Vehicle control method and device, vehicle and storage medium

Abstract

The application discloses a vehicle control method and device, a vehicle and a readable storage medium. The method comprises the following steps: determining a target path point and a related path point corresponding to the target path point from a planning path of a vehicle according to pose information of the vehicle; determining a heading angle proportional coefficient according to a curvature at the related path point in the planning path and a vehicle speed of the vehicle; determining a heading angle deviation feedback control amount of the vehicle according to path point information of the target path point, the heading angle proportional coefficient, a preset heading angle integral coefficient and a preset heading angle differential coefficient; and controlling the vehicle according to the heading angle deviation feedback control amount. According to the method, the heading angle proportional coefficient is adjusted in real time according to the curvature at the related path point and the vehicle speed, so that the accuracy of the heading angle proportional coefficient is higher, the accuracy of the determined heading angle deviation feedback control amount is higher, and the accuracy of the vehicle control is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, and more particularly, to a vehicle control method and device, a vehicle, and a computer readable storage medium. BACKGROUND

[0002] Vehicle intelligent driving control is one of the research hotspots in the field of vehicles today, and the performance of vehicle intelligent driving control directly affects user experience. Vehicle intelligent driving control usually adopts a control scheme of decoupling lateral control and longitudinal control, and the lateral control outputs a steering wheel angle and the longitudinal control outputs a driving torque, so as to control the vehicle according to the steering wheel angle and the driving torque.

[0003] However, using the existing control means, the vehicle control accuracy is low, resulting in poor user experience of the vehicle intelligent driving control function. SUMMARY

[0004] The present application provides a vehicle control method and device, a vehicle, and a computer readable storage medium to improve vehicle control accuracy and thus improve the experience of the vehicle intelligent driving control function.

[0005] In a first aspect, an embodiment of the present application provides a vehicle control method, and the method comprises:

[0006] determining a target path point and a related path point corresponding to the target path point from a planned path of the ego vehicle according to pose information of the ego vehicle;

[0007] determining a heading angle proportionality coefficient according to a curvature at the related path point in the planned path and a vehicle speed of the ego vehicle;

[0008] determining a heading angle deviation feedback control amount of the ego vehicle according to path point information of the target path point, the heading angle proportionality coefficient, a preset heading angle integral coefficient, and a preset heading angle differential coefficient; the heading angle deviation feedback control amount is used to indicate an angle of a steering wheel of the ego vehicle when correcting a deviation of a heading angle of the ego vehicle;

[0009] controlling the ego vehicle according to the heading angle deviation feedback control amount.

[0010] In a second aspect, an embodiment of the present application further provides a vehicle control device, and the device comprises:

[0011] a first determining module configured to determine a target path point and a related path point corresponding to the target path point from a planned path of the ego vehicle according to pose information of the ego vehicle;

[0012] a coefficient determining module configured to determine a heading angle proportionality coefficient according to a curvature at the related path point in the planned path and a vehicle speed of the ego vehicle;

[0013] The second determining module is configured to determine a heading angle deviation feedback control quantity of the ego vehicle according to the path point information of the target path point, the heading angle proportionality coefficient, a preset heading angle integral coefficient, and a preset heading angle differential coefficient; when the heading angle deviation feedback control quantity is used to indicate a deviation of the heading angle of the ego vehicle, the heading angle deviation feedback control quantity is used to indicate an angle of a steering wheel of the ego vehicle that is corrected.

[0014] The control module is configured to control the ego vehicle according to the heading angle deviation feedback control quantity.

[0015] In a third aspect, an embodiment of the present application further provides a vehicle, characterized in that the vehicle comprises: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method.

[0016] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores program code executable by a processor, and the program code, when executed by the processor, causes the processor to execute the method.

[0017] The vehicle control method and device, the vehicle, and the computer-readable storage medium provided in the present application determine a target path point and a related path point corresponding to the target path point from a planned path of an ego vehicle, and then determine a heading angle proportionality coefficient according to a curvature at the related path point in the planned path and a vehicle speed of the ego vehicle, so as to realize real-time adjustment of the heading angle proportionality coefficient according to the curvature at the related path point and the vehicle speed of the ego vehicle. The heading angle proportionality coefficient is related to a real-time driving process of the ego vehicle, and the accuracy of the heading angle proportionality coefficient is relatively high, so that the heading angle deviation feedback control quantity determined according to the heading angle proportionality coefficient has relatively high accuracy, the accuracy of control of the ego vehicle based on the heading angle deviation feedback control quantity is improved, and the occurrence of situations such as head shaking of the ego vehicle caused by relatively low accuracy of the heading angle deviation feedback control quantity determined by using a fixed heading angle proportionality coefficient and relatively low accuracy of control of the ego vehicle is greatly reduced, thereby effectively improving the user experience of intelligent driving control functions of the vehicle.

[0018] Other features and advantages of the embodiments of the present application will be described in the following description, and will become apparent from the description, or will be learned from the practice of the embodiments of the present application. The purposes and other advantages of the embodiments of the present application can be achieved and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiment description will be briefly introduced. Obviously, the accompanying drawings in the following description only represent some embodiments of the present application, and all other embodiments obtained by those skilled in the art without creative effort based on these accompanying drawings also belong to the scope of protection of the present application.

[0020] Figure 1 A schematic diagram of a vehicle hardware environment suitable for embodiments of the present application is shown.

[0021] Figure 2 A flowchart of a vehicle control method according to an embodiment of the present application is shown.

[0022] Figure 3 A flowchart of steps S140 of a corresponding embodiment is shown. Figure 2 A flowchart of steps S140 of a corresponding embodiment is shown.

[0023] Figure 4 A schematic diagram of a vehicle control process according to an embodiment of the present application is shown.

[0024] Figure 5 A block diagram of a vehicle control apparatus according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiment description will be briefly introduced. Obviously, the accompanying drawings in the following description only represent some embodiments of the present application, and all other embodiments obtained by those skilled in the art without creative effort based on these accompanying drawings also belong to the scope of protection of the present application.

[0026] It should be noted that similar reference numerals and letters refer to similar items throughout the accompanying drawings, and thus once an item is defined in one drawing, it is not necessary to further define and explain it in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0027] Referring to Figure 1 , Figure 1A schematic diagram of a vehicle hardware environment suitable for embodiments of the present application is shown. The vehicle 100 comprises a driving system 110 which can be built-in with various autonomous driving functions. The driving system 110 can store an electronic map and can plan a driving path according to the stored electronic map. The driving system 110 can also control the vehicle to drive autonomously according to the planned driving path.

[0028] The driving system 110 can comprise a data acquisition device 111, one or more (only one is shown in the figure) processors 112 and a memory 113.

[0029] The data acquisition device 111 is configured to detect the pose information of the vehicle and the environmental information around the vehicle. The data acquisition device 111 can comprise an in-vehicle camera, an in-vehicle infrared sensor, an in-vehicle monitoring radar, an out-vehicle camera, an out-vehicle monitoring radar, a door monitoring radar, a vehicle speed sensor and a steering wheel angle sensor, etc.

[0030] The processor 112 can be a micro control unit (MCU) which is built-in with the memory 113. The memory 113 stores programs which can be executed to implement the embodiments described below. The processor 112 can execute the programs stored in the memory 113.

[0031] The processor 112 can comprise one or more processors. The processor 112 is connected to various parts of the vehicle 100 via various interfaces and lines. The processor 112 executes various functions of the vehicle 100 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 113 and calling data stored in the memory 113.

[0032] The memory 113 can comprise a random access memory (RAM) and a read-only memory (ROM). The memory 113 can be configured to store instructions, programs, codes, code sets or instruction sets. The memory 113 can comprise a program storage area and a data storage area. The program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, etc.

[0033] Please refer to Figure 2 , Figure 2 A flow chart of a vehicle control method according to an embodiment of the present application is shown. The method is used for a vehicle and comprises the following steps.

[0034] S110, determining a target path point and a related path point corresponding to the target path point from a planned path of the ego vehicle according to the pose information of the ego vehicle.

[0035] The vehicle in the embodiment can be an electric vehicle or a fuel vehicle, and can be a car, an SUV, a bus, a truck, etc.; the ego vehicle refers to the vehicle itself.

[0036] The pose information of the ego vehicle refers to information for indicating the position and attitude of the ego vehicle, and can include coordinates (x a , y a ) for indicating the position of the ego vehicle, which can refer to the coordinates of the ego vehicle in the xoy coordinate plane of the world coordinate system, and can refer to the coordinates of a key point on the ego vehicle, which can be the center of mass of the ego vehicle, the center of the rear axle of the ego vehicle, etc.; the pose information of the ego vehicle can also include actual heading angle φ a and vehicle speed v a (actual vehicle speed) for indicating the attitude of the ego vehicle, etc.

[0037] In the embodiment, the pose information of the ego vehicle can be collected by various sensors in the ego vehicle, which can include a speed sensor, a steering wheel angle sensor, etc. In the embodiment, the pose information of the ego vehicle can refer to real-time pose information of the ego vehicle when the vehicle control method of the application is executed.

[0038] The planned path of the ego vehicle refers to a path planned by a trajectory prediction module of the ego vehicle based on the driving state of the ego vehicle. The trajectory prediction module can predict the trajectory of the ego vehicle according to the speed, acceleration, surrounding obstacles, speed of the obstacles, acceleration of the obstacles, and road information of the ego vehicle, to obtain the planned path of the ego vehicle, which can include a plurality of path points, each path point corresponding to a planning time, if the ego vehicle travels according to the planned path points, the ego vehicle is located at the path point when the planning time corresponding to each path point arrives; the plurality of path points are sequentially connected in order to form a planned path, wherein the order of the path points refers to the order of the planning times corresponding to the path points, that is, the path point with an earlier planning time is located in front of the path point with a later planning time. The planning time can be set based on requirements, for example, the interval between any two adjacent planning times is 0.1s.

[0039] Each path point in the planned path corresponds to path point information of the path point, and the path point information of the path point can include the coordinates (x r , y r ) and the attitude of the ego vehicle at the path point, wherein the coordinates in the path point information of the path point can refer to the coordinates of the path point in the xoy coordinate plane of the world coordinate system, and the attitude in the path point information of the path point can include the expected heading angle φ r of the ego vehicle at the path point and the curvature k r at the path point in the planned path, etc.

[0040] After obtaining the pose information of the ego vehicle and the planned path, a target path point and a related path point corresponding to the target path point are determined from a plurality of path points included in the planned path of the ego vehicle based on the pose information of the ego vehicle and the planned path.

[0041] In this embodiment, the related path point corresponding to the target path point can be the path point closest to the target path point in the planned path of the ego vehicle, or can be the path point with the most similar path point information to the target path point in the planned path of the ego vehicle, wherein the most similar path point information means that the relative distance is within a preset threshold range and the pose is the most similar; the preset threshold range can be set based on requirements, for example, the preset threshold range is 0.5 m. The most similar pose can mean that the difference in expected heading angle is the smallest or the difference in curvature is the smallest.

[0042] In some embodiments, the planned path includes a plurality of ordered path points (wherein the order of the plurality of path points is described above and will not be repeated); the related path point includes a first related path point and a second related path point; S110 can include: determining, from the plurality of path points, a path point with the smallest distance difference from the ego vehicle as the target path point according to the pose information of the ego vehicle; determining, from the plurality of path points, a first path point after the target path point as the first related path point; determining, from the plurality of path points, a second path point after the target path point as the second related path point.

[0043] After determining the target path point closest to the ego vehicle, a first path point after the target path point in the planned path is obtained as the first related path point, and a second path point after the target path point in the planned path is obtained as the second related path point.

[0044] S120, determining a heading angle proportionality coefficient according to the curvature at the related path point in the planned path and the speed of the ego vehicle.

[0045] The speed of the ego vehicle refers to the actual speed in the pose information of the ego vehicle. After determining the related path point, the curvature at the related path point can be obtained from the path point information of the related path point, and then the curvature at the related path point and the speed of the ego vehicle are combined to determine the heading angle proportionality coefficient.

[0046] In some embodiments, the related path point includes a first related path point and a second related path point, and accordingly, S120 can include: determining an adjustment coefficient according to the speed of the ego vehicle and a calibration constant; the adjustment coefficient is positively correlated with the speed of the ego vehicle; determining an adjustment amplitude based on the curvature difference between the curvature at the first related path point and the curvature at the second related path point in the planned path; the adjustment amplitude is positively correlated with the curvature difference; determining the heading angle proportionality coefficient based on the sine value of the adjustment amplitude and the adjustment coefficient.

[0047] In this embodiment, the calibration constant can be set based on requirements and is not limited. For example, the calibration constant may include a first calibration constant d and a second calibration constant e, thereby determining the calibration constant based on the first calibration constant d, the second calibration constant e, and the vehicle speed v. a The adjustment coefficient 'a' is determined by referring to Formula 1, which is as follows:

[0048] a=d*v a +e

[0049] It is understandable that Formula 1 is just an example, and other methods for calculating the adjustment coefficient can be determined, as long as the adjustment coefficient is positively correlated with the vehicle's speed.

[0050] After obtaining the adjustment coefficient 'a', the adjustment magnitude can be determined based on the curvature difference between the curvature at the first relevant path point and the curvature at the second relevant path point in the planned path, as well as other calibration constants. For example, other calibration constants may include a third calibration constant 'b' and a fourth calibration constant 'c'. Correspondingly, the process of determining the adjustment magnitude 'f' can refer to Formula 2, as follows:

[0051] f = b*(k) n+1 ―k n+2 )+c

[0052] Where, k n+1 Let k be the curvature at the first relevant path point in the planned path. n+2 Let k be the curvature at the second relevant path point in the planned path. n+1 ―k n+2 ) represents the curvature difference between the curvature at the first relevant path point and the curvature at the second relevant path point.

[0053] It is understandable that Formula 2 is just an example, and other methods for calculating the adjustment range can be determined, as long as the adjustment range is positively correlated with the curvature difference.

[0054] After obtaining the adjustment range f, the heading angle proportionality coefficient can be determined by combining the sine value of the adjustment range and the adjustment coefficient. For example, the product of the sine value of the adjustment range f and the adjustment coefficient a can be calculated as the heading angle proportionality coefficient. With the adjustment coefficient a determined according to Formula 1 and the adjustment range f determined according to Formula 2, the determination process for the heading angle proportionality coefficient refers to Formula 3, as follows:

[0055] K p―psi =a*sinf=a*sin[b*(k n+1 ―k n+2 )+c]

[0056] Among them, Kp―psi is a proportional coefficient of the heading angle.

[0057] In this embodiment, for the convenience of description, k n represents the curvature at the target path point in the planned path, k n+1 represents the curvature at the first related path point in the planned path, k n+2 represents the curvature at the second related path point in the planned path, the curvature of the path point at the future planning time in the driving process of the ego vehicle can obtain the change of the planned path in advance, so as to cope with the problem of vehicle shaking caused by poor tracking accuracy of the curve and control overshoot after turning out of the curve due to the delay of the action of the ego vehicle.

[0058] However, when k n ≠ k n+1 ≠ k n+2 , the curvatures of the three consecutive path points are discontinuous, that is, the ego vehicle is in the variable-curvature path tracking stage, at this time, the response of the expected heading angle deviation feedback controller should be larger to quickly converge the deviation caused by the delay of the action; when k n ≠ k n+1 = k n+2 , that is, the variable-curvature path stage ends, at this time, the output of the expected heading angle deviation feedback controller should be as stable as possible to reduce the control overshoot. Therefore, according to the above analysis, it is determined that the heading angle deviation feedback controller maintains fixed heading angle integral and differential coefficients, and uses an adjustable heading angle proportional coefficient, the acquisition process of the adjustable heading angle proportional coefficient is as above, and will not be described again.

[0059] S130, determining the heading angle deviation feedback control amount of the ego vehicle according to the path point information of the target path point, the heading angle proportional coefficient, the preset heading angle integral coefficient, and the preset heading angle differential coefficient.

[0060] Wherein, the heading angle deviation feedback control amount is used to indicate the deviation of the corrected heading angle of the ego vehicle, and the angle of the steering wheel of the ego vehicle is corrected; in other words, after the steering wheel of the ego vehicle is turned according to the heading angle deviation feedback control amount of the ego vehicle, the deviation of the heading angle of the ego vehicle is eliminated.

[0061] After obtaining the heading angle proportional coefficient, the preset heading angle integral coefficient and the heading angle differential coefficient are obtained, so that the heading angle deviation feedback controller determines the heading angle deviation feedback control amount of the ego vehicle according to the path point information of the target path point, the heading angle proportional coefficient, the preset heading angle integral coefficient, and the preset heading angle differential coefficient; wherein, the preset heading angle integral coefficient and the heading angle differential coefficient are values that can be set based on demand, and the present application does not make any constraints, wherein, in different driving conditions, the preset heading angle integral coefficient and the heading angle differential coefficient are fixed and unchanged.

[0062] In this embodiment, the heading angle deviation feedback controller can be a PID (Proportional-Integral-Derivative) controller, that is, the heading angle...

[0063] The deviation feedback controller performs proportional-integral-derivative calculations based on the path point information of the target path point, the heading angle proportional coefficient, the preset heading angle integral coefficient, and the preset heading angle derivative coefficient. The result is the heading angle deviation feedback control quantity of the vehicle.

[0064] In some embodiments, S130 may include: determining a heading angle deviation based on the difference between the desired heading angle in the path point information of the target path point and the actual heading angle in the vehicle's pose information; and determining a heading angle deviation feedback control quantity based on the heading angle deviation, the heading angle proportional coefficient, the heading angle integral coefficient, and the heading angle differential coefficient.

[0065] The vehicle's heading angle can be obtained from its pose information as the vehicle's actual heading angle φ. a And obtain the desired heading angle φ at the target waypoint from the waypoint information of the target waypoint. rn Then, φ can be calculated. rn With φ a The difference is taken as the heading angle deviation. That is, the heading angle deviation e psi =φ rn ―φ a .

[0066] Subsequently, the heading angle deviation feedback controller is based on e psi Perform proportional-integral-derivative (PI-DE) calculations to obtain the heading angle deviation feedback control quantity. This PI-DE calculation is based on Formula 4, which is as follows:

[0067]

[0068] Among them, u psi (t) represents the heading angle deviation feedback control value, K I―psi K is the preset integral coefficient for the heading angle. d―psi Here, ∫e is the preset differential coefficient of the heading angle, and t is the planning time at the target path point; psi (t)dt is the integral of the heading angle deviations (i.e., the cumulative heading angle deviations) of all planning times before planning time t within the planning period (which can be a fixed-length period based on demand, such as every 5 seconds) within the planning time t. This is the rate of change of the heading angle deviation at the planning time t (generally the difference between the heading angle deviation at planning time t and the heading angle deviation at planning time t-1).

[0069] As the aforementioned formula four, the heading angle deviation feedback controller is actually a weighted sum of the heading angle deviation, the accumulated heading angle deviation and the heading angle deviation change rate, wherein the weight of the heading angle deviation is the heading angle proportion coefficient, the weight of the accumulated heading angle deviation is the heading angle integral coefficient, and the weight of the heading angle deviation change rate is the heading angle differential coefficient.

[0070] S140, controlling the ego vehicle according to the heading angle deviation feedback control amount.

[0071] After obtaining the heading angle deviation feedback control amount, the ego vehicle is controlled according to the heading angle deviation feedback control amount.

[0072] The heading angle deviation feedback control amount is a control parameter of the ego vehicle in the lateral control direction, so the steering wheel steering angle of the ego vehicle can be determined based on the heading angle deviation feedback control amount, and then the steering wheel of the ego vehicle is controlled to rotate through the steering wheel steering angle, thereby realizing the lateral control of the ego vehicle.

[0073] As for the driving torque of the ego vehicle in the longitudinal control direction, it can be determined based on the existing control means, so as to control the ego vehicle in the lateral and longitudinal directions in combination with the driving torque and the steering wheel steering angle determined according to the method of the present application.

[0074] It is worth mentioning that the vehicle control method of the present application can be used in the driving process and parking process of the ego vehicle, and is not limited to one of the driving process or the parking process of the ego vehicle.

[0075] In the embodiment, the target path point and the related path point corresponding to the target path point are determined from the planned path of the ego vehicle, and then the heading angle proportion coefficient is determined according to the curvature at the related path point in the planned path and the vehicle speed of the ego vehicle, thereby realizing the real-time adjustment of the heading angle proportion coefficient according to the curvature at the related path point and the vehicle speed of the ego vehicle. The heading angle proportion coefficient is related to the real-time driving process of the ego vehicle, the accuracy of the heading angle proportion coefficient is high, so that the heading angle deviation feedback control amount determined according to the heading angle proportion coefficient has high accuracy, the accuracy of the control of the ego vehicle based on the heading angle deviation feedback control amount is improved, and the occurrence of the situation such as the ego vehicle shaking caused by the low accuracy of the heading angle deviation feedback control amount determined by using the fixed heading angle proportion coefficient and the low accuracy of the control of the ego vehicle is greatly reduced, thereby effectively improving the user experience of the intelligent driving control function of the vehicle.

[0076] Meanwhile, in the embodiment, specific means for determining the heading angle proportion coefficient are also proposed, so that the accuracy of the determined heading angle proportion coefficient is further improved, thereby further improving the accuracy of the control of the ego vehicle.

[0077] In an embodiment, as Figure 3As shown, S140 can include:

[0078] S210, determining a lateral distance deviation according to the pose information of the ego vehicle and the path point information of the target path point.

[0079] The distance deviation in the lateral direction can be determined as the lateral distance deviation based on the pose information of the ego vehicle and the path point information of the target path point.

[0080] Specifically, the position difference between the ego vehicle and the target path point can be determined based on the position information in the pose information of the ego vehicle and the position information in the path point information of the target path point; and the position difference is projected on the lateral direction of the ego vehicle according to the expected heading angle in the path point information of the target path point to obtain the lateral distance deviation.

[0081] For example, the position information of the ego vehicle can be (x a , y a ), and the position information of the target path point can be (x rn , y rn ), at this time, the position difference between the ego vehicle and the target path point can include the difference in the x direction (x rn -x a ) and the difference in the y direction (y rn -y a ), and then the position difference between the ego vehicle and the target path point is projected on the lateral direction of the ego vehicle based on Formula Five to obtain the lateral distance deviation e dist , and Formula Five is as follows:

[0082]

[0083] S220, determining a lateral distance deviation feedback control amount of the ego vehicle based on the lateral distance deviation, a preset lateral distance proportion coefficient, a preset lateral distance integral coefficient, and a preset lateral distance differential coefficient.

[0084] The lateral distance deviation feedback control amount is used to indicate the angle of the steering wheel of the ego vehicle when correcting the deviation of the lateral distance of the ego vehicle; in other words, after the ego vehicle controls the steering wheel to rotate according to the lateral distance deviation feedback control amount of the ego vehicle, the deviation of the lateral distance of the ego vehicle is eliminated.

[0085] In this embodiment, the lateral distance deviation feedback controller can determine the lateral distance deviation feedback control amount of the ego vehicle according to the lateral distance deviation, a preset lateral distance proportional coefficient, a preset lateral distance integral coefficient, and a preset lateral distance differential coefficient. The preset lateral distance proportional coefficient, the preset lateral distance integral coefficient, and the preset lateral distance differential coefficient are values that can be set based on requirements, and the application does not make any constraints. In different driving conditions, the preset lateral distance proportional coefficient, the preset lateral distance integral coefficient, and the preset lateral distance differential coefficient are fixed and unchanged.

[0086] The lateral distance deviation feedback controller and the heading angle deviation feedback controller are both objective manifestations of the performance of the lateral control of the ego vehicle, and the two are strongly coupled. Therefore, the lateral control needs to take both into account when designing. However, in the actual driving process, especially in the parking process, the performance of the heading angle deviation is more obvious than that of the lateral distance deviation. Therefore, the lateral distance deviation feedback controller uses fixed coefficients (i.e., fixed lateral distance proportional coefficient, fixed lateral distance integral coefficient, and fixed lateral distance differential coefficient), and the heading angle deviation feedback controller uses fixed heading angle integral coefficient, fixed heading angle differential coefficient, and real-time adjusted heading angle proportional coefficient.

[0087] In this embodiment, the lateral distance deviation feedback controller can be a PID (Proportion Integration Differentiation) controller, that is, the lateral distance deviation feedback controller performs proportion-integration-differentiation operation according to the lateral distance deviation, a preset lateral distance proportional coefficient, a preset lateral distance integral coefficient, and a preset lateral distance differential coefficient, and the operation result is the lateral distance deviation feedback control amount of the ego vehicle.

[0088] The lateral distance deviation feedback controller determines the lateral distance deviation feedback control amount of the ego vehicle based on the lateral distance deviation e dist The proportion-integration-differentiation operation process refers to Formula Six, which is as follows:

[0089]

[0090] wherein u dist (t) is the lateral distance deviation feedback control amount, K p―dist is the preset lateral distance proportional coefficient, K I―dist is the preset lateral distance integral coefficient, and K d―dist is the preset lateral distance differential coefficient, and t is the planning time point at which the target path point is located; and ∫e dist (t)dt is the integral (i.e., cumulative lateral distance deviation) of the lateral distance deviation at each planning time point before the planning time point t in the planning period in which the planning time point t is located. a lateral distance deviation change rate corresponding to the planning moment t (generally, a difference between the lateral distance deviation at the planning moment t and the lateral distance deviation at the planning moment t-1).

[0091] As shown in the above Formula Six, the lateral distance deviation feedback controller is actually a weighted sum of the lateral distance deviation, the accumulated lateral distance deviation, and the lateral distance deviation change rate, wherein the weight of the lateral distance deviation is the lateral distance proportional coefficient, the weight of the accumulated lateral distance deviation is the lateral distance integral coefficient, and the weight of the lateral distance deviation change rate is the lateral distance differential coefficient.

[0092] S230, determining a feedforward calibration quantity according to the curvature at the target path point in the planning path.

[0093] The feedforward calibration quantity is used to indicate an ideal steering wheel angle of the ego vehicle when the ego vehicle drives to the target path point according to the planning path. Generally, in an ideal state, the ego vehicle drives according to the planning path. If the ego vehicle drives to the target path point according to the planning path, the steering wheel angle of the ego vehicle at the target path point is obtained as the ideal steering wheel angle of the ego vehicle.

[0094] In some embodiments, a target correspondence relationship of the ego vehicle can be obtained. The target correspondence relationship is used to indicate a correspondence relationship between a calibrated steering wheel angle of the steering wheel and a calibrated curvature. Based on the target correspondence relationship, a calibrated steering wheel angle corresponding to the curvature at the target path point in the planning path is determined as the feedforward calibration quantity.

[0095] Different vehicles have different structures, and therefore, the target correspondence relationship can be different. Vehicles of the same vehicle type have the same structure, and therefore, the target correspondence relationship of the vehicles of the same vehicle type can be the same. The target correspondence relationship can be expressed in the form of a curve or a table. The target correspondence relationship involves two quantities, the steering wheel angle and the curvature. A plurality of calibrated steering wheel angles can be set for the steering wheel of the ego vehicle based on requirements. For each calibrated steering wheel angle, a respective curvature is determined as a calibrated curvature corresponding to the respective calibrated steering wheel angle. According to the calibrated steering wheel angles and the calibrated curvatures corresponding to the calibrated steering wheel angles, a curve or a table is drawn to obtain the target correspondence relationship.

[0096] After the target correspondence relationship is obtained, a calibrated steering wheel angle corresponding to the curvature at the target path point in the planning path can be determined from the target correspondence relationship as the feedforward calibration quantity.

[0097] S240, determining a steering wheel angle of the steering wheel of the ego vehicle based on the heading angle deviation feedback control quantity, the lateral distance deviation feedback control quantity, and the feedforward calibration quantity.

[0098] Exemplarily, the heading angle deviation feedback control amount, the lateral distance deviation feedback control amount and the feedforward calibration amount can be superimposed to obtain a superimposed result, and the superimposed result is used as the steering wheel rotation angle. The superimposition method includes, but is not limited to, summation, weighted summation, etc.

[0099] S250, controlling the ego vehicle according to the steering wheel rotation angle.

[0100] After obtaining the steering wheel rotation angle, the steering wheel rotation angle can be transmitted to an actuator EPS (Electronic Power Steering) in the ego vehicle, and the actuator EPS in the ego vehicle controls the ego vehicle based on the steering wheel rotation angle to realize lateral control of the ego vehicle.

[0101] The vehicle control process of the embodiment is shown in Figure 4 The target path point is determined from the planned path of the ego vehicle, and then the related path point is selected based on the target path point. At the same time, the lateral distance deviation and the heading angle deviation are determined according to the path point information of the target path point and the pose information of the ego vehicle. Then, the heading angle proportionality coefficient is determined according to the speed of the ego vehicle and the curvature of the related path point. The heading angle deviation feedback control amount and the lateral distance deviation feedback control amount are determined. Finally, in the vehicle control stage, the feedforward calibration amount is obtained, and the steering wheel rotation angle is output to the actuator (i.e., the aforementioned EPS) based on the feedforward calibration amount, the heading angle deviation feedback control amount and the lateral distance deviation feedback control amount, and the vehicle control is realized by the actuator.

[0102] In the embodiment, the heading angle proportionality parameter is adjusted in real time in the lateral control direction of the ego vehicle, so that the heading angle proportionality parameter is related to the driving condition of the ego vehicle, and the heading angle proportionality parameter is accurate. Therefore, the heading angle deviation feedback control amount determined according to the heading angle proportionality parameter is more accurate, and the accuracy of the determined steering wheel rotation angle is improved, thereby effectively reducing the occurrence of the ego vehicle shaking caused by large tracking deviation and heading angle exceeding the adjustment range, and improving the user experience of the vehicle intelligent driving function.

[0103] Referring to the accompanying Figure 5 , Figure 5 A structural block diagram of a vehicle control device according to an embodiment of the present application is shown. The device 800 for a vehicle includes:

[0104] A first determination module 810 is configured to determine a target path point and a related path point corresponding to the target path point from a planned path of an ego vehicle according to pose information of the ego vehicle.

[0105] A coefficient determination module 820 is configured to determine a heading angle proportionality coefficient according to a curvature at the related path point in the planned path and a speed of the ego vehicle.

[0106] The second determining module 830 is configured to determine a heading angle deviation feedback control amount of the ego vehicle according to the path point information of the target path point, the heading angle proportion coefficient, the preset heading angle integral coefficient, and the preset heading angle differential coefficient. The heading angle deviation feedback control amount is used to indicate an angle of a steering wheel of the ego vehicle to be corrected when a deviation of a heading angle of the ego vehicle is corrected.

[0107] The control module 840 is configured to control the ego vehicle according to the heading angle deviation feedback control amount.

[0108] Optionally, the related path points include a first related path point and a second related path point. The coefficient determining module 820 is further configured to determine an adjustment coefficient according to a vehicle speed of the ego vehicle and a calibration constant. The adjustment coefficient is positively correlated with the vehicle speed of the ego vehicle. An adjustment amplitude is determined based on a curvature difference between a curvature at the first related path point and a curvature at the second related path point in the planned path. The adjustment amplitude is positively correlated with the curvature difference. The heading angle proportion coefficient is determined based on a sine value of the adjustment amplitude and the adjustment coefficient.

[0109] Optionally, the second determining module 830 is further configured to determine a heading angle deviation according to a difference between an expected heading angle in the path point information of the target path point and an actual heading angle in the pose information of the ego vehicle. The heading angle deviation feedback control amount is determined based on the heading angle deviation, the heading angle proportion coefficient, the heading angle integral coefficient, and the heading angle differential coefficient.

[0110] Optionally, the planned path includes a plurality of path points in sequence. The related path points include a first related path point and a second related path point. The first determining module 810 is further configured to determine, from the plurality of path points, a path point with a minimum distance difference from the ego vehicle as the target path point according to the pose information of the ego vehicle. The first determining module 810 is further configured to determine, from the plurality of path points, a first path point after the target path point as the first related path point. The first determining module 810 is further configured to determine, from the plurality of path points, a second path point after the target path point as the second related path point.

[0111] Optionally, the control module 840 is further configured to determine a lateral distance deviation according to the pose information of the ego vehicle and the path point information of the target path point. The lateral distance deviation feedback control amount of the ego vehicle is determined based on the lateral distance deviation, a preset lateral distance proportion coefficient, a preset lateral distance integral coefficient, and a preset lateral distance differential coefficient. The lateral distance deviation feedback control amount is used to indicate an angle of a steering wheel of the ego vehicle to be corrected when a deviation of a lateral distance of the ego vehicle is corrected. A feedforward calibration amount is determined according to a curvature at the target path point in the planned path. The feedforward calibration amount is used to indicate an ideal steering wheel turning angle of the ego vehicle when the ego vehicle travels to the target path point according to the planned path. A steering wheel turning angle of the steering wheel of the ego vehicle is determined based on the heading angle deviation feedback control amount, the lateral distance deviation feedback control amount, and the feedforward calibration amount. The ego vehicle is controlled according to the steering wheel turning angle.

[0112] Optionally, the control module 840 is further configured to determine a position difference between the ego vehicle and the target path point based on position information in the ego vehicle's pose information and position information in the target path point's path point information; and project the position difference on a lateral direction of the ego vehicle to obtain a lateral distance deviation according to an expected heading angle in the target path point's path point information.

[0113] Optionally, the control module 840 is further configured to obtain a target correspondence relationship for the ego vehicle; the target correspondence relationship is used to indicate a correspondence relationship between a calibrated steering wheel angle and a calibrated curvature of the steering wheel; and determine, based on the target correspondence relationship, a calibrated steering wheel angle corresponding to the curvature at the target path point in the planned path as the feedforward calibration quantity.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and module can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0115] In addition, each function in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. The above integrated module can be realized in the form of hardware or in the form of a software functional module.

[0116] In addition, each function in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. The above integrated module can be realized in the form of hardware or in the form of a software functional module.

[0117] In addition, each function in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. The above integrated module can be realized in the form of hardware or in the form of a software functional module.

[0118] On the other hand, the present application also provides a computer readable storage medium, the computer readable storage medium stores program code, the program code can be called and executed by a processor to execute the method described in the foregoing method embodiments.

[0119] The computer-readable storage medium can be an electronic, magnetic, optical, or other physical storage device that contains or stores a programmable code that can be read by a computer. The computer-readable storage medium can be a non-transitory computer-readable storage medium. The computer-readable storage medium can have a storage space that stores program codes for performing any of the method steps described above. The program codes can be read from or written to one or more computer program products. The program codes can be compressed in an appropriate form, for example.

[0120] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same. Although the present application has been described in detail with reference to the foregoing examples, those skilled in the art will understand that the technical solutions described in the foregoing examples can still be modified, or some of the technical features can be replaced by equivalent features. Such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle control method characterized by, The method comprises: determining a target path point and a related path point corresponding to the target path point from a planned path of the ego vehicle according to pose information of the ego vehicle; the related path point comprises a first related path point and a second related path point; determining an adjustment coefficient according to a vehicle speed of the ego vehicle and a calibration constant; the adjustment coefficient is positively correlated with the vehicle speed of the ego vehicle; determining an adjustment amplitude based on a curvature difference between a curvature at the first related path point and a curvature at the second related path point in the planned path; the adjustment amplitude is positively correlated with the curvature difference; determining a heading angle proportion coefficient based on a sine value of the adjustment amplitude and the adjustment coefficient; determining a heading angle deviation feedback control amount of the ego vehicle according to path point information of the target path point, the heading angle proportion coefficient, a preset heading angle integral coefficient and a preset heading angle differential coefficient; the heading angle deviation feedback control amount is used to indicate an angle of a steering wheel of the ego vehicle to be corrected when a deviation of a heading angle of the ego vehicle is corrected; controlling the ego vehicle according to the heading angle deviation feedback control amount.

2. The method of claim 1, wherein, The determining of the heading angle deviation feedback control amount of the ego vehicle according to the path point information of the target path point, the heading angle proportion coefficient, the preset heading angle integral coefficient and the preset heading angle differential coefficient comprises: determining a heading angle deviation according to a difference between an expected heading angle in the path point information of the target path point and an actual heading angle in the pose information of the ego vehicle; determining a heading angle deviation feedback control amount based on the heading angle deviation, the heading angle proportion coefficient, the heading angle integral coefficient and the heading angle differential coefficient.

3. The method of claim 1, wherein, The planned path comprises a plurality of path points in sequence; The determining of the target path point and the related path point corresponding to the target path point from the planned path of the ego vehicle according to the pose information of the ego vehicle comprises: determining a path point with a minimum distance difference from the ego vehicle as the target path point from the plurality of path points according to the pose information of the ego vehicle; determining a first path point after the target path point as the first related path point from the plurality of path points; determining a second path point after the target path point as the second related path point from the plurality of path points.

4. The method of claim 1, wherein, The controlling of the ego vehicle according to the heading angle deviation feedback control amount comprises: determining a lateral distance deviation according to the pose information of the ego vehicle and the path point information of the target path point; determining a lateral distance deviation feedback control amount of the ego vehicle based on the lateral distance deviation, a preset lateral distance proportion coefficient, a preset lateral distance integral coefficient and a preset lateral distance differential coefficient; the lateral distance deviation feedback control amount is used to indicate an angle of a steering wheel of the ego vehicle to be corrected when a deviation of a lateral distance of the ego vehicle is corrected; determining a feedforward calibration amount according to a curvature at the target path point in the planned path; the feedforward calibration amount is used to indicate an ideal steering wheel turning angle of the ego vehicle when the ego vehicle travels to the target path point according to the planned path; determine a steering wheel rotation angle of a steering wheel of the ego vehicle based on the heading angle deviation feedback control quantity, the lateral distance deviation feedback control quantity, and the feedforward calibration quantity; control the ego vehicle according to the steering wheel rotation angle.

5. The method of claim 4, wherein, The determining the lateral distance deviation based on the pose information of the ego vehicle and the path point information of the target path point comprises: determining a position difference between the ego vehicle and the target path point based on position information in the pose information of the ego vehicle and position information in the path point information of the target path point; projecting the position difference on a lateral direction of the ego vehicle to obtain the lateral distance deviation according to an expected heading angle in the path point information of the target path point.

6. The method of claim 4, wherein, The determining the feedforward calibration quantity according to the curvature at the target path point in the planned path comprises: obtaining a target correspondence relationship for the ego vehicle; the target correspondence relationship is used to indicate a correspondence relationship between a calibration steering wheel rotation angle and a calibration curvature of the steering wheel; determining a calibration steering wheel rotation angle corresponding to the curvature at the target path point in the planned path as the feedforward calibration quantity based on the target correspondence relationship.

7. A vehicle control device characterized by comprising: The device comprises: a first determining module configured to determine a target path point and a related path point corresponding to the target path point from a planned path of an ego vehicle according to pose information of the ego vehicle; the related path point comprises a first related path point and a second related path point; a coefficient determining module configured to determine an adjustment coefficient according to a speed of the ego vehicle and a calibration constant; the adjustment coefficient is positively correlated with the speed of the ego vehicle; determine an adjustment amplitude based on a curvature difference between a curvature at the first related path point and a curvature at the second related path point in the planned path; the adjustment amplitude is positively correlated with the curvature difference; determine a heading angle proportion coefficient based on a sine value of the adjustment amplitude and the adjustment coefficient; a second determining module configured to determine a heading angle deviation feedback control quantity of the ego vehicle according to path point information of the target path point, the heading angle proportion coefficient, a preset heading angle integral coefficient, and a preset heading angle differential coefficient; the heading angle deviation feedback control quantity is used to indicate an angle corrected for a steering wheel of the ego vehicle when correcting a deviation of a heading angle of the ego vehicle; a control module configured to control the ego vehicle according to the heading angle deviation feedback control quantity.

8. A vehicle characterized by comprising: comprise: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores processor-executable program code, and the processor-executable program code, when executed by the processor, causes the processor to perform the method according to any one of claims 1-6.

Images