灯的状态，预测障碍物的行为轨迹。In addition, it should be noted that while obtaining the above state parameters, if the obstacle is a motor vehicle, it can also detect whether the current obstacle turns on the turn signal, so that it can be combined with the state parameters of the obstacle and the state of the turn signal to predict The behavior trajectory of obstacles.
此外，上述描述是通过摄像设备以及传感器等，获取HV周围的环境参数的过程，其中，通过上述实现过程，所得到的仅仅是以HV自身为参照的环境参数，为了能够获知更多的环境信息，在本发明的一个可选实施例中，可以首先定位HV的精确位置。In addition, the above description is the process of acquiring the environmental parameters around the HV through the camera equipment and sensors, etc., wherein, through the above implementation process, only the environmental parameters with the HV itself as a reference are obtained. In order to obtain more environmental information , in an alternative embodiment of the present invention, the precise position of the HV can be located first.
具体的，可以使用GPS(Global Positioning System，全球定位系统)和IMU(Inertial measurement unit，惯性测量单元)，结合预先输入的地图，定位HV在地图上的初始位置，然后，可以通过摄像头等设备采集初始位置周围的环境特征，并检测所采集的环境特征与地图上相应位置的信息匹配度，筛选出匹配度最高的区域，从而能够根据匹配度最高的区域调整初始位置，得到HV的精确位置。当然，本实施例仅仅是对该定位过程的简单描述，在实际操作过程中，为了得到HV的精确位置，可以在确定匹配度最高的区域之后，在该区域内再次采集特征，并重复上述检测和调整的步骤，以得到HV的精确位置。Specifically, GPS (Global Positioning System, Global Positioning System) and IMU (Inertial measurement unit, inertial measurement unit) can be used, combined with a pre-input map, to locate the initial position of the HV on the map, and then, it can be collected by a camera and other equipment The environmental characteristics around the initial position, and detect the matching degree between the collected environmental characteristics and the corresponding position information on the map, and filter out the area with the highest matching degree, so that the initial position can be adjusted according to the area with the highest matching degree, and the precise position of the HV can be obtained. Of course, this embodiment is only a simple description of the positioning process. In the actual operation process, in order to obtain the precise position of the HV, after the area with the highest matching degree is determined, features can be collected again in this area, and the above detection can be repeated. and adjustment steps to get the exact position of the HV.
需要指出的是，上述定位过程是本领域技术人员所熟知的技术，可以参考粒子滤波算法，本发明实施例此处不再详述。It should be pointed out that the above positioning process is a technology well known to those skilled in the art, and a particle filter algorithm may be referred to, which will not be described in detail in this embodiment of the present invention.
由此可见，采用本步骤的方法，不仅能够精确的定位HV的位置，而且基于HV的精确位置，还能够进一步准确的获取本车周围的环境信息，进而为计算障碍物即将发生的行为提供精确的参数依据。It can be seen that the method of this step can not only accurately locate the position of the HV, but also can further accurately obtain the environmental information around the vehicle based on the precise position of the HV, thereby providing accurate information for calculating the upcoming behavior of obstacles. based on the parameters.
步骤S102，根据T1时刻的状态参数以及T1时刻之前N个时刻的状态参数，计算障碍物T2时刻的状态参数。Step S102, calculating the state parameter of the obstacle at time T2 according to the state parameter at time T1 and the state parameters at time N before time T1.
其中，本实施例中，T2时刻是T1时刻之后的时刻。具体的，可以是与T1时刻间隔一定时间段的下一时刻。例如，当将间隔时间段设置为10ms时，那么，T2时刻即为T1时刻10ms之后的时刻。N是大于1的正整数。Wherein, in this embodiment, time T2 is a time after time T1. Specifically, it may be the next moment that is separated from the time T1 by a certain period of time. For example, when the interval period is set to 10ms, then the time T2 is the time 10ms after the time T1. N is a positive integer greater than 1.
需要说明的是，车辆和行人在行动时，应当遵守交通规则，例如，机动车在转弯或者变道时，应当开启转向灯，以提醒其他车辆的用户，因此，当HV检测到其前方车辆开启转向灯时，可以根据转向灯判断其前方车辆转向的方向，进而确定该车辆在T2时刻的状态参数。然而，在实际生活中，许多行人并不遵守交通规则，例如。很多用户在开车时操作不规范，变道不开转向灯的情况时常出现，因此，如果HV仅依靠转向灯判断障碍物下一刻的行为，将会产生大量错误的判断，从而造成道路交通事故。有鉴于此，本方案中，当障碍物未开启转向灯时，根据障碍物在T1时刻及其之前N个时刻的状态参数，确定障碍物在T2时刻的状态参数，以确定障碍物即将发生的行为。It should be noted that vehicles and pedestrians should abide by traffic rules when they act. For example, when a motor vehicle is turning or changing lanes, it should turn on the turn signal to remind other vehicle users. Therefore, when the HV detects that the vehicle in front of it is turned on When the turn signal is turned, the direction of the vehicle in front of it can be judged according to the turn signal, and then the state parameters of the vehicle at T2 can be determined. However, in real life, many pedestrians do not obey traffic rules, eg. Many users do not operate in a standardized manner when driving, and often change lanes without turning on the turn signal. Therefore, if the HV only relies on the turn signal to judge the next behavior of the obstacle, a large number of wrong judgments will be generated, resulting in road traffic accidents. In view of this, in this solution, when the obstacle does not turn on the turn signal, according to the state parameters of the obstacle at the time T1 and N times before it, the state parameters of the obstacle at the time T2 are determined to determine the impending occurrence of the obstacle Behavior.
其中，HV根据障碍物T1时刻和前N个时刻的状态参数，计算T2时刻的状态参数，实质上是根据T1时刻之前的一段历史行为轨迹，预测T2时刻的状态。因此，本实施例中，HV在获知障碍物T1时刻和前N个时刻的状态参数之后，可以将T1时刻的状态参数和N个时刻的状态参数转换为障碍物的轨迹线，该轨迹线表示的是障碍物的一段历史行为轨迹，进而根据该段历史行为轨迹确定障碍物未来的状态。Among them, HV calculates the state parameters at T2 according to the state parameters of the obstacle at T1 and the previous N moments, and essentially predicts the state at T2 based on a historical behavior track before T1. Therefore, in this embodiment, after the HV knows the state parameters at time T1 and the previous N times of the obstacle, it can convert the state parameters at time T1 and the state parameters at N times into the trajectory of the obstacle, which represents It is a historical behavior trajectory of the obstacle, and then the future state of the obstacle is determined according to the historical behavior trajectory.
此外，具体的，本实施例中，可以预先训练模型，该模型用于计算障碍物处于某个状态时的概率值。因此，本实施例中，在获知障碍物T1时刻的状态参数时，可以假设障碍物在T2时刻可能会在的方位，并预测相应方位对应的预测状态参数，分别将每个预测状态参数以及T1时刻的状态参数代入模型，分别计算得到每个预测状态参数初始概率值，形成第一概率组。进而，提取T1时刻之前N个时刻对应的概率组，其中，N个概率组是该障碍物分别在N个时刻对应的预测状态参数的最终概率值，然后，针对每个方位，根据其对应的第一概率组中的概率值，和N个概率组中的概率值计算，得到第二概率组，即，障碍物T2时刻每个预测状态参数的最终概率值，并选择最终概率值最大的预测状态参数作为T2时刻的状态参数。In addition, specifically, in this embodiment, a model may be pre-trained, and the model is used to calculate the probability value when the obstacle is in a certain state. Therefore, in this embodiment, when the state parameters of the obstacle at time T1 are obtained, it is possible to assume the possible orientation of the obstacle at time T2, and predict the predicted state parameters corresponding to the corresponding orientations, and each predicted state parameter and T1 The state parameters at each moment are substituted into the model, and the initial probability values of each predicted state parameter are calculated separately to form the first probability group. Furthermore, the probability groups corresponding to N moments before T1 are extracted, where the N probability groups are the final probability values of the predicted state parameters corresponding to the obstacle at N moments respectively, and then, for each orientation, according to its corresponding Calculate the probability value in the first probability group and the probability value in the N probability groups to obtain the second probability group, that is, the final probability value of each predicted state parameter at the time of obstacle T2, and select the prediction with the largest final probability value The state parameter is used as the state parameter at T2 time.
例如，障碍物在T1时刻的状态参数是A，障碍物在T2时刻可能会向右转、直行或向左转，根据障碍物当前的速度信息，分别生成其向右转的预测状态参数X、直行的预测状态参数Y和向左转的预测状态参数Z，分别计算预测状态参数X的初始概率值，得到30％，预测状态参数Y的初始概率值，得到40％，预测状态参数Z的初始概率值，得到70％。然后，调取障碍物在T1时刻之前3个时刻的概率组，并分别计算预测状态参数X的最终概率值，得到20％，预测状态参数Y的最终概率值，得到30％，预测状态参数Z的最终概率值，得到90％，那么，可以将障碍物向左转的预测状态参数Z，作为障碍物T2时刻的状态参数。For example, the state parameter of the obstacle at time T1 is A, and the obstacle may turn right, go straight or turn left at time T2. According to the current speed information of the obstacle, the predicted state parameters X, X, For the predicted state parameter Y of going straight and the predicted state parameter Z of turning left, calculate the initial probability value of the predicted state parameter X respectively, and obtain 30%, the initial probability value of the predicted state parameter Y, and obtain 40%, the initial probability value of the predicted state parameter Z Probability value, get 70%. Then, the probability group of the obstacle at 3 moments before T1 is called, and the final probability value of the predicted state parameter X is calculated respectively to obtain 20%, the final probability value of the predicted state parameter Y is obtained, and 30% is obtained, and the predicted state parameter Z The final probability value of is 90%, then the predicted state parameter Z of the obstacle turning left can be used as the state parameter of the obstacle at T2 time.
也就是说，为了及时、准确的预测障碍物下一刻的行为，本方案中，每隔一定时间段获取一次障碍物的状态参数，并根据预先训练的模型，计算障碍物下一刻的状态参数，从而预测障碍物下一刻的行为，不仅操作简单，计算量小，而且所预测的状态参数准确度也较高。That is to say, in order to timely and accurately predict the behavior of the obstacle at the next moment, in this scheme, the state parameters of the obstacle are obtained every certain period of time, and the state parameters of the obstacle at the next moment are calculated according to the pre-trained model. Therefore, predicting the behavior of the obstacle at the next moment is not only easy to operate, but also requires a small amount of calculation, and the accuracy of the predicted state parameters is also high.
步骤S103，根据T2时刻的状态参数控制本车的行为。Step S103, controlling the behavior of the own vehicle according to the state parameters at T2.
基于上述步骤的描述，本方案在得到障碍物T2时刻的状态参数之后，可以得到障碍物T2时刻在道路模型上的轨迹线，进而，可以通过检测该轨迹线的曲率与道路的曲率，预测障碍物即将发生的行为，进而控制本车的行为。Based on the description of the above steps, after obtaining the state parameters of the obstacle at T2, the program can obtain the trajectory of the obstacle on the road model at T2, and then, can predict the obstacle by detecting the curvature of the trajectory and the curvature of the road The upcoming behavior of the object, and then control the behavior of the vehicle.
例如，请参见图3至图6，图3至图6分别是不同实施场景下的道路模型图。如图3所示，图3中的障碍物RV1，在最近一段时间内的轨迹线曲率与道路曲率一致，且未开启转向灯，因此，认为障碍物RV1将会一直在中间的车道行驶。如图4所示，虽然障碍物RV1的轨迹线曲率与道路曲率一致，但是障碍物RV1开启了右侧的转向灯，因此，可以认为障碍物RV1将会从中间的车道驶向右侧的车道。再看图5，图5中障碍物RV1的轨迹线曲率与道路曲率明显不一致，虽然障碍物RV1未开启转向灯，但是障碍物RV1的朝向是右侧车道，因此，可以认为障碍物RV1即将从中间的车道驶向右侧的车道。此外，还请参见图6，其中，本实施例中，障碍物RV1的轨迹线曲率与道路曲率相差不大，但是障碍物RV1的部分车身已经位于右侧车道，此种场景下，可以认为是障碍物RV1在变道的过程中，因此，可以认为障碍物RV1即将从中间的车道驶向右侧的车道。For example, please refer to Fig. 3 to Fig. 6, Fig. 3 to Fig. 6 are respectively road model diagrams under different implementation scenarios. As shown in Figure 3, the curvature of the trajectory of obstacle RV1 in Figure 3 is consistent with the curvature of the road in the recent period, and the turn signal is not turned on. Therefore, it is considered that obstacle RV1 will always be driving in the middle lane. As shown in Figure 4, although the curvature of the trajectory of obstacle RV1 is consistent with the curvature of the road, obstacle RV1 turns on the turn signal on the right, so it can be considered that obstacle RV1 will drive from the middle lane to the right lane . Looking at Figure 5 again, the curvature of the trajectory of obstacle RV1 in Figure 5 is obviously inconsistent with the curvature of the road. Although obstacle RV1 does not turn on the turn signal, the direction of obstacle RV1 is the right lane. Therefore, it can be considered that obstacle RV1 is about to move from The middle lane turns to the right lane. In addition, please also refer to Fig. 6, wherein, in this embodiment, the trajectory curvature of the obstacle RV1 is not much different from the road curvature, but part of the vehicle body of the obstacle RV1 is already located in the right lane. In this scenario, it can be considered as The obstacle RV1 is in the process of changing lanes, therefore, it can be considered that the obstacle RV1 is about to move from the middle lane to the right lane.
在上述描述的基础上，由于已经获知障碍物即将发生的行为，则可以根据需求控制HV的行为。具体的，可以按照如下规则执行：On the basis of the above description, since the impending behavior of the obstacle has been known, the behavior of the HV can be controlled according to the requirement. Specifically, it can be executed according to the following rules:
当障碍物均在本车道正常行驶，HV可以根据需要保持在所在的车道行驶，或者变道，如果变道，则开启相应的转向灯；当障碍物开启转向灯，HV保持在所在的车道行驶；当障碍物即将变道，HV可以根据判断是否能够在本车道上通过。例如，参见图3，障碍物RV1在本车道正常行驶，那么，HV可以在右侧车道行驶，或者根据需要变道到左侧车道，并且当从右侧车道变道到左侧车道时，开启左侧的转向灯。When obstacles are driving normally in this lane, HV can keep driving in the lane where it is located, or change lanes, if it changes lanes, turn on the corresponding turn signal; when the obstacle turns on the turn signal, HV can keep driving in the lane where it is ; When the obstacle is about to change lanes, the HV can judge whether it can pass in this lane. For example, referring to Figure 3, if the obstacle RV1 is driving normally in this lane, then the HV can drive in the right lane, or change lanes to the left lane as needed, and when changing lanes from the right lane to the left lane, turn on Turn signal on the left.
此外，在上述基础上，在HV变道，或者超车之前，还可以获取障碍物的型号，然后，根据预先存储的车辆型号与车身宽度的对应关系，查找障碍物的宽度，进而，根据道路模型所展示的相应车道的宽度，计算HV是否能够通过。In addition, on the basis of the above, before the HV changes lanes or overtakes, the model of the obstacle can also be obtained, and then, according to the pre-stored correspondence between the vehicle model and the body width, the width of the obstacle can be found, and then, according to the road model Display the width of the corresponding lane, calculate whether the HV can pass.
由此可见，本方案的车辆控制方法，通过障碍物在T1时刻及其之前N个时刻的历史状态参数，计算出其在T1时刻之后的状态参数，不仅计算量小，而且执行过程更为简单，此外，本方案在实施过程中，本车无需与障碍物进行通信，因此，也无需安装DSRC模块，所以，与现有技术相比，本方案更加节省成本，适用性更好。It can be seen that the vehicle control method of this scheme calculates the state parameters of the obstacle after T1 through the historical state parameters of the obstacle at T1 and N moments before it, not only the calculation amount is small, but also the execution process is simpler , In addition, during the implementation of this solution, the vehicle does not need to communicate with obstacles, so there is no need to install a DSRC module. Therefore, compared with the existing technology, this solution is more cost-effective and has better applicability.
为了使本领域技术人员更加清楚、详细的了解本方案，下面结合图7对本方案的执行过程进行详述。In order to make those skilled in the art understand this solution more clearly and in detail, the execution process of this solution will be described in detail below with reference to FIG. 7 .
需要说明的是，由于行人和自行车所行驶的车道，与HV所行驶的车道之间，设置有道路围栏或者绿化带等阻隔，因此，行人与自行车的行为基本上无法影响到HV，所以，本实施例中，以HV前方的机动车作为HV的障碍物进行描述。在实施过程中，可以通过各个障碍物的速度信息和位置信息筛选出机动车，具体的，本发明实施例不再详述。It should be noted that since the lanes on which pedestrians and bicycles drive are separated from the lanes on which HVs drive, there are road fences or green belts, so the behavior of pedestrians and bicycles basically cannot affect HVs. Therefore, this In the embodiment, the vehicle in front of the HV is described as an obstacle of the HV. During the implementation process, motor vehicles can be screened out through the speed information and position information of each obstacle. Specifically, the embodiments of the present invention will not be described in detail.
其中，本实施例中，HV精确定位，获取自身周围的环境参数，以及创建道路模型的过程详见上述实施例的描述，本方案此处不再赘述。参见图7，图7为本发明实施例提供的车辆控制方法的示例图，在本实施例中，HV前方有两辆机动车，分别为障碍物RV1和障碍物RV2。其中，由于针对障碍物RV1和障碍物RV2，本方案的实施过程相同，因此，本实施例以RV1为例对本方案进行描述，针对障碍物RV2的实施过程可以参考下述描述。Wherein, in this embodiment, the process of accurately locating the HV, obtaining the environment parameters around itself, and creating the road model is detailed in the description of the above embodiment, and will not be repeated here. Referring to FIG. 7 , FIG. 7 is an example diagram of a vehicle control method provided by an embodiment of the present invention. In this embodiment, there are two motor vehicles in front of the HV, which are obstacles RV1 and RV2 respectively. Wherein, since the implementation process of this solution is the same for obstacle RV1 and obstacle RV2, this embodiment uses RV1 as an example to describe this solution, and the implementation process for obstacle RV2 can refer to the following description.
假设在本实施例中，每隔10ms获取一次障碍物RV1的状态参数，当前时刻是k。获取k时刻的状态参数i，并根据状态参数i确定(k+1)时刻的预测状态参数j。其中，根据图7所示可以看出，障碍物RV1可能的行为状态包括向前直行和向右转两种，因此，本实施例中，预测状态参数j包括，向前直行对应的预测状态参数j1和向右转对应的预测状态参数j2，分别将i和j1，以及i和j2代入公式：Assume that in this embodiment, the state parameters of the obstacle RV1 are acquired every 10 ms, and the current moment is k. Obtain the state parameter i at time k, and determine the predicted state parameter j at (k+1) time according to the state parameter i. Wherein, as shown in FIG. 7, it can be seen that the possible behavior states of the obstacle RV1 include two types: going straight ahead and turning right. Therefore, in this embodiment, the predicted state parameter j includes the predicted state parameter corresponding to going straight ahead. j1 and the predicted state parameter j2 corresponding to the right turn, respectively substitute i and j1, and i and j2 into the formula:
计算得到障碍物RV1的预测状态参数是j1的概率值，以及障碍物RV1的预测状态参数是j1的概率值。The predicted state parameter of the obstacle RV1 is calculated to be the probability value of j1, and the predicted state parameter of the obstacle RV1 is the probability value of j1.
其中，该公式是按照跟踪算法预先训练得到的，而本方案中，跟踪对象即为障碍物RV1。该公式中Kj为卡尔曼滤波增益。在目标跟踪系统中，p是马尔科夫转移概率矩阵的初始值且是已知的，ε是各模型概率的初始值。该公式所表达的意思是，假定k时刻目标观测的特征概率密度为Z(k)，在给定前向观测序列的情况下，系统在k时刻状态为i，在(k+1)时刻状态为j的概率。Wherein, the formula is pre-trained according to the tracking algorithm, and in this solution, the tracking object is the obstacle RV1. In this formula, Kj is the Kalman filter gain. In the target tracking system, p is the initial value of the Markov transition probability matrix and is known, and ε is the initial value of each model probability. The meaning expressed by this formula is that, assuming that the characteristic probability density of the target observation at time k is Z(k), given the forward observation sequence, the state of the system at time k is i, and the state at time (k+1) is i is the probability of j.
需要指出的是，本方案中，障碍物RV1每个时刻对应的两个概率值均被记录，并与其对应的时刻形成状态矩阵，当按照上述公式计算得到障碍物RV1在(k+1)时刻的两个概率值之后，从预先维护的状态矩阵中，抽取(k-N)到k时刻中每个时刻对应的两个预测状态参数概率值，并分别将向前直行时对应的预测状态参数的所有概率值，代入下述公式，得到(k+1)时刻向前直行对应的预测状态参数的最终概率，将向右转时对应的预测状态参数的所有概率值，代入下述公式，得到(k+1)时刻向右转对应的预测状态参数的最终概率。It should be pointed out that in this scheme, the two probability values corresponding to each moment of obstacle RV1 are recorded, and form a state matrix with the corresponding moment. When the obstacle RV1 is calculated according to the above formula at (k+1) After the two probability values of , from the pre-maintained state matrix, extract (k-N) to the two predicted state parameter probability values corresponding to each moment in k time, and respectively put all the corresponding predicted state parameters when going straight forward The probability value is substituted into the following formula to obtain the final probability of the predicted state parameter corresponding to the time (k+1) when going straight forward, and all the probability values of the corresponding predicted state parameter when turning right are substituted into the following formula to obtain (k +1) The final probability of the predicted state parameter corresponding to turning right at the moment.
其中，由于(k+1)时刻是即将到来的时刻，而上述最终概率最大的预测状态参数，即为发生几率最大的行为对应的状态参数，因此，将最终概率最大的预测状态参数作为所预测的(k+1)的状态参数。在本实施例中，障碍物RV1在(k+1)时刻的行为被预测为向右转，向右转的行为对应预测状态参数即为障碍物RV1在(k+1)时刻的状态参数。Among them, since (k+1) time is the upcoming time, and the above-mentioned predicted state parameter with the highest final probability is the state parameter corresponding to the behavior with the highest probability of occurrence, therefore, the predicted state parameter with the highest final probability is used as the predicted The state parameter of (k+1). In this embodiment, the behavior of obstacle RV1 at time (k+1) is predicted to turn right, and the predicted state parameter corresponding to the behavior of turning right is the state parameter of obstacle RV1 at time (k+1).
其中，在本实施例中，对应障碍物RV2的执行过程，与上述过程相同，本实施例不再赘述。此外，本实施例中，N的取值是4，且障碍物RV1在前4个时刻对应的位置如图7所示。Wherein, in this embodiment, the execution process corresponding to the obstacle RV2 is the same as the above process, and will not be repeated in this embodiment. In addition, in this embodiment, the value of N is 4, and the corresponding positions of the obstacle RV1 at the first 4 moments are shown in FIG. 7 .
其中，图7中第五个时刻对应的状态，是预测得到的状态，在计算得到预测状态之后，可以将第一个状态到第五个状态在道路模型上连线形成轨迹线，障碍物RV1和障碍物RV2的轨迹线如图7所示。很明显的，障碍物RV1的轨迹线曲率与道路曲率不一致，障碍物RV1朝向中间的车道，而障碍物RV2的轨迹线曲率虽然与道路曲率一致，但是，障碍物RV2开启了向左的转向灯，因此，障碍物RV1即将向中间或者右侧的车道行驶，而障碍物RV2即将向中间或者左侧的车道行驶，因此，HV可以保持在中间的车道行驶。Among them, the state corresponding to the fifth moment in Figure 7 is the predicted state. After the predicted state is calculated, the first state to the fifth state can be connected on the road model to form a trajectory line. The obstacle RV1 and the trajectory of obstacle RV2 are shown in Figure 7. Obviously, the curvature of the trajectory of obstacle RV1 is inconsistent with the curvature of the road. Obstacle RV1 faces the middle lane, while the curvature of the trajectory of obstacle RV2 is consistent with the curvature of the road. However, obstacle RV2 turns on the left turn signal Therefore, the obstacle RV1 is about to travel to the middle or right lane, and the obstacle RV2 is about to travel to the middle or left lane, so the HV can keep driving in the middle lane.
由此可见，本方案以障碍物的转向灯，以及其历史行为参数为依据，预测障碍物将来的行为状态，从而能够相对准确的判断障碍物的行为轨迹，不仅不需要安装设置DSRC，而且处理过程简单，能够更加有效的避免道路交通事故的发生，适用性也相对较强，易于推广。It can be seen that this scheme predicts the future behavior state of the obstacle based on the turn signal of the obstacle and its historical behavior parameters, so that the behavior track of the obstacle can be judged relatively accurately, not only does not need to install DSRC, but also handles The process is simple, can more effectively avoid the occurrence of road traffic accidents, has relatively strong applicability, and is easy to promote.
与上述实现方法相对应的，本发明实施例还提供了一种车辆控制装置，参见图8，图8为本发明实施例提供的车辆控制装置的结构示意图，装置用于执行图1至图7所对应的车辆控制方法。Corresponding to the above implementation method, the embodiment of the present invention also provides a vehicle control device, refer to Fig. 8, Fig. 8 is a schematic structural diagram of the vehicle control device provided by the embodiment of the present invention, and the device is used to execute Fig. 1 to Fig. 7 The corresponding vehicle control method.
本实施例的装置包括：获取模块11，计算模块12和控制模块13，其中，获取模块11，用于获取障碍物T1时刻的状态参数，其中，状态参数包括障碍物的朝向信息，和障碍物相对于本车的位置信息；计算模块12，用于根据T1时刻的状态参数以及T1时刻之前N个时刻的状态参数，计算障碍物T2时刻的状态参数；其中，T2时刻是T1时刻之后的时刻；N是大于1的正整数；控制模块13，用于根据T2时刻的状态参数控制本车的行为。The device in this embodiment includes: an acquisition module 11, a calculation module 12 and a control module 13, wherein the acquisition module 11 is used to acquire the state parameters of the obstacle T1 moment, wherein the state parameters include the orientation information of the obstacle, and the obstacle Relative to the position information of the vehicle; the calculation module 12 is used to calculate the state parameter of the obstacle at the time T2 according to the state parameter at the time T1 and the state parameters at N moments before the time T1; wherein, the time T2 is the time after the time T1 ; N is a positive integer greater than 1; the control module 13 is used to control the behavior of the vehicle according to the state parameters at T2.
在上述实施例的基础上，在另一个实施例中，计算模块包括转换单元和控制单元，其中，转换单元，用于将T1时刻的状态参数和N个时刻的状态参数转换为障碍物的轨迹线；计算单元，用于根据轨迹线计算障碍物T2时刻的状态参数。On the basis of the above embodiments, in another embodiment, the calculation module includes a conversion unit and a control unit, wherein the conversion unit is used to convert the state parameters at T1 time and the state parameters at N times into the trajectory of the obstacle line; a calculation unit, used to calculate the state parameter of the obstacle at T2 according to the trajectory line.
在上述实施例的基础上，在一个具体实施例中，计算模块12包括计算单元、提取单元和确定单元，其中，On the basis of the above-mentioned embodiments, in a specific embodiment, the calculation module 12 includes a calculation unit, an extraction unit and a determination unit, wherein,
计算单元，用于根据T1时刻的状态参数计算得到第一概率组，其中，第一概率组包括障碍物T2时刻对应的至少两个预测状态参数的初始概率值；A calculation unit, configured to calculate a first probability group according to state parameters at time T1, wherein the first probability group includes initial probability values of at least two predicted state parameters corresponding to obstacles at time T2;
提取单元，用于提取N个时刻对应的N个概率组，其中，N个概率组是障碍物分别在N个时刻对应的至少两个预测状态参数的最终概率值；An extraction unit, configured to extract N probability groups corresponding to N times, wherein the N probability groups are final probability values of at least two predicted state parameters corresponding to obstacles at N times;
计算单元，还用于根据第一概率组和N个概率组计算得到第二概率组，其中，第二概率组包括障碍物T2时刻对应的至少两个预测状态参数的最终概率值；The calculation unit is further configured to calculate a second probability group according to the first probability group and N probability groups, wherein the second probability group includes final probability values of at least two predicted state parameters corresponding to the obstacle T2 moment;
确定单元，用于确定第二概率组中最大的最终概率值对应的预测状态参数为T2时刻的状态参数。A determining unit, configured to determine that the predicted state parameter corresponding to the largest final probability value in the second probability group is the state parameter at T2.
此外，装置还包括：定位模块、采集模块、检测模块和调整模块，其中，In addition, the device also includes: a positioning module, an acquisition module, a detection module and an adjustment module, wherein,
定位模块，用于在预先接收的地图上定位HV的初始位置；A positioning module, configured to locate the initial position of the HV on the map received in advance;
采集模块，用于采集初始位置周围的环境特征；A collection module, configured to collect environmental features around the initial position;
检测模块，用于检测环境特征与地图相应位置的信息匹配度，得到匹配度最高的区域；The detection module is used to detect the information matching degree between the environmental feature and the corresponding position on the map, and obtain the area with the highest matching degree;
调整模块，用于根据匹配度最高的区域调整初始位置，得到HV的精确位置。The adjustment module is used to adjust the initial position according to the area with the highest matching degree to obtain the precise position of the HV.
基于上述描述，相应的，本发明实施例还提供了一种车辆控制设备，参见图9，图9为本发明实施例提供的车辆控制设备的结构示意图。其中，本实施例的车辆控制设备应用于本车，包括：一个或多个处理器910以及存储器920，图9中以一个处理器910为例进行展示。Based on the above description, correspondingly, the embodiment of the present invention also provides a vehicle control device, refer to FIG. 9 , which is a schematic structural diagram of the vehicle control device provided by the embodiment of the present invention. Wherein, the vehicle control device of this embodiment is applied to the vehicle, and includes: one or more processors 910 and a memory 920, and one processor 910 is taken as an example in FIG. 9 for illustration.
此外，执行车辆控制方法的设备还可以包括：输入装置930和输出装置940。处理器910、存储器920、输入装置930和输出装置940可以通过总线或者其他方式连接，如图9所示。In addition, the device for executing the vehicle control method may further include: an input device 930 and an output device 940 . The processor 910, the memory 920, the input device 930 and the output device 940 may be connected through a bus or in other ways, as shown in FIG. 9 .
其中，存储器920作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本发明实施例中的车辆控制方法对应的程序指令/模块。处理器910通过运行存储在存储器920中的非易失性软件程序、指令以及模块，从而执行上述各种功能以及参数的处理，即实现上述方法实施例的内容。输入装置930可接收外部输入的数字或字符信息，例如，本发明实施例中，接收外部输入的地图，以及接收传感器等外部设备输入的障碍物的各项状态参数，而输出装置940可用于输出控制指令等。Among them, the memory 920, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the vehicle control method in the embodiment of the present invention. Program instructions/modules. The processor 910 executes the above-mentioned various functions and parameter processing by running the non-volatile software programs, instructions, and modules stored in the memory 920 , that is, implements the content of the above-mentioned method embodiments. The input device 930 can receive externally input digital or character information, for example, in the embodiment of the present invention, it receives an externally input map, and receives various state parameters of obstacles input by external devices such as sensors, while the output device 940 can be used to output control commands, etc.
上述设备可执行本发明实施例所提供的方法，并包含执行方法的功能模块。其中，详情请参见上述实施例的描述，本发明实施例此处不再详述。The above-mentioned device can execute the method provided by the embodiment of the present invention, and includes a functional module for executing the method. For details, refer to the description of the foregoing embodiments, and the embodiments of the present invention will not be described in detail here.
此外，本领域技术人员应明白，本发明的实施例可提供为方法、装置(设备)、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。In addition, those skilled in the art should understand that the embodiments of the present invention may be provided as methods, devices (devices), 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.
本发明是参照根据本发明实施例的方法、装置(设备)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 with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments of the 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.
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。While preferred embodiments of the invention have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, it is intended that the appended claims be construed to cover the preferred embodiment as well as all changes and modifications which fall within the scope of the invention.
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710211584.0ACN108657176A (en) | 2017-04-01 | 2017-04-01 | Control method for vehicle, device and related computer program product |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710211584.0ACN108657176A (en) | 2017-04-01 | 2017-04-01 | Control method for vehicle, device and related computer program product |
| Publication Number | Publication Date |
|---|---|
| CN108657176Atrue CN108657176A (en) | 2018-10-16 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710211584.0APendingCN108657176A (en) | 2017-04-01 | 2017-04-01 | Control method for vehicle, device and related computer program product |
| Country | Link |
|---|---|
| CN (1) | CN108657176A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109849903A (en)* | 2019-01-15 | 2019-06-07 | 北京百度网讯科技有限公司 | Car body surrounding objects Activity recognition method, apparatus, equipment and readable storage medium storing program for executing |
| CN111123933A (en)* | 2019-12-24 | 2020-05-08 | 华为技术有限公司 | Vehicle track planning method and device, intelligent driving area controller and intelligent vehicle |
| CN111524391A (en)* | 2020-04-29 | 2020-08-11 | 安徽江淮汽车集团股份有限公司 | Vehicle steering assist method, apparatus, storage medium, and device |
| CN112078592A (en)* | 2019-06-13 | 2020-12-15 | 初速度（苏州）科技有限公司 | Method and device for predicting vehicle behavior and/or vehicle track |
| CN112541437A (en)* | 2020-12-15 | 2021-03-23 | 北京百度网讯科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
| CN112824832A (en)* | 2019-11-20 | 2021-05-21 | 炬星科技（深圳）有限公司 | Method, system, device and computer readable storage medium for predicting movement locus of obstacle |
| WO2021121105A1 (en)* | 2019-12-19 | 2021-06-24 | 华为技术有限公司 | Height determination method and device |
| CN114537442A (en)* | 2022-03-21 | 2022-05-27 | 中维建通信技术服务有限公司 | Mobile intelligent vehicle management method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101536058A (en)* | 2006-11-10 | 2009-09-16 | 丰田自动车株式会社 | Obstacle course predicting method, device and program |
| CN103318181A (en)* | 2013-06-19 | 2013-09-25 | 电子科技大学 | Driver intention recognition method |
| CN103794086A (en)* | 2014-01-26 | 2014-05-14 | 浙江吉利控股集团有限公司 | Vehicle driving early warning method |
| CN104882025A (en)* | 2015-05-13 | 2015-09-02 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
| CN105528593A (en)* | 2016-01-22 | 2016-04-27 | 江苏大学 | Forward vehicle driver driving behavior prediction system and prediction method |
| CN105711586A (en)* | 2016-01-22 | 2016-06-29 | 江苏大学 | Front collision avoiding system based on driving behavior of front vehicle driver and vehicle collision avoiding algorithm |
| CN105956704A (en)* | 2016-05-04 | 2016-09-21 | 大连理工大学 | A Destination Recognition Method for Plug-in Hybrid Electric Vehicles |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101536058A (en)* | 2006-11-10 | 2009-09-16 | 丰田自动车株式会社 | Obstacle course predicting method, device and program |
| CN103318181A (en)* | 2013-06-19 | 2013-09-25 | 电子科技大学 | Driver intention recognition method |
| CN103794086A (en)* | 2014-01-26 | 2014-05-14 | 浙江吉利控股集团有限公司 | Vehicle driving early warning method |
| CN104882025A (en)* | 2015-05-13 | 2015-09-02 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
| CN105528593A (en)* | 2016-01-22 | 2016-04-27 | 江苏大学 | Forward vehicle driver driving behavior prediction system and prediction method |
| CN105711586A (en)* | 2016-01-22 | 2016-06-29 | 江苏大学 | Front collision avoiding system based on driving behavior of front vehicle driver and vehicle collision avoiding algorithm |
| CN105956704A (en)* | 2016-05-04 | 2016-09-21 | 大连理工大学 | A Destination Recognition Method for Plug-in Hybrid Electric Vehicles |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109849903B (en)* | 2019-01-15 | 2020-10-16 | 北京百度网讯科技有限公司 | Method, device, device and readable storage medium for behavior recognition of objects around vehicle body |
| CN109849903A (en)* | 2019-01-15 | 2019-06-07 | 北京百度网讯科技有限公司 | Car body surrounding objects Activity recognition method, apparatus, equipment and readable storage medium storing program for executing |
| CN112078592B (en)* | 2019-06-13 | 2021-12-24 | 魔门塔(苏州)科技有限公司 | Method and device for predicting vehicle behavior and/or vehicle track |
| CN112078592A (en)* | 2019-06-13 | 2020-12-15 | 初速度（苏州）科技有限公司 | Method and device for predicting vehicle behavior and/or vehicle track |
| CN112824832A (en)* | 2019-11-20 | 2021-05-21 | 炬星科技（深圳）有限公司 | Method, system, device and computer readable storage medium for predicting movement locus of obstacle |
| WO2021121105A1 (en)* | 2019-12-19 | 2021-06-24 | 华为技术有限公司 | Height determination method and device |
| US12315184B2 (en) | 2019-12-19 | 2025-05-27 | Shenzhen Yinwang Intelligent Technologies Co., Ltd. | Height determining method and apparatus |
| CN111123933B (en)* | 2019-12-24 | 2021-10-01 | 华为技术有限公司 | Method, device, intelligent driving domain controller and intelligent vehicle for vehicle trajectory planning |
| CN111123933A (en)* | 2019-12-24 | 2020-05-08 | 华为技术有限公司 | Vehicle track planning method and device, intelligent driving area controller and intelligent vehicle |
| US12371070B2 (en) | 2019-12-24 | 2025-07-29 | Shenzhen Yinwang Intelligent Technologies Co., Ltd. | Method and apparatus for planning vehicle trajectory, intelligent driving domain controller, and intelligent vehicle |
| CN111524391A (en)* | 2020-04-29 | 2020-08-11 | 安徽江淮汽车集团股份有限公司 | Vehicle steering assist method, apparatus, storage medium, and device |
| CN112541437A (en)* | 2020-12-15 | 2021-03-23 | 北京百度网讯科技有限公司 | Vehicle positioning method and device, electronic equipment and storage medium |
| CN114537442A (en)* | 2022-03-21 | 2022-05-27 | 中维建通信技术服务有限公司 | Mobile intelligent vehicle management method and system |
| CN114537442B (en)* | 2022-03-21 | 2022-09-23 | 中维建通信技术服务有限公司 | Mobile intelligent vehicle management method and system |
| Publication | Publication Date | Title |
|---|---|---|
| US10618519B2 (en) | Systems and methods for autonomous vehicle lane change control | |
| CN108657176A (en) | Control method for vehicle, device and related computer program product | |
| CN111583715B (en) | A vehicle trajectory prediction method, vehicle collision warning method, device and storage medium | |
| US11527078B2 (en) | Using captured video data to identify pose of a vehicle | |
| US12429340B2 (en) | Systems and methods for deriving path-prior data using collected trajectories | |
| CN108688660B (en) | Operating range determination device | |
| US9495602B2 (en) | Image and map-based detection of vehicles at intersections | |
| KR20210038852A (en) | Method, apparatus, electronic device, computer readable storage medium and computer program for early-warning | |
| CN109426256A (en) | The lane auxiliary system based on driver intention of automatic driving vehicle | |
| US10369993B2 (en) | Method and device for monitoring a setpoint trajectory to be traveled by a vehicle for being collision free | |
| CN111369831A (en) | Road driving danger early warning method, device and equipment | |
| JP2021165080A (en) | Vehicle control device, vehicle control method and computer program for vehicle control | |
| CN110487288A (en) | A kind of estimation method and carriage way estimating system of carriage way | |
| JP2019039831A (en) | Automatic driving device | |
| CN114973644B (en) | Road information generating device | |
| US10160459B2 (en) | Vehicle lane direction detection | |
| CN112703140A (en) | Control method and control device | |
| EP4145420A1 (en) | Hierarchical processing of traffic signal face states | |
| CN116135654A (en) | Vehicle running speed generation method and related equipment | |
| WO2021170140A1 (en) | Lane structure detection method and apparatus | |
| CN113753038A (en) | Trajectory prediction method and apparatus, electronic device and storage medium | |
| JP6854141B2 (en) | Vehicle control unit | |
| US20240101106A1 (en) | Systems and methods for scene understanding | |
| CN115797409A (en) | 3D target object positioning method and device and electronic equipment | |
| CN113386754A (en) | Method, device and system for controlling automatic driving safety distance of vehicle and storage medium |
| 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:20181016 | |
| WD01 | Invention patent application deemed withdrawn after publication |