WO2023142794A1

WO2023142794A1 - Vehicle control method and apparatus, and device and storage medium

Info

Publication number: WO2023142794A1
Application number: PCT/CN2022/140591
Authority: WO
Inventors: 刘洋; 陈博; 尚秉旭; 陈志新; 王洪峰; 张勇; 何柳; 金百鑫; 张中举
Original assignee: 中国第一汽车股份有限公司
Priority date: 2022-01-30
Filing date: 2022-12-21
Publication date: 2023-08-03
Also published as: CN114348026A; CN114348026B

Abstract

A vehicle control method and apparatus, and a device and a storage medium. The method comprises: determining a first control amount according to the vehicle speed of a vehicle at the current moment, an expected path, position information of the vehicle at the current moment, and vehicle attribute parameters; determining a second control amount according to the expected path, the position information of the vehicle at the current moment, the first control amount, and a vehicle dynamic model; and generating a vehicle control instruction according to the second control amount, and controlling the traveling of the vehicle at the next moment on the basis of the vehicle control instruction.

Description

一种车辆控制方法、装置、设备以及存储介质A vehicle control method, device, device and storage medium

本申请要求在2022年1月30日提交中国专利局、申请号为202210114375.5的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。This application claims priority to a Chinese patent application with application number 202210114375.5 filed with the China Patent Office on January 30, 2022, the entire contents of which are incorporated herein by reference.

技术领域technical field

本申请实施例涉及智能交通技术，例如涉及一种车辆控制方法、装置、设备以及存储介质。Embodiments of the present application relate to intelligent transportation technologies, for example, to a vehicle control method, device, equipment, and storage medium.

背景技术Background technique

随着人工智能技术的快速发展，自动驾驶的相关研究也取得了长足进步。已有多种经典的控制算法被提出用于控制车辆按照规划路径行驶，但相关技术中的控制算法都具有一定的局限性，在工程应用上控制的稳定性以及准确性不高。With the rapid development of artificial intelligence technology, research on autonomous driving has also made great progress. A variety of classic control algorithms have been proposed to control the vehicle to travel along the planned route, but the control algorithms in the related art have certain limitations, and the stability and accuracy of the control in engineering applications are not high.

因此，如何使得车辆控制***更精准稳定地控制车辆行驶，提高车辆在各个应用场景下的自适应性，是目前亟待解决的问题。Therefore, how to make the vehicle control system more accurately and stably control the driving of the vehicle and improve the adaptability of the vehicle in various application scenarios is an urgent problem to be solved.

发明内容Contents of the invention

本申请提供一种车辆控制方法、装置、设备以及存储介质，能够生成更加稳定准确的车辆控制指令，控制车辆更精准地行驶，从而提高了车辆在各个应用场景下的自适应性。The present application provides a vehicle control method, device, device, and storage medium, capable of generating more stable and accurate vehicle control commands, and controlling the vehicle to drive more precisely, thereby improving the adaptability of the vehicle in various application scenarios.

第一方面，本申请实施例提供了一种车辆控制方法，该方法包括：In a first aspect, an embodiment of the present application provides a vehicle control method, the method comprising:

根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；Determining the first control amount according to the vehicle speed at the current moment of the vehicle, the expected path, the position information of the vehicle at the current moment, and the attribute parameters of the vehicle;

根据所述期望路径、所述车辆当前时刻的位置信息、所述第一控制量以及车辆动力学模型，确定第二控制量；determining a second control amount according to the desired path, the current location information of the vehicle, the first control amount, and a vehicle dynamics model;

根据所述第二控制量，生成车辆控制指令，并基于所述车辆控制指令，控制车辆下一时刻的行驶。According to the second control amount, a vehicle control instruction is generated, and based on the vehicle control instruction, the driving of the vehicle at the next moment is controlled.

第二方面，本申请实施例还提供了一种车辆控制装置，该装置包括：In the second aspect, the embodiment of the present application also provides a vehicle control device, which includes:

第一确定模块，设置为根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；The first determining module is configured to determine the first control amount according to the vehicle speed at the current moment of the vehicle, the desired route, the position information of the vehicle at the current moment, and the attribute parameters of the vehicle;

第二确定模块，设置为根据所述期望路径、所述车辆当前时刻的位置信息、所述第一控制量以及车辆动力学模型，确定第二控制量；The second determination module is configured to determine a second control amount according to the expected path, the current location information of the vehicle, the first control amount and a vehicle dynamics model;

控制模块，设置为根据所述第二控制量，生成车辆控制指令，并基于所述车辆控制指令，控制车辆下一时刻的行驶。The control module is configured to generate a vehicle control instruction according to the second control amount, and control the driving of the vehicle at a next moment based on the vehicle control instruction.

第三方面，本申请实施例还提供了一种电子设备，该电子设备包括：In a third aspect, the embodiment of the present application also provides an electronic device, the electronic device includes:

至少一个处理器；at least one processor;

存储器，设置为存储至少一个程序；a memory configured to store at least one program;

当至少一个程序被所述至少一个处理器执行，使得至少一个处理器实现如本申请任意实施例所提供的车辆控制方法。When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle control method provided in any embodiment of the present application.

第四方面，本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时用于执行本申请任意实施例所提供的车辆控制方法。In a fourth aspect, the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the program is used to execute the vehicle control method provided in any embodiment of the present application when executed by a processor.

附图说明Description of drawings

图1为本申请实施例一提供的一种车辆控制方法的流程图；FIG. 1 is a flow chart of a vehicle control method provided in Embodiment 1 of the present application;

图2A为本申请实施例二提供的一种车辆控制方法的流程图；FIG. 2A is a flow chart of a vehicle control method provided in Embodiment 2 of the present application;

图2B为本申请实施例二提供的侧向偏差与约束条件上限的关系坐标图；FIG. 2B is a coordinate diagram of the relationship between the lateral deviation and the upper limit of constraint conditions provided by Embodiment 2 of the present application;

图3A为本申请实施例三提供的一种车辆控制方法的流程图；FIG. 3A is a flow chart of a vehicle control method provided in Embodiment 3 of the present application;

图3B为本申请实施例三提供的确定车辆转弯半径的过程示意图；FIG. 3B is a schematic diagram of the process of determining the turning radius of a vehicle provided in Embodiment 3 of the present application;

图4为本申请实施例四提供的一种车辆控制装置的结构框图；FIG. 4 is a structural block diagram of a vehicle control device provided in Embodiment 4 of the present application;

图5为本申请实施例五提供的一种电子设备的结构示意图。FIG. 5 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application.

具体实施方式Detailed ways

实施例一Embodiment one

图1为本申请实施例一提供的一种车辆控制方法的流程图，本实施例可适用于控制车辆自动行驶的情况，该方法可以由车辆控制装置来执行，该装置可以采用软件和/或硬件方式实现，并可集成于车辆中具有车辆控制功能的电子设备中，例如，车辆的车载终端中，如图1所示，本实施例提供的车辆控制方法包括：Figure 1 is a flow chart of a vehicle control method provided in Embodiment 1 of the present application. This embodiment is applicable to the situation of controlling the automatic driving of the vehicle. The method can be executed by the vehicle control device, which can use software and/or Implemented in hardware, and can be integrated in electronic equipment with vehicle control functions in the vehicle, for example, in the vehicle-mounted terminal of the vehicle, as shown in Figure 1, the vehicle control method provided in this embodiment includes:

S101、根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量。S101. Determine a first control amount according to the vehicle speed at the current moment, the desired route, the location information of the vehicle at the current moment, and the attribute parameters of the vehicle.

其中，车辆当前时刻的车速是指车辆在当前时刻的行驶速度。期望路径是指根据出发地和目的地预先为车辆规划好的期望行驶路径，示例性地，期望路径可以包括车辆坐标系下至少一个不同预测时刻车辆的位置坐标点。车辆当前时刻的位置信息是指车辆坐标系下车辆在当前时刻的位置坐标信息。车辆属性参数是指可以表征车辆性能的相关参数信息，示例性地，车辆属性参数至少可以包括车辆前轴到车辆质心的距离a、后轴到质心的距离b、整车质量m、前轮的侧偏刚度k ₁、车辆轴距L以及后轮的侧偏刚度k ₂。第一控制量是指用于控制车辆行驶的初步预估控制参数，示例性地可以包括两个维度，在横向上表示控制车辆转弯的方向盘转角，在纵向上表示控制车辆行驶的加速度。 Wherein, the vehicle speed at the current moment of the vehicle refers to the traveling speed of the vehicle at the current moment. The expected route refers to the expected driving route planned for the vehicle in advance according to the departure place and the destination. Exemplarily, the expected route may include at least one position coordinate point of the vehicle at different prediction times in the vehicle coordinate system. The position information of the vehicle at the current moment refers to the position coordinate information of the vehicle at the current moment in the vehicle coordinate system. Vehicle attribute parameters refer to relevant parameter information that can characterize vehicle performance. Exemplarily, the vehicle attribute parameters can at least include the distance a from the front axle of the vehicle to the center of mass of the vehicle, the distance b from the rear axle to the center of mass, the mass of the vehicle m, and the distance of the front wheels. The cornering stiffness k ₁ , the wheelbase L of the vehicle, and the cornering stiffness k ₂ of the rear wheels. The first control amount refers to a preliminary estimated control parameter used to control the driving of the vehicle, and may include two dimensions for example, the horizontal direction represents the steering wheel angle for controlling the turning of the vehicle, and the vertical direction represents the acceleration for controlling the vehicle driving.

可选的，车辆当前时刻的车速可以由车辆的控制单元根据相关的车速传感器直接获取。车辆属性参数可以由车辆的控制单元从车辆的存储单元直接获取。Optionally, the vehicle speed at the current moment can be directly obtained by the vehicle control unit according to the relevant vehicle speed sensor. The vehicle attribute parameters can be directly acquired by the vehicle's control unit from the vehicle's storage unit.

可选的，期望路径可以由车辆的控制单元从车辆的存储单元直接获取，也可以由车辆的决策单元根据用户实时输入的相关指令规划出最优路径之后，将规划好的最优路径作为期望路径。Optionally, the desired path can be directly acquired by the control unit of the vehicle from the storage unit of the vehicle, or the decision-making unit of the vehicle can plan the optimal path according to the relevant instructions input by the user in real time, and then use the planned optimal path as the expected path. path.

可选的，车辆当前时刻的位置信息可以由车辆的定位***根据定位传感器采集获取。Optionally, the location information of the vehicle at the current moment may be collected and acquired by the positioning system of the vehicle according to the positioning sensor.

可选的，在获取车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数之后，可以根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，将获取的参数输入预先设置好的第一控制量确定模型，输出第一控制量；也可以按照一定的计算规则，根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数进行计算，得到第一控制量。Optionally, after obtaining the vehicle speed at the current moment, the expected path, the location information of the vehicle at the current moment and the vehicle attribute parameters, according to the vehicle speed at the current moment, the expected path, the location information of the vehicle at the current moment and the vehicle attribute parameters, the The obtained parameters are input into the pre-set first control quantity determination model, and the first control quantity is output; it can also be carried out according to the vehicle speed at the current moment, the expected path, the position information of the vehicle at the current moment and the attribute parameters of the vehicle according to certain calculation rules. Calculate to obtain the first control quantity.

S102、根据期望路径、车辆当前时刻的位置信息、第一控制量以及车辆动力学模型，确定第二控制量。S102. Determine a second control amount according to the desired route, the current location information of the vehicle, the first control amount, and the vehicle dynamics model.

其中，车辆动力学模型是指用于分析车辆的平顺性和车辆操纵的稳定性的模型，不同的车辆由于其本身构造的差异，具有不同的车辆动力学模型。第二控制量是指用于控制车辆行驶的最终控制参数，示例性地可以包括两个维度，在横向上表示控制车辆转弯的方向盘转角，在纵向上表示控制车辆行驶的加速度。Wherein, the vehicle dynamics model refers to a model used to analyze the ride comfort of the vehicle and the stability of the vehicle handling, and different vehicles have different vehicle dynamics models due to differences in their own structures. The second control amount refers to the final control parameter used to control the driving of the vehicle, and may include two dimensions for example, the horizontal direction represents the steering wheel angle for controlling the turning of the vehicle, and the longitudinal direction represents the acceleration for controlling the vehicle driving.

可选的，车辆当前时刻的位置信息可以由车辆的定位***根据定位传感器采集获取。车辆的动力学模型可以由车辆的控制单元从车辆的存储单元直接获取。Optionally, the location information of the vehicle at the current moment may be collected and acquired by the positioning system of the vehicle according to the positioning sensor. The dynamic model of the vehicle can be directly acquired by the control unit of the vehicle from the storage unit of the vehicle.

可选的，车辆动力学模型可以为单轨车辆动力学模型。示例性的，经过欧拉法离散化处理之后，车辆单轨车辆动力学模型的状态空间方程可以由以下公式表示：Optionally, the vehicle dynamics model may be a monorail vehicle dynamics model. Exemplarily, after being discretized by the Euler method, the state space equation of the vehicle monorail vehicle dynamics model can be expressed by the following formula:

其中，U(k)和X(k)为车辆动力学模型k时刻的状态量，X(k+1)为车辆动力学模型k+1时刻的状态量，Y(k)为车辆动力学模型k时刻的输出量。A _c为车辆动力学模型的第一系数矩阵，B _c为车辆动力学模型的第二系数矩阵，C为车辆动力学模型的第三系数矩阵。 Among them, U(k) and X(k) are the state quantities of the vehicle dynamics model at time k, X(k+1) is the state quantity of the vehicle dynamics model at k+1 time, and Y(k) is the vehicle dynamics model output at time k. A _c is the first coefficient matrix of the vehicle dynamics model, B _c is the second coefficient matrix of the vehicle dynamics model, and C is the third coefficient matrix of the vehicle dynamics model.

车辆动力学模型的第一系数矩阵A _c可以由以下公式表示： The first coefficient matrix _Ac of the vehicle dynamics model can be expressed by the following formula:

其中，T _s表示离散化时的采样时间，a表示车辆前轴到车辆质心的距离，b表示后轴到质心的距离，m表示车辆整车的质量，k ₁表示前轮的侧偏刚度，k ₂表示后轮的侧偏刚度，U _x表示车辆的纵向车速，I _z表示单位矩阵。 Among them, T _s represents the sampling time during discretization, a represents the distance from the front axle of the vehicle to the center of mass of the vehicle, b represents the distance from the rear axle to the center of mass of the vehicle, m represents the mass of the vehicle as a whole, k ₁ represents the cornering stiffness of the front wheels, k ₂ represents the cornering stiffness of the rear wheels, U _x represents the longitudinal speed of the vehicle, and I _z represents the identity matrix.

车辆动力学模型的第二系数矩阵B _c可以由以下公式表示： The second coefficient matrix B _c of the vehicle dynamics model can be expressed by the following formula:

其中，a表示车辆前轴到车辆质心的距离，k ₁表示前轮的侧偏刚度，T _s表示离散化时的采样时间，I _z表示单位矩阵，m表示车辆整车的质量。 Among them, a represents the distance from the front axle of the vehicle to the center of mass of the vehicle, k ₁ represents the cornering stiffness of the front wheel, T _s represents the sampling time during discretization, I _z represents the identity matrix, and m represents the mass of the vehicle.

车辆动力学模型的第三系数矩阵C可以由以下公式表示：The third coefficient matrix C of the vehicle dynamics model can be expressed by the following formula:

可选的，车辆的控制单元在获取车辆动力学模型之后，可以根据车辆动力学模型，确定车辆动力学模型的第一系数矩阵、第二系数矩阵以及第三系数矩阵，进一步结合期望路径、车辆当前时刻的位置信息以及第一控制量，可以将车辆动力学模型的第一系数矩阵、第二系数矩阵、第三系数矩阵、期望路径、车辆当前时刻的位置信息以及第一控制量输入预先设定的第二控制量确定模型，输出第二控制量，也可以按照预设的计算规则，根据以上参数，通过计算确定第二控制量。Optionally, after obtaining the vehicle dynamics model, the control unit of the vehicle may determine the first coefficient matrix, the second coefficient matrix and the third coefficient matrix of the vehicle dynamics model according to the vehicle dynamics model, and further combine the expected path, the vehicle The position information at the current moment and the first control amount can input the first coefficient matrix, the second coefficient matrix, the third coefficient matrix, the expected path, the current position information of the vehicle and the first control amount of the vehicle dynamics model into the preset The second control quantity can be determined by a predetermined model to output the second control quantity, or the second control quantity can be determined through calculation according to the above parameters according to the preset calculation rules.

S103、根据第二控制量，生成车辆控制指令，并基于车辆控制指令，控制车辆下一时刻的行驶。S103. Generate a vehicle control instruction according to the second control amount, and control the driving of the vehicle at a next moment based on the vehicle control instruction.

其中，车辆控制指令是指控制车辆行驶的指令，示例性地可以包括车辆的转向角度信息和车辆的加速度。Wherein, the vehicle control instruction refers to an instruction to control the running of the vehicle, and may include, for example, steering angle information of the vehicle and acceleration of the vehicle.

可选的，根据第二控制量，可以获取第二控制量横向维度的值作为车辆的转向角度的值，生成方向盘转角命令，获取第二控制量纵向维度的值作为车辆行驶加速度的值，生成车辆加速度命令，将方向盘转角命令和车辆加速度命令作为车辆控制指令，基于车辆控制指令，控制车辆组件根据转向角度以及加速度执行车辆转向。Optionally, according to the second control amount, the value of the horizontal dimension of the second control amount can be obtained as the value of the steering angle of the vehicle to generate a steering wheel angle command, and the value of the longitudinal dimension of the second control amount can be obtained as the value of the vehicle driving acceleration to generate The vehicle acceleration command uses the steering wheel angle command and the vehicle acceleration command as vehicle control commands, and based on the vehicle control commands, controls the vehicle components to perform vehicle steering according to the steering angle and acceleration.

本申请实施例根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；根据期望路径、车辆当前时刻的位置信息、第一控制量以及车辆动力学模型，确定第二控制量；根据第二控制量，生成车辆控制指令，并基于车辆控制指令，控制车辆下一时刻的行驶。通过这样的方式，能够生成更加稳定准确的车辆控制指令，控制车辆更精准地行驶，从而提高了车辆在各个应用场景如工程应用下的自适应性。In the embodiment of the present application, the first control amount is determined according to the vehicle speed at the current moment, the desired route, the position information of the vehicle at the current moment, and the vehicle attribute parameters; The model determines the second control quantity; generates a vehicle control instruction according to the second control quantity, and controls the driving of the vehicle at a next moment based on the vehicle control instruction. In this way, more stable and accurate vehicle control commands can be generated, and the vehicle can be controlled to drive more precisely, thereby improving the adaptability of the vehicle in various application scenarios such as engineering applications.

实施例二Embodiment two

图2A为本申请实施例二提供的一种车辆控制方法的流程图，图2B为本申请实施例二提供的侧向偏差与约束条件上限的关系坐标图，本实施例在上述实施例的基础上，对“根据期望路径、车辆当前时刻的位置信息、第一控制量以及车辆动力学模型，确定第二控制量”进行详细的解释说明，如图2A所示，本实施例提供的车辆控制方法包括：Figure 2A is a flow chart of a vehicle control method provided in Embodiment 2 of the present application, and Figure 2B is a coordinate diagram of the relationship between the lateral deviation and the upper limit of constraint conditions provided in Embodiment 2 of the present application. This embodiment is based on the above-mentioned embodiments In the above, a detailed explanation of "determining the second control amount based on the desired route, the current position information of the vehicle, the first control amount, and the vehicle dynamics model" is given in detail. As shown in Figure 2A, the vehicle control provided by this embodiment Methods include:

S201、根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量。S201. Determine a first control amount according to the vehicle speed at the current moment, the desired route, the location information of the vehicle at the current moment, and the attribute parameters of the vehicle.

S202、根据期望路径和车辆当前时刻的位置信息，确定当前时刻的侧向偏差。S202. Determine the lateral deviation at the current moment according to the desired path and the current location information of the vehicle.

其中，当前时刻的侧向偏差是指车辆当前所处的位置与期望路径中期望车辆所处位置之间的偏差。Wherein, the lateral deviation at the current moment refers to the deviation between the current position of the vehicle and the expected position of the vehicle in the expected route.

可选的，可以将期望路径和车辆当前时刻的位置信息输入预设的侧向偏差确定模型，输出侧向偏差，也可以先根据车辆当前时刻的位置信息，确定车辆坐标系下车辆的当前时刻所处的位置坐标，进一步确定出期望路径中预瞄点的位置坐标，计算出预瞄点与车辆当前时刻所处的位置坐标之间偏差的绝对值，作为当前时刻的侧向偏差。Optionally, the expected path and the current position information of the vehicle can be input into the preset lateral deviation determination model to output the lateral deviation, or the current position of the vehicle in the vehicle coordinate system can be determined first according to the current position information of the vehicle The location coordinates are used to further determine the location coordinates of the preview point in the desired path, and the absolute value of the deviation between the preview point and the current location coordinates of the vehicle is calculated as the lateral deviation at the current moment.

S203、根据侧向偏差与偏差阈值间的大小关系，确定目标函数的约束条件。S203. Determine the constraint condition of the objective function according to the magnitude relationship between the lateral deviation and the deviation threshold.

其中，偏差阈值包括：第一阈值、第二阈值和第三阈值，且第一阈值小于第二阈值，第二阈值小于第三阈值。目标函数是指用于确定最优控制量即第二控制量的函数。目标函数的约束条件是指对目标函数中的自变量的取值范围进行限制约束的条件。Wherein, the deviation threshold includes: a first threshold, a second threshold and a third threshold, and the first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold. The objective function refers to a function for determining the optimal control quantity, that is, the second control quantity. The constraint condition of the objective function refers to the condition that restricts the value range of the independent variable in the objective function.

可选的，偏差阈值的个数以及对应的取值可以预先设置好，存储在车辆的存储单元中。Optionally, the number of deviation thresholds and corresponding values may be preset and stored in the storage unit of the vehicle.

可选的，可以根据侧向偏差与偏差阈值间的大小关系，确定目标函数的约束条件的上限U _Δmax，根据U _Δmin＝-U _Δmax，确定目标函数的约束条件的下限U _Δmin，根据目标函数的约束条件的上限和下限，确定目标函数的约束条件。 Optionally, the upper limit U _Δmax of the constraint condition of the objective function can be determined according to the size relationship between the lateral deviation and the deviation threshold, and the lower limit U _Δmin of the constraint condition of the objective function can be determined according to U _Δmin =-U _Δmax , and according to the objective function The upper and lower bounds of the constraints determine the constraints of the objective function.

示例性的，若侧向偏差小于第一阈值，或侧向偏差大于或等于第三阈值，则根据预设数值确定目标函数的约束条件。Exemplarily, if the lateral deviation is smaller than the first threshold, or the lateral deviation is greater than or equal to the third threshold, the constraint condition of the objective function is determined according to a preset value.

若侧向偏差大于或等于第一阈值且小于第二阈值，则根据转向角最大变化增量、第一阈值、第二阈值和侧向偏差，确定目标函数的约束条件；If the lateral deviation is greater than or equal to the first threshold and less than the second threshold, then determine the constraints of the objective function according to the maximum change increment of the steering angle, the first threshold, the second threshold and the lateral deviation;

若侧向偏差大于或等于第二阈值且小于第三阈值，则根据转向角最大变化增量、第二阈值、第三阈值和侧向偏差，确定目标函数的约束条件。If the lateral deviation is greater than or equal to the second threshold and less than the third threshold, the constraint condition of the objective function is determined according to the maximum change increment of the steering angle, the second threshold, the third threshold and the lateral deviation.

示例性的，参见图2B，可以基于如下公式，根据侧向偏差与偏差阈值间的大小关系，确定目标函数约束条件的上限U _Δmax： Exemplarily, referring to FIG. 2B , the upper limit U _Δmax of the objective function constraint can be determined based on the following formula and according to the magnitude relationship between the lateral deviation and the deviation threshold:

其中，|e _y|表示侧向偏差，e _y0表示第一阈值，e _y1表示第二阈值，e _y2表示第三阈值。δ _Δ1表示车辆前轮的转向角最大变化增量，其可以由车辆的控制单元自行设定。示例性的，若侧向偏差满足0≤|e _y|＜e _y0，即侧向偏差小于第一阈值，则确定目标函数的约束条件的上限为0，进一步的确定约束条件的下限也为0。，此时车辆的控制单元仅进行前馈控制，不引入反馈控制，避免了反馈控制可能引起的振荡问题。 Wherein, |e _y | represents the lateral deviation, e _y0 represents the first threshold, e _y1 represents the second threshold, and e _y2 represents the third threshold. δ _Δ1 represents the maximum change increment of the steering angle of the front wheels of the vehicle, which can be set by the control unit of the vehicle itself. Exemplarily, if the lateral deviation satisfies 0≤|e _y |<e _y0 , that is, the lateral deviation is smaller than the first threshold, then the upper limit of the constraint condition for determining the objective function is 0, and the lower limit of the further determination constraint condition is also 0 . , at this time, the control unit of the vehicle only performs feedforward control without introducing feedback control, which avoids the oscillation problem that may be caused by feedback control.

若侧向偏差满足e _y0≤|e _y|＜e _y1，即侧向偏差大于或等于第一阈值且小于第二阈值，则基于转向角最大变化增量、第一阈值、第二阈值和侧向偏差，利用如下公式确定目标函数约束条件的上限： If the lateral deviation satisfies e _y0 ≤|e _y |<e _y1 , that is, the lateral deviation is greater than or equal to the first threshold and less than the second threshold, then based on the maximum change increment of the steering angle, the first threshold, the second threshold and the side direction deviation, use the following formula to determine the upper limit of the objective function constraints:

根据U _Δmin＝-U _Δmax，确定目标函数的约束条件的下限U _Δmin。此时前馈控制渐渐不能满足控制要求，因此逐渐增加反馈控制对控制进行调节，增加控制器整体的控制能力。 According to U _Δmin =−U _Δmax , the lower limit U _Δmin of the constraint condition of the objective function is determined. At this time, the feedforward control gradually cannot meet the control requirements, so the feedback control is gradually increased to adjust the control and increase the overall control capability of the controller.

若侧向偏差满足e _y1≤|e _y|＜e _y2，即侧向偏差大于或等于第二阈值且小于第三阈值，则可以根据转向角最大变化增量、第二阈值、第三阈值和侧向偏差，基于如下公式确定目标函数的约束条件的上限： If the lateral deviation satisfies e _y1 ≤|e _y |<e _y2 , that is, the lateral deviation is greater than or equal to the second threshold and less than the third threshold, then according to the maximum change increment of the steering angle, the second threshold, the third threshold and Lateral deviation, based on the following formula to determine the upper limit of the constraints of the objective function:

根据U _Δmin＝-U _Δmax，确定目标函数的约束条件的下限U _Δmin。此时反馈控制极易引起振荡现象，需要逐渐减小反馈控制的控制能力。 According to U _Δmin =−U _Δmax , the lower limit U _Δmin of the constraint condition of the objective function is determined. At this time, the feedback control is very easy to cause oscillation, and it is necessary to gradually reduce the control ability of the feedback control.

若侧向偏差满足|e _y|≥e _y2，即侧向偏差大于或等于第三阈值，则确定目标函数的约束条件的上限为0，进一步的确定约束条件的下限也为0。此时反馈控制的控制能力完全失效。 If the lateral deviation satisfies |e _y |≥e _y2 , that is, the lateral deviation is greater than or equal to the third threshold, then the upper limit of the constraint condition for determining the objective function is 0, and the lower limit of the further determination constraint condition is also 0. At this time, the control ability of the feedback control is completely invalid.

S204、根据第一控制量、期望路径、车辆动力学模型以及目标函数的约束条件，利用模型预测控制器构建目标函数。S204. Construct an objective function by using a model predictive controller according to the first control quantity, the desired path, the vehicle dynamics model, and the constraints of the objective function.

其中，模型预测控制(model predictive control，MPC)是一类特殊的控制。它的当前控制动作是在每一个采样瞬间通过求解一个有限时域开环最优控制问题而获得。Among them, model predictive control (model predictive control, MPC) is a special kind of control. Its current control action is obtained by solving a finite-time open-loop optimal control problem at each sampling instant.

可选的，可以根据第一控制量和车辆动力学模型，构建模型预测控制器的状态方程，从而获取控制量系数S _u和***状态系数S _x；根据期望路径，确定出期望的模型预测控制器输出序列

进一步结合目标函数的约束条件，利用模型预测控制器构建目标函数。 Optionally, the state equation of the model predictive controller can be constructed according to the first control quantity and the vehicle dynamics model, so as to obtain the control quantity coefficient S _u and the system state coefficient S _x ; according to the desired path, the desired model predictive control can be determined output sequence

Further combining the constraints of the objective function, the objective function is constructed using the model predictive controller.

可选的，在根据第一控制量和车辆动力学模型，构建模型预测控制器的状态方程之前，可以先获取模型预测控制器的预测长度和控制长度。Optionally, before constructing the state equation of the model predictive controller according to the first control quantity and the vehicle dynamics model, the prediction length and the control length of the model predictive controller may be obtained first.

其中，模型预测控制器的预测长度是指模型预测控制器的预测时域长度。模型预测控制器的控制长度是指模型预测控制器的控制时域长度。可选的，可以由车辆的控制单元从车辆的存储单元获取预存的模型预测控制器的预测长度和控制长度的取值。Wherein, the prediction length of the model predictive controller refers to the prediction time domain length of the model predictive controller. The control length of the model predictive controller refers to the control time domain length of the model predictive controller. Optionally, the pre-stored values of the prediction length and the control length of the model predictive controller may be obtained from the storage unit of the vehicle by the control unit of the vehicle.

可选的，在获取模型预测控制器的预测长度和控制长度之后，可以根据第一控制量、车辆动力学模型的第一系数矩阵、第二系数矩阵、第三系数矩阵、模型预测控制器的预测长度以及控制长度，构建模型预测控制器的状态方程。示例性的，可以构建如下模型预测控制器的状态方程：Optionally, after obtaining the prediction length and control length of the model predictive controller, the first control variable, the first coefficient matrix of the vehicle dynamics model, the second coefficient matrix, the third coefficient matrix, and the model predictive controller's The predicted length and the controlled length are used to construct the state equation of the model predictive controller. Exemplarily, the state equation of the model predictive controller can be constructed as follows:

其中，

表示模型预测控制器输出序列，U _Δ表示模型预测控制器的状态方程的自变量，即控制量，δ _Δ(k)表述k时刻δ的增量，X(k)表示k时刻车辆动力学模型的状态量，Y(k+1)为车辆动力学模型k+1时刻的预测输出量，U _o、δ ₀均表示第一控制量；S _u表示模型预测控制器状态方程的控制量系数，S _x表示模型预测控制器状态方程的***状态系数，A _c表示车辆动力学模型的第一系数矩阵、B _c表示车辆动力学模型的第二系数矩阵，C表示车辆动力学模型的第三系数矩阵，N _c表示模型预测控制器的控制长度，N _p表示模型预测控制器的预测长度。 in,

Represents the output sequence of the model predictive controller, U _Δ represents the independent variable of the state equation of the model predictive controller, that is, the control quantity, δ _Δ (k) represents the increment of δ at time k, and X(k) represents the vehicle dynamics model at time k The state quantity of , Y(k+1) is the predicted output quantity of the vehicle dynamics model at k+1 moment, U _o and δ ₀ both represent the first control quantity; S _u represents the control quantity coefficient of the state equation of the model predictive controller, S _x represents the system state coefficient of the model predictive controller state equation, A _c represents the first coefficient matrix of the vehicle dynamics model, B _c represents the second coefficient matrix of the vehicle dynamics model, and C represents the third coefficient of the vehicle dynamics model matrix, N _c represents the control length of the model predictive controller, and N _p represents the prediction length of the model predictive controller.

模型预测控制器状态方程的控制量系数S _u可以由如下公式获得： The control variable coefficient S _u of the model predictive controller state equation can be obtained by the following formula:

其中，N _c表示模型预测控制器的控制长度，N _p表示模型预测控制器的预测长度。车辆动力学模型的第一系数矩阵A _c、车辆动力学模型的第二系数矩阵B _c以及车辆动力学模型的第三系数矩阵C的计算公式在上述实施例已经给出，此处不再赘述。 Among them, N _c represents the control length of the model predictive controller, and N _p represents the prediction length of the model predictive controller. The calculation formulas of the first coefficient matrix A _c of the vehicle dynamics model, the second coefficient matrix B _c of the vehicle dynamics model, and the third coefficient matrix C of the vehicle dynamics model have been given in the above-mentioned embodiments, and will not be repeated here .

模型预测控制器状态方程的***状态系数S _x可以由如下公式获得： The system state coefficient _Sx of the model predictive controller state equation can be obtained by the following formula:

其中，N _c表示模型预测控制器的控制长度，N _p表示模型预测控制器的预测长度。车辆动力学模型的第一系数矩阵A _c和车辆动力学模型的第三系数矩阵C的计算公式在上述实施例已经给出，此处不再赘述。 Among them, N _c represents the control length of the model predictive controller, and N _p represents the prediction length of the model predictive controller. The calculation formulas of the first coefficient matrix A _c of the vehicle dynamics model and the third coefficient matrix C of the vehicle dynamics model have been given in the above embodiments, and will not be repeated here.

需要说明的是，通过构建模型预测控制器的状态方程，便于对目标函数进行滚动优化求解，从而可以确定出更准确稳定的第二控制量，生成更加稳定准确的车辆控制指令，控制车辆更精准地行驶。It should be noted that by constructing the state equation of the model predictive controller, it is convenient to solve the rolling optimization of the objective function, so that a more accurate and stable second control quantity can be determined, a more stable and accurate vehicle control command can be generated, and the vehicle can be controlled more precisely. driving.

可选的，在构建模型预测控制器的状态方程之后，可以基于模型预测控制器的状态方程，根据期望路径和目标函数的约束条件，利用模型预测控制器构建目标函数。示例性的，利用模型预测控制器构建的目标函数可以设计为如下线性二次规划问题：Optionally, after constructing the state equation of the model predictive controller, the model predictive controller may be used to construct the objective function based on the state equation of the model predictive controller and according to the desired path and constraints of the objective function. Exemplarily, the objective function constructed by using the model predictive controller can be designed as the following linear quadratic programming problem:

s.t.U _Δmin≤U _Δ≤U _Δmax stU _Δmin ≤ U _Δ ≤ _{U Δmax}

其中，U _Δ为目标函数的自变量，通过对线性二次规划问题进行求解获得的自变量最优解即为本申请实施例所述的第二控制量。U _Δmin≤U _Δ≤U _Δmax为目标函数的约束条件。H为目标函数的第一系数，F为目标函数的第二系数。 Wherein, U _Δ is an independent variable of the objective function, and the optimal solution of the independent variable obtained by solving the linear quadratic programming problem is the second control quantity described in the embodiment of the present application. U _Δmin ≤ U _Δ ≤ _{U Δmax} is the constraint condition of the objective function. H is the first coefficient of the objective function, and F is the second coefficient of the objective function.

目标函数的第一系数H可以通过如下公式获得：The first coefficient H of the objective function can be obtained by the following formula:

H＝2(S _u ^TQS _u+R) H＝2(S _u ^T QS _u +R)

其中，Q表示状态权重，R表示输入权重，模型预测控制器状态方程的控制量系数S _u的计算公式在上述实施例已经给出，此处不再赘述。 Wherein, Q represents the state weight, R represents the input weight, and the calculation formula of the control variable coefficient S _u of the model predictive controller state equation has been given in the above-mentioned embodiments, and will not be repeated here.

目标函数的第二系数F可以通过如下公式获得：The second coefficient F of the objective function can be obtained by the following formula:

其中，X表示模型预测控制器的***状态，

表示期望的模型预测控制器输出序列，可以根据期望路径确定。U _o表示第一控制量。Q表示状态权重。模型预测控制器状态方程的控制量系数S _u和模型预测控制器状态方程的***状态系数S _x的计算公式在上述实施例已经给出，此处不再赘述。 where X represents the system state of the model predictive controller,

represents the desired sequence of model predictive controller outputs, which can be determined from the desired path. U _o represents the first control quantity. Q represents the state weight. The calculation formulas of the control quantity coefficient S _u of the model predictive controller state equation and the system state coefficient S _x of the model predictive controller state equation have been given in the above-mentioned embodiments, and will not be repeated here.

S205、根据目标函数，利用模型预测控制器的状态方程，对目标函数进行滚动优化求解，确定第二控制量。S205. According to the objective function, use the state equation of the model predictive controller to solve the objective function by rolling optimization, and determine the second control quantity.

可选的，可以根据目标函数约束条件中控制量U _Δ的取值范围，利用模型预测控制器的状态方程，确定出多组控制量U _Δ与对应的模型预测控制器输出序列

的测试数据，将多组测试数据代入目标函数进行滚动优化求解，求解出使得目标函数达到最优值的控制量，将其作为第二控制量，即确定第二控制量。 Optionally, according to the value range of the control quantity U _Δ in the constraint condition of the objective function, the state equation of the model predictive controller can be used to determine multiple sets of control quantity U _Δ and the corresponding model predictive controller output sequence

Substituting multiple sets of test data into the objective function for rolling optimization solution, and solving the control quantity that makes the objective function reach the optimal value, and using it as the second control quantity, that is, determining the second control quantity.

可选的，在根据目标函数，利用模型预测控制器的状态方程，对目标函数进行滚动优化求解，确定第二控制量之前，还包括获取模型预测控制器的预测长度和控制长度；根据第一控制量、车辆动力学模型、模型预测控制器的预测长度以及控制长度，构建模型预测控制器的状态方程，过程在S204已经给出了详细的介绍，此处不进行赘述。Optionally, before determining the second control quantity by using the state equation of the model predictive controller to solve the objective function through rolling optimization according to the objective function, it also includes obtaining the prediction length and control length of the model predictive controller; according to the first The control quantity, the vehicle dynamics model, the prediction length of the model predictive controller and the control length, and the construction of the state equation of the model predictive controller have been introduced in detail in S204 and will not be repeated here.

S206、根据第二控制量，生成车辆控制指令，并基于车辆控制指令，控制车辆下一时刻的行驶。S206. Generate a vehicle control instruction according to the second control amount, and control the driving of the vehicle at a next moment based on the vehicle control instruction.

本申请实施例在确定第一控制量之后，根据期望路径和车辆当前时刻的位置信息，确定当前时刻的侧向偏差，根据侧向偏差与偏差阈值间的大小关系，确定目标函数的约束条件，根据第一控制量、期望路径、车辆动力学模型以及目标函数的约束条件，利用模型预测控制器构建目标函数，根据目标函数，利用模型预测控制器的状态方程，对目标函数进行滚动优化求解，确定第二控制量，最后根据第二控制量控制车辆下一时刻的行驶，通过这样的方式确定出的第二控制量具有更好的稳定性和准确性，从而便于后续生成更加稳定准确的车辆控制指令，控制车辆更精准地行驶。In the embodiment of the present application, after the first control amount is determined, the lateral deviation at the current time is determined according to the desired path and the position information of the vehicle at the current time, and the constraints of the objective function are determined according to the magnitude relationship between the lateral deviation and the deviation threshold, According to the constraint conditions of the first control quantity, expected path, vehicle dynamics model and objective function, the objective function is constructed by using the model predictive controller, and the rolling optimization is carried out to solve the objective function according to the objective function, using the state equation of the model predictive controller, Determine the second control amount, and finally control the driving of the vehicle at the next moment according to the second control amount. The second control amount determined in this way has better stability and accuracy, so as to facilitate subsequent generation of more stable and accurate vehicles Control instructions to control the vehicle to drive more precisely.

实施例三Embodiment three

图3A为本申请实施例三提供的一种车辆控制方法的流程图，图3B为本申请实施例三提供的确定车辆转弯半径的过程示意图，本实施例在上述实施例的基础上，对“根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量”进行详细的解释说明，如图3A所示，本实施例提供的车辆控制方法包括：Fig. 3A is a flow chart of a vehicle control method provided in the third embodiment of the present application, and Fig. 3B is a schematic diagram of the process of determining the turning radius of the vehicle provided in the third embodiment of the present application. This embodiment is based on the above-mentioned embodiments. According to the vehicle speed at the current moment of the vehicle, the expected route, the position information of the vehicle at the current moment and the vehicle attribute parameters, determine the first control amount" for detailed explanation, as shown in Figure 3A, the vehicle control method provided by this embodiment includes:

S301、根据期望路径和车辆当前时刻的位置信息，确定车辆的转弯半径。S301. Determine the turning radius of the vehicle according to the desired path and the current location information of the vehicle.

其中，车辆的转弯半径是指车辆转向行驶时，外侧转向轮的中心在支承平面上滚过的轨迹圆半径。Wherein, the turning radius of the vehicle refers to the radius of the track circle where the center of the outer steering wheel rolls on the supporting plane when the vehicle is turning.

可选的，可以根据车辆当前时刻的位置信息确定车辆坐标系下车辆的当前位置坐标。根据期望路径，确定期望路径上距离车辆当前位置最近的位置坐标点即最近点，根据最近点确定期望路径上的预瞄点，根据车辆坐标系下车辆的当前位置和预瞄点的坐标信息，确定车辆的转弯半径。Optionally, the current position coordinates of the vehicle in the vehicle coordinate system may be determined according to the position information of the vehicle at the current moment. According to the expected path, determine the position coordinate point closest to the current position of the vehicle on the expected path, that is, the closest point, determine the preview point on the expected path according to the closest point, and according to the current position of the vehicle in the vehicle coordinate system and the coordinate information of the preview point, Determine the turning radius of the vehicle.

示例性的，参见图3B，其中S为期望路径，A为期望路径上的预瞄点，B为期望路径上的最近点，坐标原点O表示车辆当前时刻的位置，R表示车辆的转弯半径。在确定最近点B、预瞄点A以及车辆位置坐标O之后，可以根据车辆位置坐标O与预瞄点A之间的几何关系，确定车辆的转弯半径R。For example, refer to FIG. 3B , where S is the desired path, A is the preview point on the desired path, B is the closest point on the desired path, the coordinate origin O represents the current position of the vehicle, and R represents the turning radius of the vehicle. After determining the closest point B, the preview point A, and the vehicle position coordinate O, the turning radius R of the vehicle can be determined according to the geometric relationship between the vehicle position coordinate O and the preview point A.

S302、根据车辆当前时刻的车速、车辆的转弯半径和车辆属性参数，利用纯跟踪算法确定第一控制量。S302. Determine the first control amount by using a pure tracking algorithm according to the vehicle speed at the current moment, the turning radius of the vehicle, and the vehicle attribute parameters.

其中，纯跟踪算法(Pure Pursuit)也叫纯路径跟踪算法，是一种传统且经典的车辆横向运动控制算法。Among them, the pure pursuit algorithm (Pure Pursuit) is also called the pure path tracking algorithm, which is a traditional and classic vehicle lateral motion control algorithm.

可选的，确定车辆的转弯半径之后，可以将车辆当前时刻的车速、车辆的转弯半径和车辆属性参数输入第一控制量确定模型，利用纯跟踪算法，输出第一控制量；也可以根据一定的计算规则，将车辆当前时刻的车速、车辆的转弯半径和车辆属性参数代入计算公式，利用纯跟踪算法，得到第一控制量。示例性的，可以根据如下公式计算第一控制量δ ₀： Optionally, after determining the turning radius of the vehicle, the vehicle speed at the current moment, the turning radius of the vehicle and the vehicle attribute parameters can be input into the first control variable determination model, and the first control variable can be output by using the pure tracking algorithm; The calculation rules of the vehicle, the vehicle speed at the current moment, the turning radius of the vehicle and the vehicle attribute parameters are substituted into the calculation formula, and the first control quantity is obtained by using the pure tracking algorithm. Exemplarily, the first control amount δ ₀ can be calculated according to the following formula:

其中，L表示车辆轴距，R表示车辆的转弯半径，U _x表示车速。K表示稳定性因素，可以通过如下公式计算稳定性因素K： Among them, L represents the wheelbase of the vehicle, R represents the turning radius of the vehicle, and U _x represents the vehicle speed. K represents the stability factor, and the stability factor K can be calculated by the following formula:

其中，a表示车辆前轴到车辆质心的距离，b表示后轴到质心的距离，m表示整车质量，L表示车辆轴距，k ₁表示前轮的侧偏刚度，k ₂表示后轮的侧偏刚度。 Among them, a represents the distance from the front axle of the vehicle to the center of mass of the vehicle, b represents the distance from the rear axle to the center of mass, m represents the mass of the vehicle, L represents the wheelbase of the vehicle, k ₁ represents the cornering stiffness of the front wheels, and k ₂ represents the stiffness of the rear wheels cornering stiffness.

S303、根据期望路径、车辆当前时刻的位置信息、第一控制量以及车辆动力学模型，确定第二控制量。S303. Determine the second control amount according to the desired route, the current position information of the vehicle, the first control amount, and the vehicle dynamics model.

S304、根据第二控制量，生成车辆控制指令，并基于车辆控制指令，控制车辆下一时刻的行驶。S304. Generate a vehicle control instruction according to the second control amount, and control the driving of the vehicle at a next moment based on the vehicle control instruction.

本申请实施例根据期望路径和车辆当前时刻的位置信息，确定车辆的转弯半径。根据车辆当前时刻的车速、车辆的转弯半径和车辆属性参数，利用纯跟踪算法确定第一控制量。进一步根据期望路径、车辆当前时刻的位置信息、第一控制量以及车辆动力学模型，确定第二控制量，进而根据第二控制量，生成车辆控制指令，并基于车辆控制指令，控制车辆下一时刻的行驶。通过首先确定车辆的转弯半径，再利用纯跟踪算法确定第一控制量，可以得到更加准确的第一控制量，由此可以确定出更稳定准确的第二控制量，生成更加稳定准确的车辆控制指令，控制车辆更精准地行驶。In the embodiment of the present application, the turning radius of the vehicle is determined according to the desired path and the current location information of the vehicle. According to the current speed of the vehicle, the turning radius of the vehicle and the attribute parameters of the vehicle, a pure tracking algorithm is used to determine the first control amount. Further, according to the desired path, the current position information of the vehicle, the first control quantity and the vehicle dynamics model, determine the second control quantity, and then generate the vehicle control instruction according to the second control quantity, and control the next step of the vehicle based on the vehicle control instruction. Moments of driving. By first determining the turning radius of the vehicle, and then using the pure tracking algorithm to determine the first control quantity, a more accurate first control quantity can be obtained, and thus a more stable and accurate second control quantity can be determined to generate a more stable and accurate vehicle control commands to control the vehicle to drive more precisely.

实施例四Embodiment four

图4为本申请实施例四提供的一种车辆控制装置的结构框图，本申请实施例所提供的一种车辆控制装置可执行本申请任一实施例所提供的一种车辆控制方法，具备执行方法相应的功能模块。所述车辆控制装置可以包括第一确定模块401、第二确定模块402和控制模块403。Fig. 4 is a structural block diagram of a vehicle control device provided in Embodiment 4 of the present application. The vehicle control device provided in the embodiment of the present application can execute a vehicle control method provided in any embodiment of the present application. The corresponding function module of the method. The vehicle control device may include a first determination module 401 , a second determination module 402 and a control module 403 .

第一确定模块401，设置为根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；The first determination module 401 is configured to determine the first control amount according to the vehicle speed at the current moment, the desired route, the position information of the vehicle at the current moment, and the vehicle attribute parameters;

第二确定模块402，设置为根据所述期望路径、所述车辆当前时刻的位置信息、所述第一控制量以及车辆动力学模型，确定第二控制量；The second determination module 402 is configured to determine a second control amount according to the desired path, the position information of the vehicle at the current moment, the first control amount and the vehicle dynamics model;

控制模块403，设置为根据所述第二控制量，生成车辆控制指令，并基于所述车辆控制指令，控制车辆下一时刻的行驶。The control module 403 is configured to generate a vehicle control instruction according to the second control amount, and control the driving of the vehicle at a next moment based on the vehicle control instruction.

本申请实施例根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；根据期望路径、车辆当前时刻的位置信息、第一控制量以及车辆动力学模型，确定第二控制量；根据第二控制量，生成车辆控制指令，并基于车辆控制指令，控制车辆下一时刻的行驶。通过这样的方式，能够生成更加稳定准确的车辆控制指令，控制车辆更精准地行驶，从而提高了车辆在各个应用场景如工程应用下的自适应性。In the embodiment of the present application, the first control amount is determined according to the vehicle speed at the current moment, the desired route, the position information of the vehicle at the current moment, and the vehicle attribute parameters; The model is used to determine the second control quantity; according to the second control quantity, a vehicle control command is generated, and based on the vehicle control command, the vehicle is controlled to travel at a next moment. In this way, more stable and accurate vehicle control commands can be generated, and the vehicle can be controlled to drive more precisely, thereby improving the adaptability of the vehicle in various application scenarios such as engineering applications.

可选的，第二确定模块402可以包括：Optionally, the second determining module 402 may include:

侧向偏差确定单元，设置为根据所述期望路径和所述车辆当前时刻的位置信息，确定当前时刻的侧向偏差；a lateral deviation determination unit, configured to determine the lateral deviation at the current moment according to the expected path and the current position information of the vehicle;

约束条件确定单元，设置为根据所述侧向偏差与偏差阈值间的大小关系，确定目标函数的约束条件；A constraint condition determining unit, configured to determine the constraint condition of the objective function according to the size relationship between the lateral deviation and the deviation threshold;

目标函数构建单元，设置为根据所述第一控制量、期望路径、车辆动力学模型以及目标函数的约束条件，利用模型预测控制器构建目标函数；The objective function construction unit is configured to use a model predictive controller to construct the objective function according to the first control amount, the desired path, the vehicle dynamics model, and the constraints of the objective function;

第二确定单元，设置为根据所述目标函数，利用模型预测控制器的状态方程，对所述目标函数进行滚动优化求解，确定第二控制量。The second determination unit is configured to perform a rolling optimization solution to the objective function by using the state equation of the model predictive controller according to the objective function, and determine the second control amount.

可选的，所述偏差阈值包括：第一阈值、第二阈值和第三阈值，且第一阈值小于第二阈值，第二阈值小于第三阈值。Optionally, the deviation threshold includes: a first threshold, a second threshold and a third threshold, and the first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold.

可选的，约束条件确定单元可以包括：Optionally, the constraint condition determination unit may include:

第一确定子单元，设置为若所述侧向偏差小于所述第一阈值，或所述侧向偏差大于或等于所述第三阈值，则根据预设数值确定所述目标函数的约束条件；The first determination subunit is configured to determine the constraints of the objective function according to preset values if the lateral deviation is smaller than the first threshold, or the lateral deviation is greater than or equal to the third threshold;

第二确定子单元，设置为若所述侧向偏差大于或等于所述第一阈值且小于所述第二阈值，则根据转向角最大变化增量、所述第一阈值、所述第二阈值和所述侧向偏差，确定所述目标函数的约束条件；The second determination subunit is configured to: if the lateral deviation is greater than or equal to the first threshold and less than the second threshold, according to the maximum change increment of the steering angle, the first threshold, and the second threshold and the lateral deviation, determining constraints on the objective function;

第三确定子单元，设置为若所述侧向偏差大于或等于所述第二阈值且小于所述第三阈值，则根据所述转向角最大变化增量、所述第二阈值、所述第三阈值和所述侧向偏差，确定所述目标函数的约束条件。The third determination subunit is configured to: if the lateral deviation is greater than or equal to the second threshold and smaller than the third threshold, according to the maximum change increment of the steering angle, the second threshold, the first Three thresholds and the lateral deviation determine the constraints of the objective function.

可选的，第二确定单元可以包括：Optionally, the second determining unit may include:

获取子单元，设置为获取所述模型预测控制器的预测长度和控制长度；The acquisition subunit is configured to acquire the prediction length and control length of the model predictive controller;

方程构建子单元，设置为根据所述第一控制量、车辆动力学模型、所述模型预测控制器的预测长度以及控制长度，构建模型预测控制器的状态方程。The equation construction subunit is configured to construct the state equation of the model predictive controller according to the first control quantity, the vehicle dynamics model, the prediction length of the model predictive controller, and the control length.

可选的，第一确定模块401可以包括：Optionally, the first determining module 401 may include:

转弯半径确定单元，设置为根据期望路径和车辆当前时刻的位置信息，确定车辆的转弯半径；The turning radius determination unit is configured to determine the turning radius of the vehicle according to the desired path and the current location information of the vehicle;

第一确定单元，设置为根据车辆当前时刻的车速、车辆的转弯半径和车辆属性参数，利用纯跟踪算法确定第一控制量。The first determining unit is configured to determine the first control amount by using a pure tracking algorithm according to the vehicle speed at the current moment, the turning radius of the vehicle and the vehicle attribute parameters.

可选的，所述车辆动力学模型为单轨车辆动力学模型。Optionally, the vehicle dynamics model is a monorail vehicle dynamics model.

实施例五Embodiment five

图5为本申请实施例五提供的一种电子设备的结构示意图，图5示出了适于用来实现本申请实施例实施方式的示例性设备的框图。图5显示的设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。Fig. 5 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application, and Fig. 5 shows a block diagram of an exemplary device suitable for implementing the implementation manner of the embodiment of the present application. The device shown in FIG. 5 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

如图5所示，电子设备12以通用计算设备的形式表现。电子设备12的组件可以包括但不限于：至少一个处理器或者处理单元16，***存储器28，连接不同***组件(包括***存储器28和处理单元16)的总线18。As shown in FIG. 5, electronic device 12 takes the form of a general-purpose computing device. Components of electronic device 12 may include, but are not limited to, at least one processor or processing unit 16 , system memory 28 , bus 18 connecting various system components including system memory 28 and processing unit 16 .

总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，***总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(ISA，Industry Standard Architecture)总线，微通道体系结构(MCA，Micro Channel Architecture)总线，增强型ISA总线、视频电子标准协会(VESA，Video Electronics Standards Association)局域总线以及***组件互连(PCI，peripheral component interconnect)总线。 Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA, Industry Standard Architecture) bus, Micro Channel Architecture (MCA, Micro Channel Architecture) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA, Video Electronics Standards Association) local bus and peripheral component interconnect (PCI, peripheral component interconnect) bus.

电子设备12典型地包括多种计算机***可读介质。这些介质可以是任何能够被电子设备12访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。 Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.

***存储器28可以包括易失性存储器形式的计算机***可读介质，例如随机存取存储器(RAM，Random Access Memory)30和/或高速缓存存储器(高速缓存32)。电子设备12可以进一步包括其它可移动/不可移动的、易失性/非易失性计算机***存储介质。作为举例，存储***34可以用于读写不可移动的、非易失性磁介质(图5未显示，通常称为“硬盘驱动器”)。尽管图5中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如CD-ROM(Compact Disc Read-Only Memory，只读光盘),DVD-ROM(Digital Video Disc-Read Only Memory，高密度数字视频光盘)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过至少一个数据介质接口与总线18相连。***存储器28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请实施例各实施例的功能。 System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM, Random Access Memory) 30 and/or cache memory (cache 32). The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a disk drive for reading and writing to a removable nonvolatile disk (such as a "floppy disk") may be provided, as well as a removable nonvolatile disk (such as a CD-ROM (Compact Disc Read). -Only Memory, read-only disc), DVD-ROM (Digital Video Disc-Read Only Memory, high-density digital video disc) or other optical media) CD-ROM drive. In these cases, each drive may be connected to bus 18 via at least one data medium interface. The system memory 28 may include at least one program product, which has a set of (for example, at least one) program modules configured to execute the functions of the various embodiments of the embodiments of the present application.

具有一组(至少一个)程序模块42的程序/实用工具40，可以存储在例如***存储器28中，这样的程序模块42包括但不限于操作***、至少一个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本申请实施例所描述的实施例中的功能和/或方法。a program/utility 40 having a set (at least one) of program modules 42, such as may be stored in system memory 28, such as but not limited to an operating system, at least one application program, other program modules, and program data, Implementations of networked environments may be included in each or some combination of these examples. The program module 42 generally executes the functions and/or methods in the embodiments described in the embodiments of this application.

电子设备12也可以与至少一个外部设备14(例如键盘、指向设备、显示器24等)通信，还可与至少一个使得用户能与该电子设备12交互的设备通信，和/或与使得该电子设备12能与至少一个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O，Input/Output) 接口22进行。并且，电子设备12还可以通过网络适配器20与至少一个网络(例如局域网(LAN，Local Area Network)，广域网(WAN，Wide Area Network)和/或公共网络，例如因特网)通信。如图所示，网络适配器20通过总线18与电子设备12的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备12使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID(Redundant Arrays of Independent Disks，磁盘阵列)***、磁带驱动器以及数据备份存储***等。The electronic device 12 can also communicate with at least one external device 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with at least one device that enables a user to interact with the electronic device 12, and/or communicate with the electronic device 12. 12. Any device capable of communicating with at least one other computing device (eg, network card, modem, etc.). This communication can take place via an input/output (I/O, Input/Output) interface 22 . Moreover, the electronic device 12 can also communicate with at least one network (such as a local area network (LAN, Local Area Network), a wide area network (WAN, Wide Area Network) and/or a public network, such as the Internet) through the network adapter 20. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18 . It should be understood that although not shown, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID (Redundant Arrays of Independent Disks, disk array) systems, tape drives, and data backup storage systems.

处理单元16通过运行存储在***存储器28中的程序，从而执行各种功能应用以及数据处理，例如实现本申请任意实施例所提供的车辆控制方法。The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , such as realizing the vehicle control method provided by any embodiment of the present application.

实施例六Embodiment six

本申请实施例六还提供一种计算机可读存储介质，其上存储有计算机程序(或称为计算机可执行指令)，该程序被处理器执行时用于执行本申请任意实施例所提供的车辆控制方法。Embodiment 6 of the present application also provides a computer-readable storage medium, on which a computer program (or computer-executable instruction) is stored. When the program is executed by a processor, it is used to execute the vehicle provided by any embodiment of the present application. Control Method.

本申请实施例的计算机存储介质，可以采用至少一个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM，Read-Only Memory)、可擦式可编程只读存储器(EPROM，Erasable Programmable Read-Only Memory)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。The computer storage medium in the embodiments of the present application may use any combination of at least one computer-readable medium. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connection with at least one lead, portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM, Read-Only Memory), Erasable Programmable Read-Only Memory (EPROM, Erasable Programmable Read-Only Memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any of the above-mentioned suitable combination. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。A computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave traveling as a data signal. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .

计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。The program code contained on the computer readable medium can be transmitted by any appropriate medium, including but not limited to wireless, electric wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.

可以以一种或多种程序设计语言或其组合来编写用于执行本申请实施例操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络包括局域网(LAN)或广域网(WAN)连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。Computer program codes for performing the operations of the embodiments of the present application may be written in one or more programming languages or combinations thereof, the programming languages including object-oriented programming languages—such as Java, Smalltalk, C++, including A conventional procedural programming language such as the "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. Where a remote computer is involved, the remote computer may be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g. via the Internet using an Internet Service Provider). .

Claims

一种车辆控制方法，包括：A method of vehicle control comprising:

根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；Determining the first control amount according to the vehicle speed at the current moment of the vehicle, the expected path, the position information of the vehicle at the current moment, and the attribute parameters of the vehicle;

根据所述期望路径、所述车辆当前时刻的位置信息、所述第一控制量以及车辆动力学模型，确定第二控制量；determining a second control amount according to the desired path, the current location information of the vehicle, the first control amount, and a vehicle dynamics model;

根据所述第二控制量，生成车辆控制指令，并基于所述车辆控制指令，控制车辆下一时刻的行驶。A vehicle control command is generated according to the second control amount, and based on the vehicle control command, the running of the vehicle at a next moment is controlled.
根据权利要求1所述的方法，其中，所述根据所述期望路径、所述车辆当前时刻的位置信息、所述第一控制量以及车辆动力学模型，确定第二控制量，包括：The method according to claim 1, wherein said determining the second control quantity according to the expected path, the current location information of the vehicle, the first control quantity and the vehicle dynamics model comprises:

根据所述期望路径和所述车辆当前时刻的位置信息，确定当前时刻的侧向偏差；determining the lateral deviation at the current moment according to the desired path and the current location information of the vehicle;

根据所述侧向偏差与偏差阈值的大小关系，确定目标函数的约束条件；determining the constraints of the objective function according to the size relationship between the lateral deviation and the deviation threshold;

根据所述第一控制量、期望路径、车辆动力学模型以及目标函数的约束条件，利用模型预测控制器构建目标函数；Constructing an objective function using a model predictive controller according to the first control amount, the desired path, the vehicle dynamics model, and the constraints of the objective function;

根据所述目标函数，利用模型预测控制器的状态方程，对所述目标函数进行滚动优化求解，确定第二控制量。According to the objective function, the state equation of the model predictive controller is used to solve the objective function through rolling optimization to determine the second control quantity.
根据权利要求2所述的方法，其中，所述偏差阈值包括：第一阈值、第二阈值和第三阈值，且第一阈值小于第二阈值，第二阈值小于第三阈值。The method according to claim 2, wherein the deviation threshold comprises: a first threshold, a second threshold and a third threshold, and the first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold.
根据权利要求3所述的方法，其中，所述根据所述侧向偏差与偏差阈值的大小关系，确定目标函数的约束条件，包括：The method according to claim 3, wherein said determining the constraints of the objective function according to the size relationship between the lateral deviation and the deviation threshold comprises:

响应于所述侧向偏差小于所述第一阈值，或所述侧向偏差大于或等于所述第三阈值，根据预设数值确定所述目标函数的约束条件；In response to the lateral deviation being smaller than the first threshold, or the lateral deviation being greater than or equal to the third threshold, determining constraints of the objective function according to preset values;

响应于所述侧向偏差大于或等于所述第一阈值且小于所述第二阈值，根据转向角最大变化增量、所述第一阈值、所述第二阈值和所述侧向偏差，确定所述目标函数的约束条件；In response to the lateral deviation being greater than or equal to the first threshold and less than the second threshold, based on the steering angle maximum change increment, the first threshold, the second threshold, and the lateral deviation, determine constraints on the objective function;

响应于所述侧向偏差大于或等于所述第二阈值且小于所述第三阈值，根据所述转向角最大变化增量、所述第二阈值、所述第三阈值和所述侧向偏差，确定所述目标函数的约束条件。In response to the lateral deviation being greater than or equal to the second threshold and less than the third threshold, according to the maximum change increment of the steering angle, the second threshold, the third threshold and the lateral deviation , to determine the constraints of the objective function.
根据权利要求2所述的方法，所述根据所述目标函数，利用模型预测控制器的状态方程，对所述目标函数进行滚动优化求解，确定第二控制量之前，还包括：The method according to claim 2, said according to the objective function, using the state equation of the model predictive controller, performing rolling optimization solution to the objective function, before determining the second control amount, further comprising:

获取所述模型预测控制器的预测长度和控制长度；obtaining the prediction length and control length of the model predictive controller;

根据所述第一控制量、车辆动力学模型、所述模型预测控制器的预测长度以及控制长度，构建模型预测控制器的状态方程。A state equation of the model predictive controller is constructed according to the first control quantity, the vehicle dynamics model, the predictive length of the model predictive controller, and the control length.
根据权利要求1所述的方法，其中，所述根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量，包括：The method according to claim 1, wherein said determining the first control amount according to the vehicle speed at the current moment of the vehicle, the expected route, the position information of the vehicle at the current moment and the attribute parameters of the vehicle comprises:

根据期望路径和车辆当前时刻的位置信息，确定车辆的转弯半径；Determine the turning radius of the vehicle according to the expected path and the current location information of the vehicle;

根据车辆当前时刻的车速、车辆的转弯半径和车辆属性参数，利用纯跟踪算法确定第一控制量。According to the current speed of the vehicle, the turning radius of the vehicle and the attribute parameters of the vehicle, a pure tracking algorithm is used to determine the first control amount.
根据权利要求1-6中任一项所述的方法，其中，所述车辆动力学模型为单轨车辆动力学模型。The method according to any one of claims 1-6, wherein the vehicle dynamics model is a monorail vehicle dynamics model.
一种车辆控制装置，包括：A vehicle control device comprising:

第一确定模块，设置为根据车辆当前时刻的车速、期望路径、车辆当前时刻的位置信息和车辆属性参数，确定第一控制量；The first determining module is configured to determine the first control amount according to the vehicle speed at the current moment of the vehicle, the desired route, the position information of the vehicle at the current moment, and the attribute parameters of the vehicle;

第二确定模块，设置为根据所述期望路径、所述车辆当前时刻的位置信息、所述第一控制量以及车辆动力学模型，确定第二控制量；The second determination module is configured to determine a second control amount according to the expected path, the current location information of the vehicle, the first control amount and a vehicle dynamics model;

控制模块，设置为根据所述第二控制量，生成车辆控制指令，并基于所述车辆控制指令，控制车辆下一时刻的行驶。The control module is configured to generate a vehicle control instruction according to the second control amount, and control the driving of the vehicle at a next moment based on the vehicle control instruction.
一种电子设备，包括：An electronic device comprising:

至少一个处理器；at least one processor;

存储器，设置为存储至少一个程序；a memory configured to store at least one program;

当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-7中任一项所述的车辆控制方法。When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle control method according to any one of claims 1-7.
一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-7中任一项所述的车辆控制方法。A computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the vehicle control method according to any one of claims 1-7 is implemented.