Tracking method of vehicle driving trajectory, control system, vehicle and storage medium

Abstract

The application discloses a vehicle driving track tracking method, a control system, a vehicle and a storage medium. The method comprises the following steps: acquiring planning information and positioning information; determining a longitudinal control variable and a lateral control variable based on the planning information and the positioning information; determining a target acceleration based on the longitudinal control variable; determining a target steering wheel rotation angle based on the lateral control variable; determining a first steering wheel torque based on the target steering wheel rotation angle and an observation quantity, wherein the observation quantity comprises a disturbance observation quantity; and working according to the target acceleration and the first steering wheel torque. The vehicle in the application can track and drive according to a planning path under the control of the target acceleration and the first steering wheel torque. In addition, after the first steering wheel torque is compensated and corrected through the disturbance observation quantity, when the vehicle works according to the first steering wheel torque, the interference of noise on the control system can be reduced, and the tracking accuracy of the planning path is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and more specifically, to a method for tracking vehicle driving trajectory, a control system, a vehicle, and a storage medium. Background Technology

[0002] Trajectory tracking control is a key technology in the field of autonomous driving. This technology is based on the vehicle's planned target trajectory and the vehicle's positioning data, and uses a series of control strategies to enable the vehicle to drive stably along the target trajectory.

[0003] However, the existing trajectory tracking control algorithm mainly uses the PID control algorithm. However, it is difficult to suppress noise interference in the system with a single PID control algorithm, resulting in poor control performance when the vehicle tracks the target trajectory according to the PID control algorithm. Summary of the Invention

[0004] This application provides a method for tracking vehicle driving trajectory, a control system, a vehicle, and a storage medium.

[0005] In a first aspect, some embodiments of this application provide a method for tracking a vehicle's driving trajectory. Applied to a vehicle, the method includes: acquiring planning information and positioning information, where the planning information represents parameter information of the planned path, and the positioning information represents the vehicle's position and attitude information at the current moment; determining longitudinal control quantities and lateral control quantities based on the planning information and positioning information, where the longitudinal control quantity is used to determine the vehicle's speed parameters, and the lateral control quantity is used to determine the vehicle's direction parameters; determining a target acceleration based on the longitudinal control quantity, where the target acceleration is the expected value of the acceleration; determining a target steering wheel angle based on the lateral control quantity, where the target steering wheel angle is the expected value of the steering wheel angle; determining a first steering wheel torque based on the target steering wheel angle and an observation, where the observation is determined based on a second steering wheel torque and the actual steering wheel angle in the previous control cycle, and the observation includes a disturbance observation, which represents the noise interference situation when the vehicle operates according to the second steering wheel torque; and operating according to the target acceleration and the first steering wheel torque.

[0006] Secondly, some embodiments of this application also provide a control system. This control system includes an onboard industrial control computer, a drive-by-wire gateway controller, and a vehicle execution system. The onboard industrial control computer is electrically connected to the drive-by-wire gateway controller, and the drive-by-wire gateway controller is electrically connected to the vehicle execution system. The onboard industrial control computer is configured to: acquire planning information and positioning information; determine longitudinal control quantities and lateral control quantities based on the planning information and positioning information; and send the longitudinal control quantities and lateral control quantities to the drive-by-wire gateway controller. The planning information represents the parameter information of the planned path, the positioning information represents the vehicle's position and attitude information at the current moment, the longitudinal control quantity is used to determine the vehicle's speed parameters, and the lateral control quantity is used to determine the vehicle's direction parameters. The drive-by-wire gateway controller is configured to: determine a target acceleration based on longitudinal control variables, determine a target steering wheel angle based on lateral control variables, determine a first steering wheel torque based on the target steering wheel angle and observed values, and send the target acceleration and first steering wheel torque to the vehicle actuator system. Here, the target acceleration is the desired acceleration value, the target steering wheel angle is the desired steering wheel angle, and the observed values ​​are determined based on the second steering wheel torque and actual steering wheel angle from the previous control cycle. The observed values ​​include disturbance observed values, which characterize the noise interference when the vehicle operates according to the second steering wheel torque. The vehicle actuator system is configured to operate according to the target acceleration and the first steering wheel torque.

[0007] Thirdly, some embodiments of this application also provide a vehicle, which includes one or more processors, a memory, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the one or more processors, and are configured to perform the aforementioned vehicle driving trajectory tracking method.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer program instructions. These computer program instructions can be invoked by a processor to execute the aforementioned vehicle driving trajectory tracking method.

[0009] Fifthly, embodiments of this application also provide a computer program product that, when executed, implements the aforementioned method for tracking vehicle driving trajectories.

[0010] This application provides a method, control system, vehicle, and storage medium for tracking a vehicle's driving trajectory. This application determines the vehicle's target acceleration and first steering wheel torque using the vehicle's planning and positioning information. On one hand, operating the vehicle according to the target acceleration enables precise speed control, and operating according to the first steering wheel torque enables precise steering control; that is, under the control of the target acceleration and the first steering wheel torque, the vehicle can track and drive along the planned path. On the other hand, in this application, the first steering wheel torque is determined based on observations from the previous control cycle. These observations include disturbance observations, which reflect the noise interference when the vehicle operates according to the second steering wheel torque from the previous control cycle. After compensating and correcting the first steering wheel torque using disturbance observations, the noise interference to the control system is reduced when the vehicle operates according to the first steering wheel torque, thus improving the tracking accuracy of the planned path. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This diagram illustrates the application environment of a vehicle driving trajectory tracking method provided in an embodiment of this application.

[0013] Figure 2 A structural block diagram of a control system provided in an embodiment of this application is shown.

[0014] Figure 3 A flowchart illustrating a vehicle driving trajectory tracking method provided in the first embodiment of this application is shown.

[0015] Figure 4 A schematic diagram of a longitudinal control strategy for a vehicle provided in an embodiment of this application is shown.

[0016] Figure 5 A flowchart illustrating a method for tracking a vehicle driving trajectory according to a second embodiment of this application is shown.

[0017] Figure 6 This illustration shows a schematic diagram of determining the first steering wheel torque based on a state observer, according to an embodiment of this application.

[0018] Figure 7 The diagram shows a flowchart illustrating a method for determining a target steering wheel angle according to an embodiment of this application.

[0019] Figure 8 A schematic diagram of a lateral control strategy for a vehicle provided in an embodiment of this application is shown.

[0020] Figure 9 A schematic diagram of a kinematic model of a vehicle provided in an embodiment of this application is shown.

[0021] Figure 10 A flowchart illustrating a vehicle driving trajectory tracking method provided in the third embodiment of this application is shown.

[0022] Figure 11 A flowchart illustrating a vehicle driving trajectory tracking method provided in the fourth embodiment of this application is shown.

[0023] Figure 12 A block diagram of a control system provided in another embodiment of this application is shown.

[0024] Figure 13 A block diagram of a vehicle provided in an embodiment of this application is shown.

[0025] Figure 14 A block diagram of a computer-readable storage medium provided in an embodiment of this application is shown. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0027] To enable those skilled in the art to better understand the solutions of this application, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0028] The following is an introduction to the technical terms that appear in this application.

[0029] Heading deviation: The difference between the target heading angle of the vehicle and the actual heading angle of the vehicle. The heading angle is the angle between the longitudinal axis of the vehicle and the due east direction in the ground coordinate system.

[0030] Lateral deviation: The difference between the horizontal coordinate value of the target position of the vehicle and the horizontal coordinate value of the actual position of the vehicle.

[0031] Steering wheel angle: The angle at which the vehicle's steering wheel is turned.

[0032] Steering wheel torque: The product of the magnitude of the pushing force applied when the steering wheel is turned and the radius of the steering wheel.

[0033] Front wheel steering angle: The angle at which the front wheels of a vehicle turn.

[0034] Steering ratio: The ratio between the steering wheel rotation angle and the steering angle of the vehicle's front wheels.

[0035] This application provides a method, control system, vehicle, and storage medium for tracking a vehicle's driving trajectory. This application determines the vehicle's target acceleration and first steering wheel torque using the vehicle's planning and positioning information. On one hand, operating the vehicle according to the target acceleration enables precise speed control, and operating according to the first steering wheel torque enables precise steering control; that is, under the control of the target acceleration and the first steering wheel torque, the vehicle can track and drive along the planned path. On the other hand, in this application, the first steering wheel torque is determined based on observations from the previous control cycle. These observations include disturbance observations, which reflect the noise interference when the vehicle operates according to the second steering wheel torque from the previous control cycle. After compensating and correcting the first steering wheel torque using disturbance observations, the noise interference to the control system is reduced when the vehicle operates according to the first steering wheel torque, thus improving the tracking accuracy of the planned path.

[0036] To facilitate a detailed explanation of the solution presented in this application, the application environment of the example in this application will be described below with reference to the accompanying drawings. Please refer to... Figure 1 , Figure 1 This is a schematic diagram illustrating the application environment of the vehicle driving trajectory tracking method provided in this application. The method is applied to a vehicle 100, which refers to a means of transportation driven or towed by a power device for carrying people or transporting goods, including but not limited to cars, minibuses, buses, etc. In this embodiment, the vehicle 100 includes a body 110, a control system 120, and a positioning device 130, and the control system 120 and the positioning device 130 are electrically connected.

[0037] The control system 120 processes signals and data, and controls the vehicle body 110 to operate according to the processed parameters. In this embodiment, the control system 120 has the function of acquiring planning information. The planning information represents the parameter information of the planned path of the vehicle 100, wherein the planned path includes multiple trajectory points, and each trajectory point includes planned position information and planned speed information, which are used to represent the target position and target speed of the vehicle 100 when it travels to the trajectory point. Specifically, the planning information can be acquired through the planning module in the control system 120.

[0038] Please see Figure 2 , Figure 2 A schematic block diagram of a control system provided in an embodiment of this application is shown. In this embodiment, the control system 120 includes an on-board industrial control computer 122, a drive-by-wire gateway controller 124, and a vehicle execution system 126. The on-board industrial control computer 122 is electrically connected to the drive-by-wire gateway controller 124, and the drive-by-wire gateway controller 124 is electrically connected to the vehicle execution system 126.

[0039] The vehicle-mounted industrial control computer 122 refers to an industrial control computer applied to the vehicle 100. An industrial control computer is a device that utilizes digital electronic technology to automatically execute arbitrary arithmetic or logical operations sequentially according to a series of instructions. In the embodiments of this application, the vehicle-mounted industrial control computer 122 has data acquisition, data preprocessing, and data transmission functions. The data acquisition function is used to acquire the planning and positioning information of the vehicle 100. The data preprocessing function is used to determine longitudinal and lateral control quantities based on the planning and positioning information. The longitudinal control quantity includes the target vehicle speed, and the lateral control quantity includes the curvature of the planned path, heading deviation, and lateral deviation. The data transmission function is used to send the longitudinal and lateral control quantities to the drive-by-wire gateway controller 124.

[0040] The drive-by-wire gateway controller 124 is used to determine a target control quantity based on longitudinal and lateral control quantities. In this embodiment, the drive-by-wire gateway controller 124 includes a longitudinal control module and a lateral control module. The longitudinal control module is used to determine a target acceleration based on the longitudinal control quantity. The lateral control module is used to determine a first steering wheel torque based on the lateral control quantity. In this embodiment, the drive-by-wire gateway controller 124 stores a core control algorithm (e.g., PID control algorithm, feedforward control algorithm, etc.). On one hand, the drive-by-wire gateway controller 124 calculates the target acceleration using the core control algorithm on the longitudinal control quantity; on the other hand, the drive-by-wire gateway controller 124 calculates the first steering wheel torque using the core control algorithm on the lateral control quantity. Specifically, the drive-by-wire gateway controller 124 in this embodiment is a microcontroller unit (MCU), for example, a single-chip microcontroller with a memory frequency of 200MHz.

[0041] It should be noted that the first steering wheel torque in this application is determined based on the target steering wheel angle and the observed values. The lateral control module first calculates the lateral control quantity using the core control algorithm to determine the target steering wheel angle, and then determines the first steering wheel torque based on the target steering wheel angle and the observed values. In this embodiment, the lateral control module also includes a linearly extended state observer, which is a type of disturbance observer. The linearly extended state observer is used to determine the observed values ​​in the current control cycle based on the second steering wheel torque and the actual steering wheel angle in the previous control cycle. The lateral control module then determines the first steering wheel torque based on the observed values ​​and the target steering wheel angle.

[0042] In addition, the drive-by-wire gateway controller 124 also has a data transmission function for sending the target to the vehicle execution system 126. Specifically, in this embodiment, the drive-by-wire gateway controller 124 and the vehicle execution system 126 are connected via a controller area network (CAN), and the drive-by-wire gateway controller 124 sends the target acceleration and the first steering wheel torque to the vehicle execution system 126 via the CAN bus.

[0043] It should be noted that the on-board industrial control computer 122 in this application is used for data preprocessing, while the drive-by-wire gateway controller 124 performs the calculation of the core control algorithm. This allows the core control calculation and data preprocessing calculation to be implemented on different hardware modules, ensuring module reusability. Researchers can perform corresponding development operations based on different modules, improving development efficiency. Furthermore, only the calculation of the core control algorithm needs to be completed on the drive-by-wire gateway controller, ensuring that the controller has sufficient computing resources to complete the calculation of the target acceleration and the first steering wheel torque, guaranteeing real-time control. The vehicle execution system 126 is used to control the vehicle 100 to operate based on the target control quantity. In this embodiment, the vehicle execution system 126 is a vehicle chassis actuator. The vehicle chassis actuator includes an Electrical Power Steering (EPS) control system, an Electronic Stability Program (ESP) braking control system, and a Vehicle Control Unit (VCU). Specifically, the EPS operates according to the first steering wheel torque, and the ESP or VCU operates according to the target acceleration.

[0044] The positioning device 130 is used to acquire the positioning information of the vehicle 100 and send the positioning information to the vehicle's control system 120. In this embodiment, the positioning device 130 includes a Global Navigation Satellite System (GNSS). GNSS is a high-precision radio navigation positioning system based on artificial Earth satellites, capable of providing the vehicle 100 with an accurate actual position anywhere in the world and in near-Earth space. In some embodiments, the positioning device 130 also includes an Inertial Measurement Unit (IMU). An IMU is a device that measures the three-axis attitude angles (or angular rates) and acceleration of the vehicle 100. In this application, the IMU is used to acquire the vehicle's attitude information, such as the vehicle's actual heading angle.

[0045] Please see Figure 3 , Figure 3 This illustration schematically depicts a vehicle driving trajectory tracking method provided in the first embodiment of this application. This method is applied to... Figure 1 Specifically, for vehicles in this process, the method includes the following steps S310 to S360.

[0046] Step S310: Obtain planning information and location information.

[0047] The planning information represents the parameter information of the planned path. In this embodiment, the planned path includes multiple trajectory points. The parameter information of the planned path includes the planned position information and planned speed information of the trajectory points. The planned position information represents the position of the trajectory point, and the planned speed information represents the estimated speed of the vehicle when it reaches the trajectory point. The number of trajectory points included in the planned path is determined based on the vehicle's current speed. Optionally, there is a threshold for the number of trajectory points corresponding to the vehicle's current speed. The number of trajectory points included in the planned path should be greater than the threshold for the number of trajectory points corresponding to the current vehicle speed to ensure that the subsequent trajectory point fitting steps can proceed normally. The interval information between adjacent trajectory points can be determined based on the vehicle's control accuracy requirements and control capabilities. For example, the higher the vehicle's control accuracy and the stronger its control capabilities, the smaller the interval length between adjacent trajectory points.

[0048] In some embodiments, the planning information is determined based on the vehicle's starting position and ending position. The vehicle obtains its current position, i.e., the starting position, based on its positioning device, and obtains the destination position, i.e., the ending position, from the autonomous driving instructions. Then, it determines the planning information based on a preset path planning algorithm, which may be an A* algorithm, a visibility chart method, a simulated annealing method, or other similar methods.

[0049] In other embodiments, the planning information is determined based on the vehicle's current location. The vehicle's current location can be obtained through its positioning device. Once the current location is determined, the vehicle updates the planning information in real time based on a preset local path planning algorithm. This local path planning algorithm can be a D-Star algorithm, an extended D-Star algorithm, or similar methods. It is understood that when updating the planning information in real time using the local path planning algorithm, the vehicle considers obstacle information around the vehicle (e.g., other vehicles, pedestrians, etc.). This obstacle information can be obtained through multiple LiDAR sensors around the vehicle.

[0050] The positioning information represents the vehicle's current position and attitude information. In this embodiment, when the vehicle detects that it is in motion, it acquires its position and attitude information at preset intervals via a positioning device. Specifically, the positioning device includes GNSS and IMU. The vehicle can acquire its position information via GNSS at preset intervals, and its attitude information (e.g., the vehicle's actual heading angle) via IMU at preset intervals. For example, the preset interval can be any duration greater than 5 milliseconds, such as 10 milliseconds.

[0051] In this embodiment, upon receiving an autonomous driving command, the vehicle acquires its current location planning and positioning information within each control cycle. The duration of the control cycle is determined by the developers based on the vehicle's control precision; that is, the higher the vehicle's control precision, the shorter the control cycle. Specifically, the control cycle duration can be any length greater than 5 milliseconds; for example, a control cycle duration of 20 milliseconds.

[0052] Step S320: Based on the planning information and positioning information, determine the longitudinal control quantity and the lateral control quantity.

[0053] Longitudinal control variables are used to determine the vehicle's speed parameters, and lateral control variables are used to determine the vehicle's direction parameters. In this embodiment, the vehicle's speed parameters include the target acceleration, and the vehicle's direction parameters include the target steering wheel angle. Specifically, the implementation methods for determining the longitudinal and lateral control variables based on planning and positioning information are described in the following embodiments.

[0054] Step S330: Determine the target acceleration based on the longitudinal control variable.

[0055] The target acceleration is the desired value of acceleration. In the embodiments of this application, the longitudinal control quantity includes the target vehicle speed, and the vehicle determines the target acceleration based on the target vehicle speed and the actual vehicle speed. As one implementation, given the target vehicle speed and the actual vehicle speed, the target acceleration is determined based on the acceleration controller. Please refer to [link to relevant documentation]. Figure 4 , Figure 4 A schematic diagram illustrating a longitudinal control strategy for a vehicle provided in an embodiment of this application is shown. Figure 4 In this system, the acceleration controller is a P controller, and the target acceleration determined by the P controller can be calculated using the following formula.

[0056] a=k(v req -v act ).

[0057] Where a is the target acceleration, v req For the target vehicle speed, v act The actual vehicle speed is represented by k, which is the proportional parameter of the P controller. The R&D personnel determine the value of the proportional parameter k based on the actual control situation of the vehicle.

[0058] Step S340: Determine the target steering wheel angle based on the lateral control quantity.

[0059] The target steering wheel angle is the desired value of the steering wheel angle. Specifically, the specific implementation method for determining the target steering wheel angle based on lateral control variables is described in the following examples.

[0060] Step S350: Determine the first steering wheel torque based on the target steering wheel angle and the observed values.

[0061] The observations are determined based on the second steering wheel torque and the actual steering wheel angle from the previous control cycle. The observations include disturbance observations, which characterize the noise interference when the vehicle operates according to the second steering wheel torque. The second steering wheel torque is the expected value of the steering wheel torque determined in the previous control cycle, and the first steering wheel torque is the expected value of the steering wheel torque determined in the current control cycle.

[0062] In this embodiment, after determining the second steering wheel torque in the previous control cycle, the vehicle operates according to the second steering wheel torque, achieving vehicle steering control. However, when the vehicle's execution system operates according to the second steering wheel torque, it is subject to interference from external noise. Therefore, the actual steering of the steering wheel is not controlled by the second steering wheel torque, resulting in a control deviation in the vehicle's execution system. If this control deviation is not compensated for, the control accuracy will decrease, leading to the vehicle being unable to travel along the planned path. Therefore, in this embodiment, by determining the observations including disturbance observations using the second steering wheel torque and the actual steering wheel angle in the previous control cycle, and then determining the first steering wheel torque based on the target steering wheel angle and the observations, disturbance compensation and correction are performed on the first steering wheel torque. This reduces external noise interference when the vehicle operates according to the first steering wheel torque, improving the accuracy of steering control.

[0063] Step S360: Work according to the target acceleration and the first steering wheel torque.

[0064] In the embodiments of this application, on one hand, the vehicle's braking control system or drive control system operates according to the target acceleration, thereby realizing vehicle speed control; on the other hand, the vehicle's steering control system operates according to the first steering wheel torque, thereby realizing vehicle steering control.

[0065] This application provides a method for tracking a vehicle's driving trajectory. In this method, the vehicle determines its target acceleration and first steering wheel torque using planning and positioning information. On one hand, operating the vehicle according to the target acceleration enables precise speed control, and operating according to the first steering wheel torque enables precise steering control. That is, under the control of the target acceleration and the first steering wheel torque, the vehicle can track and drive along the planned path. On the other hand, in this method, the first steering wheel torque is determined based on observations from the previous control cycle. These observations include disturbance observations, which reflect the noise interference when the vehicle operates according to the second steering wheel torque from the previous control cycle. After compensating and correcting the first steering wheel torque using disturbance observations, the noise interference to the vehicle control system is reduced when the vehicle operates according to the first steering wheel torque, improving the accuracy of steering control and thus enhancing the tracking accuracy of the planned path.

[0066] Please see Figure 5 , Figure 5 This illustration schematically depicts a vehicle driving trajectory tracking method provided in the second embodiment of this application. This method is applied to... Figure 1 The vehicle in the process includes observations of steering wheel angle and steering wheel angular velocity, both of which are determined based on the second steering wheel torque and actual steering wheel angle in the previous control cycle. Specifically, the steering wheel angle observation is an estimated value of the steering wheel angle, and the steering wheel angular velocity observation is an estimated value of the steering wheel angular velocity. This method includes steps S510 to S560. Figure 3 Step S350 is replaced by step S550.

[0067] Step S510: Obtain planning information and location information.

[0068] Step S520: Based on the planning information and positioning information, determine the longitudinal control quantity and the lateral control quantity.

[0069] In this embodiment of the application, the longitudinal control quantity and the lateral control quantity are determined by the vehicle based on the planning information and the positioning information, respectively. Specifically, step S520 may include steps S5210 and S5220.

[0070] Step S5210: Based on planning information and positioning information, determine the longitudinal control quantity.

[0071] In this embodiment, the longitudinal control quantity includes the target vehicle speed. Based on the vehicle's pre-aiming mechanism, the vehicle determines a first target trajectory point among multiple trajectory points, and the planned speed information corresponding to the first target trajectory point is determined as the vehicle's target speed. The pre-aiming mechanism is used to determine the trajectory point corresponding to a certain pre-aiming distance of the vehicle as the first target trajectory point during the vehicle's driving process, taking into account the first delay time of the vehicle's execution system. This makes the target vehicle speed determined based on the first target trajectory point more consistent with the vehicle's actual driving situation. In this embodiment, the first target trajectory point is determined based on the vehicle's actual speed and the first delay time. Specifically, based on the vehicle's actual speed and the first delay time, a first pre-aiming distance of the vehicle is determined, and then the first target trajectory point is determined based on the first pre-aiming distance. Specifically, the vehicle's first pre-aiming distance can be calculated using the following formula.

[0072] preview s1 =v*t delay .

[0073] Among them, preview s1 The first aiming distance of the vehicle is v, the actual speed of the vehicle is t. felay This is the first delay time. Specifically, the actual vehicle speed can be determined using the vehicle's positioning information. The first delay time is a calibrated value, which is determined by the R&D personnel through testing the vehicle's response performance.

[0074] In this embodiment, the distance information between the planned position information and the actual position information of the vehicle corresponding to multiple trajectory points is calculated respectively. The trajectory point with the smallest distance difference from the first pre-aiming distance among the multiple distance information is determined as the first target trajectory point, and then the planned speed information corresponding to the first target trajectory point is determined as the target speed of the vehicle. Specifically, the distance information can be calculated in the form of Euclidean distance, Manhattan distance, etc., and no specific limitation is made in this application.

[0075] Step S5220: Determine the lateral control quantity based on planning information and positioning information.

[0076] In this embodiment of the application, the lateral control quantity includes at least one of the curvature of the planned path, the heading deviation, and the lateral deviation.

[0077] As one implementation method, the length of the fitted curve is determined based on the actual speed of the vehicle, that is, the number of trajectory points used for curve fitting in the planned path. Then, the fitted curve equation corresponding to the planned path is determined based on multiple trajectory points, and finally, the curvature of the planned path is determined based on the fitted curve equation.

[0078] In the embodiments of this application, the length of the fitted curve is determined based on a first mapping relationship. This first mapping relationship characterizes the positive correlation between the actual vehicle speed and the length of the fitted curve; that is, the greater the actual vehicle speed, the longer the fitted curve. Specifically, the first mapping relationship can be represented by a first mapping function or a first mapping table, and no specific limitation is made in this application. Given a determined fitted curve length, the ratio of the fitted curve length to the distance between two adjacent trajectory points is used to determine the number of trajectory points.

[0079] The fitting curve equation corresponding to the planned path is determined by fitting the planned position information of multiple discrete trajectory points using the least squares method. The fitting curve equation can be represented by the following polynomial equation.

[0080] y = a n *x n +a n-1 *x n-1 +…+a1*x+a0.

[0081] Among them, a0, a1, ..., a n-1 and a n Here, represents the coefficients of the polynomial, and n represents the number of terms in the polynomial. It should be noted that after obtaining the polynomial equation, the variance of the polynomial equation is then calculated. If the variance is less than the preset variance, the curvature of the planned path is determined based on the polynomial equation; if the variance is greater than or equal to the preset variance, the number of terms in the polynomial is adjusted, and multiple discrete trajectory points are refitted based on the least squares method.

[0082] The curvature of the planned path is determined by differentiating the polynomial equation. Specifically, the curvature of the planned path can be calculated using the following formula.

[0083]

[0084] Where k is the curvature of the planned path, y′ represents the first-order derivative of the polynomial equation, and y″ represents the second-order derivative of the polynomial equation.

[0085] In some embodiments, before fitting a curve equation to the trajectory points, a step of processing the planned location information of the trajectory points is included. Specifically, in this application, the planned location information of the trajectory points is represented by coordinate points, which are described based on the world coordinate system. Before fitting a curve equation based on the coordinate points, a coordinate system transformation operation needs to be performed on the coordinate points, that is, the description method of the coordinate points is changed, transforming them into coordinate points described based on the vehicle coordinate system. Specifically, the vehicle coordinate system is a rectangular coordinate system, where the x-axis is the direction of the vehicle's forward movement, the y-axis is perpendicular to the direction of the vehicle's forward movement, the positive direction of the y-axis is to the left of the direction of the vehicle's forward movement, and the origin is the center position of the rear axle of the vehicle.

[0086] It should be noted that the world coordinate system is a global coordinate system, while the vehicle coordinate system is a local coordinate system. At least one coordinate element differs between the world and vehicle coordinate systems. This coordinate element can be the origin, the positive direction of the coordinate axis, the unit length of the coordinate axis, etc., and is not specifically limited in this application. In this embodiment, the vehicle uses calibration data to convert the position information of trajectory points in the world coordinate system into position information in the vehicle coordinate system. The calibration data includes the mapping relationship between the world and vehicle coordinate systems. Specifically, the calibration data can be a calibration matrix pre-stored in the vehicle's memory.

[0087] As one implementation method, based on the vehicle's pre-aiming mechanism, the vehicle determines the second target trajectory point among multiple trajectory points, and then determines the heading deviation and lateral deviation based on the vehicle's actual position and the second target trajectory point.

[0088] In this embodiment, the "pre-aiming" mechanism is used to determine the trajectory point corresponding to a certain forward pre-aiming distance of the vehicle as the second target trajectory point during vehicle operation, taking into account the second delay time of the vehicle's execution system. This makes the heading and lateral deviations determined based on the second target trajectory point more consistent with the actual driving conditions of the vehicle. In this embodiment, the second target trajectory point is determined based on the vehicle's actual speed, the second delay time, and the system compensation value. Specifically, the second pre-aiming distance of the vehicle is determined based on the vehicle's actual speed, the second delay time, and the system compensation value, and then the second target trajectory point is determined based on the second pre-aiming distance. Specifically, the second pre-aiming distance of the vehicle can be calculated using the following formula.

[0089] preview s2 =v*t pre +offset.

[0090] Among them, preview s2 The second aiming distance of the vehicle is v, the actual speed of the vehicle is t. prThe second delay time is t, and the offset is the system compensation value. Specifically, the actual vehicle speed can be determined using the vehicle's positioning information, and the second delay time is t. pre The system compensation value offset is used as the calibration value. The R&D personnel determine the above-mentioned second delay time and calibration value by testing the response performance of the vehicle.

[0091] In this embodiment, the distance information between the planned location information and the actual location information of the vehicle corresponding to multiple trajectory points is calculated respectively. The trajectory point with the smallest distance difference from the second pre-aiming distance among the multiple distance information is determined as the second target trajectory point. Specifically, the distance information can be calculated using Euclidean distance, Manhattan distance, etc., and no specific limitation is made in this application.

[0092] In this embodiment, the lateral deviation is the difference between the first abscissa value of the coordinate point corresponding to the second target trajectory point and the second abscissa value of the coordinate point corresponding to the vehicle's current position. Specifically, the lateral deviation can be calculated using the following formula.

[0093] lat err =x req -x act .

[0094] Among them, lat err For lateral deviation, x req x is the first x-coordinate value. act This is the value of the second horizontal axis.

[0095] In this embodiment, the heading deviation is the difference between the first heading angle corresponding to the second target trajectory point and the second heading angle of the vehicle's current position. The first heading angle can be determined by solving the tangent line of the fitted curve equation at the second target trajectory point, and defining the angle between the tangent line and the x-axis of the vehicle coordinate system. Specifically, the heading deviation can be calculated using the following formula.

[0096] heading err =θ req -θ act .

[0097] Among them, heading err For the heading deviation, θ req Let θ be the first heading angle. act This is the second heading angle.

[0098] It should be noted that steps S5210 and S5220 are not executed in any particular order. That is, the vehicle can execute step S5210 first and then step S5220. Alternatively, the vehicle can execute step S5220 first and then step S5210. Or, the vehicle can execute steps S5210 and S5220 simultaneously.

[0099] Step S530: Determine the target acceleration based on the longitudinal control variable.

[0100] Step S540: Determine the target steering wheel angle based on the lateral control quantity.

[0101] Step S550: Determine the first steering wheel torque based on the target steering wheel angle, disturbance observation, steering wheel angle observation, and steering wheel angular velocity observation.

[0102] In this embodiment, the observation used to determine the first steering wheel torque is determined based on a state observer. Please refer to... Figure 6 , Figure 6 This diagram schematically illustrates a method for determining the first steering wheel torque based on a state observer, as provided in an embodiment of this application. Figure 6 In this context, the state observer is a Linear Extended State Observer (LESO). The inputs to this LESO are the second steering wheel torque and the actual steering wheel angle from the previous control cycle. The outputs are the steering wheel angle observation z1, the steering wheel angular velocity observation z2, and the disturbance observation z3. In other words, this LESO is a second-order controller. Specifically, step S550 may include steps S5510 to S5550.

[0103] Step S5510: Based on the target steering wheel angle, determine the target steering wheel angular velocity, which is the expected value of the steering wheel angular velocity.

[0104] Please refer to it again. Figure 6 ,exist Figure 6 In this process, the target steering wheel angular velocity is determined based on a filter. Specifically, this filter is a differential filter, and the input value of the filter is the target steering wheel angle. That is, the target steering wheel angle is differentiated to obtain the target steering wheel angular velocity.

[0105] Step S5520: Determine the first error based on the target steering wheel angle and the steering wheel angle observation.

[0106] In this embodiment, the difference between the target steering wheel angle and the observed steering wheel angle is defined as the first error. Specifically, the first error can be calculated using the following formula.

[0107] e1 = swa req -z1.

[0108] Where e1 is the first error, swa req Let z1 be the target steering wheel angle, and z2 be the measured steering wheel angle.

[0109] Step S5530: Determine the second error based on the target steering wheel angular velocity and the observed steering wheel angular velocity.

[0110] In this embodiment, the difference between the target steering wheel angular velocity and the observed steering wheel angular velocity is defined as the second error. Specifically, the second error can be calculated using the following formula.

[0111] e2 = swa_spd req -z2.

[0112] Where e2 is the second error, swa_spd req Let z1 be the target steering wheel angular velocity, and z2 be the observed steering wheel angular velocity.

[0113] Step S5540: Determine the third error based on the first error and the second error.

[0114] In this embodiment, the third error is the error quantity obtained by feedback control of the first and second errors. Please refer again. Figure 6 ,exist Figure 6 The third error is determined based on the error feedback controller, whose inputs are the first and second errors, and whose output is the third error. Specifically, the third error can be calculated using the following formula.

[0115] e3 = b1*e1 + b2*e2.

[0116] Where e3 is the third error, and b1 and b2 are the control parameters in the error feedback controller.

[0117] Step S5550: Determine the first steering wheel torque based on the third error and disturbance observations.

[0118] In this embodiment, the first steering wheel torque is a control quantity obtained by feedback control based on the difference between the third error and the disturbance observation. Please refer again. Figure 6 ,exist Figure 6 The first steering wheel torque is determined based on the P controller, whose input is the difference between the third error and the disturbance observation, and whose output is the first steering wheel torque. Specifically, the first steering wheel torque can be calculated using the following formula.

[0119]

[0120] Where swt is the first steering wheel torque, z3 is the disturbance observation, and 1 / b0 is the proportional parameter of the P controller.

[0121] Step S560: Work according to the target acceleration and the first steering wheel torque.

[0122] This application provides a method for tracking a vehicle's driving trajectory. Specifically, this method describes a specific implementation for determining the first steering wheel torque based on observations. By using disturbance observations in the observations to compensate for and correct the disturbance in the first steering wheel torque, the interference from external noise can be reduced when the vehicle operates according to the first steering wheel torque, thus improving the accuracy of steering control.

[0123] Please see Figure 7 , Figure 7 This illustration schematically depicts a method for determining a target steering wheel angle according to an embodiment of this application. In this method, the target steering wheel angle is determined based on lateral control variables, which include the curvature of the planned path, heading deviation, and lateral deviation. Please refer to... Figure 8 , Figure 8 A schematic diagram illustrating a lateral control strategy for a vehicle provided in an embodiment of this application is shown. In this method, a first control variable is obtained by feedforward control of the curvature of the planned path; a second control variable and a third control variable are obtained by feedback control of the lateral deviation and heading deviation, respectively; then, the front wheel steering angle of the vehicle is determined based on the first, second, and third control variables; finally, the target steering wheel angle is determined based on the front wheel steering angle. Specifically, step S340 in the above embodiment may include steps S710 to S750.

[0124] Step S710: Determine the first control variable based on the curvature of the planned path.

[0125] In this embodiment, the first control variable is a control variable obtained by feedforward control based on the curvature of the planned path. Specifically, the first control variable is determined based on the curvature and the target heading angle. Please refer to [link to relevant documentation]. Figure 9 , Figure 9 A schematic diagram of a kinematic model provided in an embodiment of this application is shown. The vehicle is located at point A, point B is the target planning point, and θ... req Let B be the target heading angle corresponding to the target planning point, and P be any point between line segments AB. The heading angle and angular velocity corresponding to point P can be calculated using the following formula.

[0126]

[0127] Where β is the heading angle at point P, l rLet l be the distance between points A and P. f Let be the distance between point B and point P.

[0128] ω=k*v.

[0129] Where ω is the angular velocity at point P, k is the curvature of the planned path at point P, and v is the actual vehicle speed. Based on the heading angle and angular velocity, the vehicle can then determine the first control variable. Specifically, the first control variable can be calculated using the following formula.

[0130]

[0131] Where, δ ff This is the first control variable.

[0132] Step S720: Determine the second control variable based on the lateral deviation.

[0133] In this embodiment, the second control quantity is the control quantity obtained by feedback control of the lateral deviation. Please refer again. Figure 8 ,exist Figure 8 The second control variable is determined based on a PID controller, whose input is the lateral deviation and output is the second control variable. Specifically, the second control variable can be calculated using the following formula.

[0134]

[0135] Where, δ lb As the second control variable, lat err For lateral deviation, k p k i and k d These are the proportional, integral, and derivative parameters corresponding to the PID controller, k. p k i and k d The values ​​were calibrated by the R&D personnel based on the actual control conditions of the vehicle.

[0136] Step S730: Determine the third control variable based on the heading deviation.

[0137] In this embodiment, the third control quantity is the control quantity obtained by feedback control of the heading deviation. Please refer again. Figure 8 ,exist Figure 8 The third control variable is determined based on a PID controller, whose input is the heading deviation and output is the third control variable. Specifically, the third control variable can be calculated using the following formula.

[0138]

[0139] Where, δ hb For the third control variable, heading err For the heading deviation, k p k i and k d These are the proportional, integral, and derivative parameters corresponding to the PID controller, k. p k i and k d The values ​​were calibrated by the R&D personnel based on the actual control conditions of the vehicle.

[0140] It should be noted that in steps S720 and S730, the lateral deviation and heading deviation are controlled by the PID controller, which reduces the interference of the external environment on the steering control when the vehicle determines the front wheel angle based on the second and third control variables, thereby improving the accuracy of the steering control.

[0141] Step S740: Determine the front wheel steering angle based on the first control quantity, the second control quantity, and the third control quantity.

[0142] In this embodiment, the front wheel steering angle is determined based on a first control quantity, a second control quantity, a third control quantity, and a proportional coefficient corresponding to each control quantity. Specifically, the front wheel steering angle can be calculated using the following formula.

[0143] δ f =k ff *δ ff +k lb *δ lb +k hb *δ hb .

[0144] Where, δ f For the front wheel steering angle, k ff k lb and k hb These are the proportional coefficients corresponding to each control variable. k ff k lb and k hb The value was calibrated by the R&D personnel based on the actual control of the vehicle. In other words, the calibrated proportional coefficient can be used under different working conditions, ensuring that the vehicle can obtain accurate front wheel steering angles under different working conditions.

[0145] Step S750: Determine the target steering wheel angle based on the front wheel angle and steering gear ratio.

[0146] In this embodiment, the product of the front wheel steering angle and the steering gear ratio is determined as the target steering wheel angle. Specifically, the target steering wheel angle can be calculated using the following formula.

[0147] δ w =k r *δ f .

[0148] Where, δ w For the target steering wheel angle, k r The steering gear ratio, i.e., k r This is a steering parameter, which can be determined by reading the default parameters from the vehicle's memory.

[0149] It should be noted here that the target steering wheel angle δ in step S750 w And the target steering wheel angle swa in step S5520 req The values ​​are the same, that is, step S550 is executed after step S750.

[0150] This application provides a method for determining a target steering wheel angle. In this method, the target steering wheel angle is obtained by feedforward control of the curvature of the planned path and feedback control of lateral deviation and heading deviation, respectively. Through the combined effect of feedforward control and feedback control, the interference of the external environment on steering control is reduced, and the accuracy of subsequent steering control is improved.

[0151] Please see Figure 10 , Figure 10 This illustration schematically depicts a vehicle driving trajectory tracking method provided in the third embodiment of this application. This method is applied to... Figure 1 Specifically, for the vehicles mentioned, this method includes steps S1010 to S1070. Figure 3 Step S360 is replaced by steps S1060-S1070.

[0152] Step S1010: Obtain planning information and location information.

[0153] Step S1020: Based on the planning information and positioning information, determine the longitudinal control quantity and the lateral control quantity.

[0154] Step S1030: Determine the target acceleration based on the longitudinal control variable.

[0155] Step S1040: Determine the target steering wheel angle based on the lateral control quantity.

[0156] Step S1050: Determine the first steering wheel torque based on the target steering wheel angle and the observed values.

[0157] Step S1060: Determine the longitudinal control method of the vehicle based on the target acceleration.

[0158] The longitudinal control method includes drive control and braking control. In this embodiment, the longitudinal control method is determined based on the relationship between the target acceleration and a preset threshold. Specifically, step S1060 includes steps S10610 and S10620.

[0159] Step S10610: If the target acceleration is greater than or equal to a preset threshold, determine that the longitudinal control mode of the vehicle is drive control.

[0160] Step S10620: If the target acceleration is less than a preset threshold, determine that the longitudinal control mode of the vehicle is braking control.

[0161] The preset threshold is the vehicle's default parameter. Please refer to it again. Figure 3 ,exist Figure 3 The preset threshold value is 0, meaning that when the target acceleration is greater than or equal to 0, the longitudinal control mode of the vehicle is determined to be drive control. When the target acceleration is less than 0, the longitudinal control mode of the vehicle is determined to be drive control.

[0162] In other embodiments, the preset thresholds include a preset drive threshold and a preset braking threshold, where the preset drive threshold is greater than the preset braking threshold. When the target acceleration is greater than or equal to the preset drive threshold, the longitudinal control mode of the vehicle is determined to be drive control. When the target acceleration is less than the preset braking threshold, the longitudinal control mode of the vehicle is determined to be braking control. When the target acceleration is less than the preset drive threshold but greater than or equal to the preset braking threshold, the vehicle is determined to be in a coasting state, meaning that the vehicle speed is not controlled, thus avoiding switching between drive control and braking control modes. Specifically, the preset drive threshold and preset braking threshold are calibrated by the developers based on the actual control situation of the vehicle, and are not specifically limited in this embodiment.

[0163] In some embodiments, before sending the target acceleration to the vehicle's execution system, a step of filtering the target acceleration is included. Specifically, the filtering operation can be mean filtering, Gaussian filtering, etc. By processing the target acceleration through filtering, the vehicle can reduce noise interference in the target acceleration signal and improve the accuracy of vehicle speed control.

[0164] Step S1070: The vehicle operates according to the longitudinal control method and the first steering wheel torque.

[0165] In this embodiment, on one hand, when the longitudinal control mode of the vehicle is determined to be drive control, the vehicle's drive control system operates according to the target acceleration; on the other hand, when the longitudinal control mode of the vehicle is determined to be braking control, the vehicle's braking control system operates according to the target acceleration, thus achieving vehicle speed control. On the other hand, the vehicle's steering control system operates according to the first steering wheel torque, thus achieving vehicle steering control.

[0166] Please refer to it again. Figure 4 It should be noted that the longitudinal control strategy provided in this application includes a braking control strategy and a drive control strategy, where the target control quantity for both the braking control strategy and the drive control strategy is the target acceleration. That is, the longitudinal control strategy is essentially a single-input, single-output controller; the input to the controller is the target vehicle speed, and the output is the target acceleration. To simplify the controller design, this application uses only a P-controller to calculate the target acceleration. Because this application simplifies the longitudinal controller, the vehicle can quickly calculate the target acceleration, improving the efficiency of speed control.

[0167] In some embodiments, when the longitudinal control mode is drive control, the vehicle's drive control system operates according to the target acceleration, including steps A10 to A20.

[0168] Step A10: Determine the wheel-end torque based on the target acceleration and the actual acceleration.

[0169] In this embodiment, the wheel-end torque is a control quantity obtained by controlling the difference between the target acceleration and the actual acceleration. The control operation includes feedforward control and feedback control.

[0170] The vehicle's drive control system, upon determining the target acceleration, inputs the target acceleration and the actual acceleration into the feedforward controller and the feedback controller to obtain the wheel-end torque. The feedback controller is a PI controller. Specifically, the wheel-end torque can be calculated using the following formula.

[0171] DriveTorque = DriveTorque FF +k p *(a req -a act )+k i *∫(a req -a act ).

[0172] Where DriveTorque is the wheel-end torque, DriveTorque FF k represents the feedforward parameters of the feedforward controller. p and ki These are the proportional and integral parameters of the PI controller, a. req For the target acceleration, a act This represents the actual acceleration. Where DriveTorque... FF k p and k i The values ​​were calibrated by the R&D personnel based on the actual control conditions of the vehicle.

[0173] Step A20: Work according to the wheel end torque.

[0174] The vehicle's drive control system operates according to the wheel-end torque, thus achieving vehicle drive control, that is, speed control.

[0175] This application provides a method for tracking a vehicle's driving trajectory. In this method, the vehicle's longitudinal control includes drive control and braking control. The vehicle determines the corresponding longitudinal control mode based on the target acceleration, improving the accuracy of speed control and thus enhancing the tracking precision of the planned path.

[0176] In some embodiments, after step S310, the method further includes determining whether the planning information meets a first preset condition and whether the positioning information meets a second preset condition. If the vehicle determines that the planning information meets the first preset condition and the positioning information meets the second preset condition, then step S320 is executed. These detection steps are used to detect the accuracy and reliability of the planning information and positioning information, ensuring the stability of the autonomous vehicle control.

[0177] Specifically, after step S210, steps A100 to A300 are also included.

[0178] Step A100: Determine whether the planning information meets the first preset condition.

[0179] The first preset condition refers to the required number of trajectory points included in the planning information. In this embodiment, the planning information includes multiple trajectory points corresponding to the planned path, which are updated in real time. The vehicle obtains the number of trajectory points within the current planning information update cycle. If the number of trajectory points is greater than or equal to a threshold, the planning information is determined to meet the first preset condition; if the number of trajectory points is less than the threshold, the planning information is determined not to meet the first preset condition. It should be noted that the duration of the planning information update cycle is determined by the developers based on the vehicle's control precision; that is, the better the vehicle's control precision, the shorter the planning information update cycle. Specifically, the duration of the planning information update cycle can be any duration greater than 5 milliseconds, for example, 100 milliseconds.

[0180] In this embodiment, the quantity threshold is determined based on a second mapping relationship. This second mapping relationship represents the positive correlation between the actual vehicle speed and the quantity threshold; that is, the higher the actual vehicle speed, the higher the quantity threshold. Specifically, the second mapping relationship can be represented by a second mapping function or a second mapping table, and no specific limitation is made in this application. Taking the second mapping relationship as the second mapping function as an example, the vehicle determines its actual speed through positioning information, and then determines the quantity threshold through the second mapping function pre-stored inside the vehicle. If the number of trajectory points satisfies the following formula, then the planning information is determined to meet the first preset condition.

[0181] num plan ≥num threshold (v).

[0182] Where, num plan num represents the number of trajectory points, v represents the actual vehicle speed, and num represents the total number of trajectory points. threshold () is the second mapping function, num threshold (v) represents the quantity threshold.

[0183] In this embodiment, a vehicle quantity threshold is set. If the number of trajectory points is greater than or equal to the quantity threshold, it indicates that the planning information meets the first preset condition. This ensures that in subsequent steps, when the curve equation corresponding to the planned path is determined based on the trajectory points, there are enough trajectory points for curve direction fitting, ensuring the accuracy of curve fitting and thus ensuring the accuracy of subsequent steering control.

[0184] Step A200: Determine whether the location information meets the second preset condition.

[0185] The second preset condition refers to the accuracy requirement that the positioning information must meet. In this embodiment, the accuracy of the positioning information is determined based on the first location information collected in the previous positioning information update cycle and the second location information collected in the current positioning information update cycle. For example, the first and second location information are represented by coordinate points in a Cartesian coordinate system. Taking (x1, y1) as the first coordinate point corresponding to the first location information and (x2, y2) as the second coordinate point corresponding to the second location information as an example, if the first and second coordinate points satisfy the following formula, then the positioning information is determined to meet the second preset condition. If the first and second coordinate points do not satisfy the following formula, then the positioning information is determined not to meet the second preset condition.

[0186]

[0187] Where v is the actual vehicle speed, T is the duration of the positioning information update cycle, θ is the actual heading angle of the vehicle, and err is the error parameter. The error parameter err can be adjusted by the R&D personnel based on the positioning accuracy; that is, the higher the positioning accuracy, the smaller the error parameter. It should be noted that the duration of the positioning information update cycle is determined by the R&D personnel based on the vehicle's control accuracy; that is, the better the vehicle's control accuracy, the shorter the positioning information update cycle. Specifically, the duration of the positioning information update cycle can be any duration greater than 5 milliseconds, for example, 10 milliseconds.

[0188] Step A300: If the planning information meets the first preset condition and the positioning information meets the second preset condition, perform the step of determining the longitudinal control quantity and the lateral control quantity based on the planning information and the positioning information.

[0189] In some embodiments, if the planning information does not meet the first preset condition and / or the location information does not meet the second preset condition, the steps of obtaining the planning information and location information are re-executed.

[0190] In some embodiments, after step S210, step A400 is further included, determining whether the planning information count value is greater than the first pre-design value. If the planning information count value is greater than the first pre-design value, then step S220 is executed. If the planning information count value is less than or equal to the first pre-design value, the vehicle performs deceleration control.

[0191] The planning information count value represents the update status of the planning information. If planning information is received within the planning information update cycle, the planning information count value is increased by a first default value. If no planning information is received within the planning information update cycle, the planning information count value is decreased by a second default value. In this application, the default value of the planning information count value is 15, the first default value is 3, the second default value is 1, and the first preset count value is 0. That is, when the planning information count value is less than or equal to 0, the vehicle performs deceleration control, thereby ensuring the safety of the vehicle during driving.

[0192] It should be noted here that after adding the first default value to the planning information count value, the process also includes a step of determining whether the updated planning information count value is greater than the first count value threshold. If the updated planning information count value is greater than the first count value threshold, then the first count value threshold is used as the updated planning information count value. Specifically, this step can be described by the following formula.

[0193] n plan =max(n plan +3, 25).

[0194] Where, n planThe planning information count value is 3, which is the first default value, and 25 is the first count value threshold. In this embodiment, by setting the first count value threshold, the problem of numerical overflow caused by excessively large planning information count values ​​can be avoided.

[0195] In some embodiments, after step S210, step A500 is further included, determining whether the positioning information count value is greater than the second pre-designed value. If the positioning information count value is greater than the second pre-designed value, then step S220 is executed. If the positioning information count value is less than or equal to the second pre-designed value, the vehicle performs deceleration control.

[0196] The location information count value represents the update status of the location information. If location information is received within the location information update cycle, the location information count value is increased by a third default value. If no location information is received within the location information update cycle, the location information count value is decreased by a fourth default value. In this application, the default value of the location information count value is 3, the third default value is 3, the fourth default value is 1, and the second preset count value is 0. That is, when the location information count value is less than or equal to 0, the vehicle performs deceleration control, thereby ensuring the safety of the vehicle during driving.

[0197] It should be noted here that after adding the third default value to the location information count value, there is also a step to determine whether the updated location information count value is greater than the second count value threshold. If the updated location information count value is greater than the second count value threshold, then the second count value threshold is used as the updated location information count value. Specifically, this step can be described by the following formula.

[0198] n loc =max(n loc +3, 25).

[0199] Where, n loc Here, 3 represents the location information count value, 25 represents the third default value, and 3 represents the second count value threshold. In this embodiment, by setting the second count value threshold, the problem of numerical overflow caused by excessively large location information count values ​​can be avoided.

[0200] It should be noted that, in the embodiments of this application, the execution order of steps A100, A200, A400 and A500 is not specifically limited, and the above is only one embodiment provided by this application.

[0201] Please see Figure 11 , Figure 11 This illustration schematically depicts a vehicle driving trajectory tracking method provided in the fourth embodiment of this application. This method is applied to... Figure 1The vehicle in question includes a control system, which comprises an on-board industrial control computer, a drive-by-wire gateway controller, and a vehicle execution system. The on-board industrial control computer is electrically connected to the drive-by-wire gateway controller, and the drive-by-wire gateway controller is electrically connected to the vehicle execution system. Specifically, this method includes steps S1110 to S1180.

[0202] Step S1110: The vehicle-mounted industrial control computer acquires planning information and positioning information.

[0203] In step S1120, the on-board industrial control computer determines the longitudinal control quantity and the lateral control quantity based on the planning information and positioning information.

[0204] In step S1130, the on-board industrial control computer sends longitudinal control and lateral control quantities to the linear gateway controller.

[0205] Among them, planning information represents the parameter information of the planned path, positioning information represents the vehicle's position and attitude information at the current moment, longitudinal control variables are used to determine the vehicle's speed parameters, and lateral control variables are used to determine the vehicle's direction parameters.

[0206] In step S1140, the wire-controlled gateway controller determines the target acceleration based on the longitudinal control quantity.

[0207] In step S1150, the drive-by-wire gateway controller determines the target steering wheel angle based on the lateral control quantity.

[0208] In step S1160, the drive-by-wire gateway controller determines the first steering wheel torque based on the target steering wheel angle and the observed measurements.

[0209] In step S1170, the drive-by-wire gateway controller sends the target acceleration and the first steering wheel torque to the vehicle execution system.

[0210] Among them, the target acceleration is the expected value of acceleration, the target steering wheel angle is the expected value of steering wheel angle, the observation is determined based on the second steering wheel torque and the actual steering wheel angle in the previous control cycle, and the observation includes disturbance observation, which characterizes the noise interference when the vehicle is working according to the second steering wheel torque.

[0211] In step S1180, the vehicle execution system operates according to the target acceleration and the first steering wheel torque.

[0212] This application provides a method for tracking a vehicle's driving trajectory. In this method, the vehicle determines its target acceleration and first steering wheel torque using planning and positioning information. On one hand, operating the vehicle according to the target acceleration enables precise speed control, and operating according to the first steering wheel torque enables precise steering control. That is, under the control of the target acceleration and the first steering wheel torque, the vehicle can track and drive along the planned path. On the other hand, in this method, the first steering wheel torque is determined based on observations from the previous control cycle. These observations include disturbance observations, which reflect the noise interference when the vehicle operates according to the second steering wheel torque from the previous control cycle. After compensating and correcting the first steering wheel torque using disturbance observations, the noise interference to the vehicle control system is reduced when the vehicle operates according to the first steering wheel torque, improving the accuracy of steering control and thus enhancing the tracking accuracy of the planned path.

[0213] Please see Figure 12 , Figure 12 A schematic block diagram of a control system 1200 according to another embodiment of this application is shown. The control system 1200 includes: an on-board industrial control computer 1210, a drive-by-wire gateway controller 1220, and a vehicle execution system 1230, wherein the on-board industrial control computer 1210 is electrically connected to the drive-by-wire gateway controller 1220, and the drive-by-wire gateway controller 1220 is electrically connected to the vehicle execution system 1230.

[0214] The vehicle-mounted industrial control computer 1210 is configured to: acquire planning information and positioning information; determine longitudinal control quantities and lateral control quantities based on the planning information and positioning information; and send the longitudinal control quantities and lateral control quantities to the linear gateway controller. Among them, the planning information represents the parameter information of the planned path, the positioning information represents the position and attitude information of the vehicle at the current moment, the longitudinal control quantity is used to determine the speed parameters of the vehicle, and the lateral control quantity is used to determine the direction parameters of the vehicle.

[0215] The drive-by-wire gateway controller 1220 is configured to: determine a target acceleration based on longitudinal control variables, determine a target steering wheel angle based on lateral control variables, determine a first steering wheel torque based on the target steering wheel angle and observations, and send the target acceleration and the first steering wheel torque to the vehicle execution system; wherein, the target acceleration is the expected value of acceleration, the target steering wheel angle is the expected value of steering wheel angle, the observations are determined based on the second steering wheel torque and the actual steering wheel angle in the previous control cycle, and the observations include disturbance observations, which characterize the noise interference when the vehicle is operating according to the second steering wheel torque.

[0216] The vehicle execution system 1230 is configured to operate according to the target acceleration and the first steering wheel torque.

[0217] In some embodiments, the observations further include a steering wheel angle observation and a steering wheel angular velocity observation, wherein the steering wheel angle observation is an estimate of the steering wheel angle and the steering wheel angular velocity observation is an estimate of the steering wheel angular velocity. The drive-by-wire gateway controller 1220 is also configured to determine a first steering wheel torque based on the target steering wheel angle, the disturbance observation, the steering wheel angle observation, and the steering wheel angular velocity observation.

[0218] In some embodiments, the drive-by-wire gateway controller 1220 is further configured to: determine a target steering wheel angular velocity based on a target steering wheel angle, wherein the target steering wheel angular velocity is an expected value of the steering wheel angular velocity; determine a first error based on the target steering wheel angle and a steering wheel angle observation; determine a second error based on the target steering wheel angular velocity and a steering wheel angular velocity observation; determine a third error based on the first and second errors, wherein the third error is an error quantity obtained by feedback control of the first and second errors; and determine a first steering wheel torque based on the third error and a disturbance observation, wherein the first steering wheel torque is a control quantity obtained by feedback control of the difference between the third error and the disturbance observation.

[0219] In some embodiments, the lateral control quantities include the curvature of the planned path, the heading deviation, and the lateral deviation. The drive-by-wire gateway controller 1220 is further configured to: determine a first control quantity based on the curvature of the planned path, the first control quantity being a control quantity obtained by feedforward control of the curvature of the planned path; determine a second control quantity based on the lateral deviation, the second control quantity being a control quantity obtained by feedback control of the lateral deviation; determine a third control quantity based on the heading deviation, the third control quantity being a control quantity obtained by feedback control of the heading deviation; determine the front wheel angle based on the first, second, and third control quantities; and determine the target steering wheel angle based on the front wheel angle and the steering gear ratio.

[0220] In some embodiments, the vehicle execution system 1230 is further configured to: determine a longitudinal control mode of the vehicle based on a target acceleration, the longitudinal control mode including drive control and braking control; and operate according to the vehicle's longitudinal control mode and a first steering wheel torque.

[0221] In some embodiments, the vehicle execution system 1230 is further configured to: determine the longitudinal control mode of the vehicle as drive control when the target acceleration is greater than or equal to a preset threshold; and determine the longitudinal control mode of the vehicle as braking control when the target acceleration is less than the preset threshold.

[0222] In some embodiments, the vehicle-mounted industrial control computer 1210 is further configured to: determine whether the planning information meets a first preset condition, the first preset condition being the number requirement of trajectory points included in the planning information; determine whether the positioning information meets a second preset condition, the second preset condition being the accuracy requirement met by the positioning information; and, if the planning information meets the first preset condition and the positioning information meets the second preset condition, execute the step of determining the longitudinal control quantity and the lateral control quantity based on the planning information and the positioning information.

[0223] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0224] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0225] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0226] This application provides a control system. In this control system, the vehicle determines its target acceleration and first steering wheel torque based on planning information and positioning information. On one hand, operating the vehicle according to the target acceleration enables precise speed control, and operating according to the first steering wheel torque enables precise steering control. That is, under the control of the target acceleration and the first steering wheel torque, the vehicle can follow the planned path. On the other hand, in this control system, the first steering wheel torque is determined based on observations from the previous control cycle. These observations include disturbance observations, which reflect the noise interference when the vehicle operates according to the second steering wheel torque from the previous control cycle. After compensating and correcting the first steering wheel torque using disturbance observations, the noise interference to the vehicle control system is reduced when the vehicle operates according to the first steering wheel torque, improving the accuracy of steering control and thus improving the tracking accuracy of the planned path.

[0227] Please see Figure 13 The illustration shows that an embodiment of this application also provides a vehicle 1300, which includes one or more processors 1310, a memory 1320, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the one or more processors, and are configured to perform the parking path determination method described above.

[0228] Processor 1310 may include one or more processing cores. Processor 1310 connects to various parts of the battery management system using various interfaces and lines, and performs various functions and processes data of the battery management system by running or executing instructions, programs, code sets, or instruction sets stored in memory 1320, and by calling data stored in memory 1320. Optionally, processor 1310 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 1310 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 1310 and may be implemented separately through a communication chip.

[0229] The memory 1320 may include random access memory (RAM) or read-only memory (ROM). The memory 1320 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1320 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created during the use of the electronic device (such as phonebook data, audio and video data, chat log data, etc.).

[0230] Please see Figure 14 The present application also provides a computer-readable storage medium 1400, which stores computer program instructions 1410 that can be invoked by a processor to perform the methods described in the above embodiments.

[0231] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, computer-readable storage media includes non-transitory computer-readable storage medium. Computer-readable storage medium 1400 has storage space for computer program instructions 1410 that perform any of the method steps described above. These computer program instructions 1410 can be read from or written to one or more computer program products.

[0232] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Although this application has disclosed preferred embodiments as above, it is not intended to limit this application. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the technical solution of this application. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A method for tracking vehicle driving trajectory, applied to a vehicle, characterized in that, The method includes: The system acquires planning information and positioning information, wherein the planning information represents the parameter information of the planned path, and the positioning information represents the vehicle's position and attitude information at the current moment. Based on the planning information and the positioning information, longitudinal control variables and lateral control variables are determined. The longitudinal control variables are used to determine the speed parameters of the vehicle, and the lateral control variables are used to determine the direction parameters of the vehicle. Based on the longitudinal control quantity, the target acceleration is determined, where the target acceleration is the expected value of the acceleration; Based on the lateral control amount, the target steering wheel angle is determined, and the target steering wheel angle is the expected value of the steering wheel angle; Based on the target steering wheel angle and the observed values, a first steering wheel torque is determined. The observed values ​​are determined based on the second steering wheel torque and the actual steering wheel angle in the previous control cycle. The observed values ​​include disturbance observed values, steering wheel angle observed values, and steering wheel angular velocity observed values. The disturbance observed values ​​characterize the noise interference when the vehicle is operating according to the second steering wheel torque. The steering wheel angle observed values ​​are estimated values ​​of the steering wheel angle and the steering wheel angular velocity observed values ​​are estimated values ​​of the steering wheel angular velocity. The step of determining the first steering wheel torque based on the target steering wheel angle and the observed measurement includes: determining the first steering wheel torque based on the target steering wheel angle, the disturbance observed measurement, the steering wheel angle observed measurement, and the steering wheel angular velocity observed measurement; It operates according to the target acceleration and the first steering wheel torque.

2. The method according to claim 1, characterized in that, The determination of the first steering wheel torque based on the target steering wheel angle, the disturbance observation, the steering wheel angle observation, and the steering wheel angular velocity observation includes: Based on the target steering wheel angle, the target steering wheel angular velocity is determined, and the target steering wheel angular velocity is the expected value of the steering wheel angular velocity; Based on the target steering wheel angle and the observed steering wheel angle, a first error is determined; Based on the target steering wheel angular velocity and the observed steering wheel angular velocity, a second error is determined; Based on the first error and the second error, a third error is determined, wherein the third error is the error amount obtained by feedback control of the first error and the second error; Based on the third error and the disturbance observation, the first steering wheel torque is determined. The first steering wheel torque is a control quantity obtained by feedback control based on the difference between the third error and the disturbance observation.

3. The method according to claim 1 or 2, characterized in that, The lateral control parameters include the curvature, heading deviation, and lateral deviation of the planned path. Determining the target steering angle based on the lateral control parameters includes: Based on the curvature of the planned path, a first control quantity is determined, which is a control quantity obtained by feedforward control of the curvature of the planned path. Based on the lateral deviation, a second control quantity is determined, which is a control quantity obtained by feedback control of the lateral deviation. Based on the heading deviation, a third control quantity is determined, which is a control quantity obtained by feedback control of the heading deviation; The front wheel steering angle is determined based on the first control quantity, the second control quantity, and the third control quantity; The target steering wheel angle is determined based on the front wheel angle and the steering gear ratio.

4. The method according to claim 1 or 2, characterized in that, The operation according to the target acceleration and the first steering wheel torque includes: Based on the target acceleration, the longitudinal control mode of the vehicle is determined, and the longitudinal control mode includes drive control and braking control; It operates according to the longitudinal control method of the vehicle and the torque of the first steering wheel.

5. The method according to claim 4, characterized in that, Determining the longitudinal control method of the vehicle based on the target acceleration includes: If the target acceleration is greater than or equal to a preset threshold, the longitudinal control mode of the vehicle is determined to be the drive control. If the target acceleration is less than a preset threshold, the longitudinal control mode of the vehicle is determined to be braking control.

6. The method according to any one of claims 1 or 2, characterized in that, After obtaining the planning information and location information, the following is also included: Determine whether the planning information meets the first preset condition, where the first preset condition refers to the requirement for the number of trajectory points included in the planning information; Determine whether the positioning information meets a second preset condition, wherein the second preset condition refers to the accuracy requirement that the positioning information meets; If the planning information meets the first preset condition and the positioning information meets the second preset condition, the step of determining the longitudinal control quantity and the lateral control quantity based on the planning information and the positioning information is executed.

7. The method according to claim 1 or 2, characterized in that, The vehicle includes a control system, which includes an on-board industrial control computer, a drive-by-wire gateway controller, and a vehicle execution system. The on-board industrial control computer is electrically connected to the drive-by-wire gateway controller, and the drive-by-wire gateway controller is electrically connected to the vehicle execution system. The onboard industrial control computer acquires planning information and positioning information, determines longitudinal control quantities and lateral control quantities based on the planning information and positioning information, and sends the longitudinal control quantities and lateral control quantities to the drive-by-wire gateway controller; wherein, the planning information represents the parameter information of the planned path, the positioning information represents the position and attitude information of the vehicle at the current moment, the longitudinal control quantity is used to determine the speed parameter of the vehicle, and the lateral control quantity is used to determine the direction parameter of the vehicle; The drive-by-wire gateway controller determines a target acceleration based on the longitudinal control quantity, a target steering wheel angle based on the lateral control quantity, and a first steering wheel torque based on the target steering wheel angle and the observed values. It then sends the target acceleration and the first steering wheel torque to the vehicle execution system. The target acceleration is the expected value of the acceleration, the target steering wheel angle is the expected value of the steering wheel angle, and the observed values ​​are determined based on the second steering wheel torque and the actual steering wheel angle in the previous control cycle. The observed values ​​include disturbance observations, steering wheel angle observations, and steering wheel angular velocity observations. The disturbance observations characterize the noise interference when the vehicle operates according to the second steering wheel torque. The steering wheel angle observations are estimated values ​​of the steering wheel angle, and the steering wheel angular velocity observations are estimated values ​​of the steering wheel angular velocity. The step of determining the first steering wheel torque based on the target steering wheel angle and the observed measurement includes: determining the first steering wheel torque based on the target steering wheel angle, the disturbance observed measurement, the steering wheel angle observed measurement, and the steering wheel angular velocity observed measurement; The vehicle's actuator operates according to the target acceleration and the first steering wheel torque.

8. A control system, characterized in that, The control system includes an on-board industrial control computer, a drive-by-wire gateway controller, and a vehicle execution system. The on-board industrial control computer is electrically connected to the drive-by-wire gateway controller, and the drive-by-wire gateway controller is electrically connected to the vehicle execution system. The on-board industrial control computer is configured to: acquire planning information and positioning information; determine longitudinal control quantities and lateral control quantities based on the planning information and positioning information; and send the longitudinal control quantities and lateral control quantities to the drive-by-wire gateway controller; wherein, the planning information represents the parameter information of the planned path, the positioning information represents the position and attitude information of the vehicle at the current moment, the longitudinal control quantity is used to determine the speed parameters of the vehicle, and the lateral control quantity is used to determine the direction parameters of the vehicle; The drive-by-wire gateway controller is configured to: determine a target acceleration based on the longitudinal control quantity, determine a target steering wheel angle based on the lateral control quantity, determine a first steering wheel torque based on the target steering wheel angle and the observed quantity, and send the target acceleration and the first steering wheel torque to the vehicle execution system; wherein, the target acceleration is the expected value of acceleration, the target steering wheel angle is the expected value of steering wheel angle, the observed quantity is determined based on the second steering wheel torque and the actual steering wheel angle in the previous control cycle, the observed quantity includes disturbance observed quantity, steering wheel angle observed quantity and steering wheel angular velocity observed quantity, the disturbance observed quantity characterizes the noise interference situation when the vehicle is operating according to the second steering wheel torque, the steering wheel angle observed quantity is an estimated value of the steering wheel angle, and the steering wheel angular velocity observed quantity is an estimated value of the steering wheel angular velocity; The step of determining the first steering wheel torque based on the target steering wheel angle and the observed measurement includes: determining the first steering wheel torque based on the target steering wheel angle, the disturbance observed measurement, the steering wheel angle observed measurement, and the steering wheel angular velocity observed measurement; The vehicle actuator is configured to operate according to the target acceleration and the first steering wheel torque.

9. A vehicle, characterized in that, include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that can be invoked by a processor to perform the method as described in any one of claims 1-7.

Images