Vehicle control method and device, electronic equipment and vehicle

Abstract

The embodiment of the invention provides a vehicle control method and device, electronic equipment and a vehicle. A first planned path corresponding to a rear axle of the vehicle is obtained according to an initial planned path of the vehicle, and obstacle information around the vehicle is obtained; determining a second planned path corresponding to the front end of the vehicle according to the first planned path; according to the obstacle information, determining the minimum projection distance between the obstacle and the first planning path and the minimum projection distance between the obstacle and the second planning path; determining a comprehensive distance between the obstacle and the initial planning path according to the displacement of the obstacle relative to the first planning path and the minimum projection distance; and controlling the vehicle to run according to the corresponding acceleration or the corresponding braking parameters according to the comprehensive distance. According to the embodiment of the invention, the comprehensive influence of the vehicle contour and the obstacle on the planned path can be fully considered while the demand for computing resources is reduced, and the output and response efficiency of the vehicle control instruction is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle control method, device, electronic device, and vehicle. Background Technology

[0002] In autonomous driving systems, the trajectory planning module and control module typically employ a layered design, with trajectory planning and control functions belonging to the decision-making and planning system and the motion control system, respectively. Trajectory planning is further divided into path planning and speed planning, while motion control includes lateral control and longitudinal control. Speed ​​planning calculates safe driving speeds in complex dynamic environments. The longitudinal controller calculates torque and braking commands based on the speed planning results, and then the drive-by-wire chassis in the motion control system executes the control commands to achieve vehicle speed control.

[0003] In recent years, with the deepening of research on autonomous driving technology, researchers have gradually recognized the advantages and necessity of combining planning and control, thus giving rise to various integrated planning and control design methods. However, most existing integrated planning and control methods have some limitations, such as not fully considering the impact of obstacles on the path, ignoring the influence of vehicle contours, and having high requirements for computing resources. Summary of the Invention

[0004] This application provides a vehicle control method, apparatus, electronic device, and vehicle, which aims to solve or partially solve the above-mentioned technical problems.

[0005] To address the aforementioned problems, this application discloses a vehicle control method, wherein the vehicle includes a rear axle and a front end, and the method includes: Based on the initial planned path of the vehicle, obtain the first planned path corresponding to the rear axle of the vehicle, and obtain the obstacle information around the vehicle; Determine the second planned path corresponding to the front end of the vehicle based on the first planned path; Based on the obstacle information, determine the minimum projected distance between the obstacle and the first planned path and the second planned path, respectively; Based on the displacement of the obstacle relative to the first planned path and the minimum projection distance, determine the comprehensive distance between the obstacle and the initial planned path; The vehicle is controlled to travel at the corresponding acceleration or according to the corresponding braking parameters based on the comprehensive distance.

[0006] This application's embodiments calculate a second planned path for the vehicle's front end based on a first planned path for the rear axle, and evaluate the impact of obstacles on vehicle control based on the first and second planned paths, thus comprehensively considering the influence of vehicle contours and obstacles on the driving path. By determining the minimum projected distances between obstacles and the first and second planned paths respectively, and based on the displacement of the obstacle relative to the first planned path and the minimum projected distance, the comprehensive distance between the obstacle and the initial planned path is determined. This achieves unified processing of obstacle distance calculations in straight and curved paths. Furthermore, the vehicle is directly controlled based on this comprehensive distance, reducing the consumption of computing resources. The technical solution of this application's embodiments can reduce the demand for computing resources while fully considering the comprehensive influence of vehicle contours and obstacles on the planned path, improving the efficiency of vehicle control command output and response, and fully leveraging the performance advantages of the planning and control modules.

[0007] Optionally, controlling the vehicle to travel at a corresponding acceleration or according to corresponding braking parameters based on the comprehensive distance includes: Obtain the vehicle's current speed and the vehicle's current distance from the destination of the planned path; Identify the target obstacle with the smallest overall distance from the initial planned path, and use the overall distance corresponding to the target obstacle as the minimum overall distance; The control command for the vehicle is determined based on the minimum combined distance, the current vehicle speed, and the destination distance; According to the control command, the vehicle is controlled to travel at the corresponding acceleration or according to the corresponding braking parameters.

[0008] This application embodiment unifies the collision and non-collision scenarios based on the comprehensive distance of obstacles. During vehicle control, only the obstacle with the smallest comprehensive distance is considered, so that the control command determined based on the minimum comprehensive distance can take into account driving efficiency, safety and ride comfort. This not only makes the vehicle driving process smoother and gentler, but also further reduces the consumption of computing resources.

[0009] Optionally, the control command includes a first braking command and a torque command, wherein the first braking command is used to control the vehicle to brake according to a corresponding acceleration, and the torque command is used to control the current speed of the vehicle; The step of determining the vehicle's control command based on the minimum combined distance, the current vehicle speed, and the destination distance includes: Obtain a safe parking distance, which is the distance required for the vehicle to safely complete the parking brake; If the destination distance is greater than the safe parking distance, then the acceleration command corresponding to the vehicle is calculated based on the minimum comprehensive distance, the current vehicle speed, and the destination distance; The first braking command and the torque command are determined based on the acceleration command.

[0010] The embodiments of this application directly calculate the vehicle's acceleration command based on the minimum comprehensive distance, current vehicle speed, and destination distance, and then convert the acceleration command into the first braking command and torque command. The process is simple and reliable, with extremely low computational resource consumption. At the same time, it avoids the need for longitudinal replanning, making the command output smoother. The characteristics of chassis delay response are fully incorporated into the planning module, which helps to improve the planning and response efficiency of control commands.

[0011] Optionally, after obtaining the safe parking distance, the method further includes: If the destination distance is less than or equal to the safe stopping distance, query the braking distance corresponding to the current vehicle speed; A second braking command is determined based on the braking distance, and the second braking command is used to control the vehicle to brake.

[0012] This application embodiment only retains parking control when approaching the finish line, and realizes braking and parking control at the end through the control module. This significantly simplifies the design of control parameters, improves design efficiency, and makes the function of the control module more concise. By making full use of the high-frequency calculation advantage of the control module, the accuracy of parking control is further improved, thereby giving full play to the performance advantages of the planning module and the control module.

[0013] Optionally, the vehicle has a corresponding vehicle coordinate system, and the step of obtaining the first planned path corresponding to the rear axle of the vehicle based on the initial planned path of the vehicle, and obtaining obstacle information around the vehicle, includes: Obtain the parking area of ​​the vehicle, the initial planned path of the vehicle, and the initial obstacle information of the obstacles to be screened around the vehicle; The obstacles to be screened are obtained by filtering the parking area; The initial first planning path corresponding to the rear axle of the vehicle is determined based on the initial planning path of the vehicle. The initial first planned path and the initial obstacle information corresponding to the obstacle are respectively converted to the vehicle coordinate system to obtain the first planned path corresponding to the rear axle of the vehicle and the initial obstacle information in the vehicle coordinate system; The initial obstacle information in the vehicle coordinate system is subjected to contour processing to determine the obstacle information around the vehicle.

[0014] This application embodiment only processes obstacles located within the vehicle parking area, effectively reducing computational overhead. By converting the first planned path and obstacle information to the vehicle coordinate system, it provides data support for subsequent planning calculations related to vehicle control.

[0015] Optionally, the initial obstacle information in the vehicle coordinate system includes the length and width of the obstacle, and the step of performing contour processing on the initial obstacle information in the vehicle coordinate system to determine the obstacle information around the vehicle includes: The length and width of the obstacle are expanded to obtain the target bounding box of the obstacle. The location information of the target bounding box of the obstacle is used as the obstacle information around the vehicle.

[0016] This application embodiment expands the outline of the obstacle and determines the obstacle position in the vehicle coordinate system based on the target bounding box of the obstacle, thereby ensuring that the impact of the obstacle on the planned path is fully considered in subsequent processing.

[0017] Optionally, before determining the minimum projected distance between the obstacle and the first planned path and the second planned path respectively based on the obstacle information, the method includes: Obtain the obstacle location distance threshold; Determine a first positional relationship between the obstacle and the first planned path, and a second positional relationship between the obstacle and the second planned path; The obstacle information corresponding to the first positional relationship that does not satisfy the obstacle position distance threshold and / or the second positional relationship that does not satisfy the obstacle position distance threshold is determined as information to be removed; Remove the information to be removed from the obstacle information around the vehicle.

[0018] In this embodiment, obstacle information of obstacles whose first positional relationship and / or second positional relationship do not meet the obstacle position distance threshold is removed and not considered in subsequent processing. Only obstacles that may affect the planned path are considered, thereby reducing the consumption of computing resources.

[0019] This application also discloses a vehicle control device, the vehicle including a rear axle and a front end, the device comprising: The information acquisition module is used to acquire the first planned path corresponding to the rear axle of the vehicle based on the initial planned path of the vehicle, and to acquire obstacle information around the vehicle. The path determination module is used to determine the second planned path corresponding to the front end of the vehicle based on the first planned path. An information calculation module is used to determine, based on the obstacle information, the minimum projected distance between the obstacle and the first planned path and the second planned path, respectively; A distance determination module is used to determine the comprehensive distance between the obstacle and the initial planned path based on the displacement of the obstacle relative to the first planned path and the minimum projection distance; The instruction determination module is used to control the vehicle to travel at the corresponding acceleration or according to the corresponding braking parameters based on the comprehensive distance.

[0020] This application also discloses an electronic device, including a processor and a memory, wherein the memory is used to store computer programs; and the processor is used to execute the programs stored in the memory to implement one or more vehicle control methods as described in the embodiments of this application.

[0021] This application also discloses a vehicle that includes electronic devices as described in the embodiments of this application. Attached Figure Description

[0022] Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the planned path and obstacles of a vehicle control method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the Frenet coordinate system and obstacles for a vehicle control method provided in an embodiment of this application; Figure 4 This is a schematic diagram of obstacle handling in a vehicle control method provided in an embodiment of this application; Figure 5 This is a planning and control flowchart of a vehicle control method provided in one embodiment of this application; Figure 6 This is a structural diagram of the vehicle control device provided in the embodiments of this application; Figure 7 This is a structural diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] In autonomous driving systems, trajectory planning and control modules typically employ a layered design, with trajectory planning and control functions belonging to the decision-making and planning system and the motion control system, respectively. Trajectory planning is further divided into path planning and speed planning, while motion control includes lateral and longitudinal control. Speed ​​planning calculates safe driving speeds in complex dynamic environments. The longitudinal controller calculates torque and braking commands based on the speed planning results, and the drive-by-wire chassis in the motion control system executes the control commands to achieve vehicle speed control. However, related technologies generally do not consider the delay, dead zone, dynamic response, and road surface smoothness of the chassis actuators during speed planning calculations. These unconsidered factors often significantly impact longitudinal control performance in real-world scenarios.

[0025] In recent years, with the deepening of research on autonomous driving technology, researchers have gradually recognized the advantages and necessity of combining planning and control, thus giving rise to various integrated planning and control design methods. Existing solutions can be broadly categorized as follows, along with their corresponding shortcomings: T-shaped or S-shaped speed planning and smoothing algorithms: This method directly outputs the speed and acceleration information along the path based on the distance to the end point, maximum speed, acceleration / deceleration, and jerk. A smoothing algorithm is then used to further smooth the speed planning to improve comfort. However, this method does not consider the impact of obstacles on the path and consumes significant computational resources.

[0026] Obstacle distance calculation: The conventional method is to project the obstacle onto the Frenet coordinate system (road coordinate system). However, the Frenet coordinate system only corresponds to the rear axle of the vehicle, which is equivalent to treating the vehicle as a point mass. When driving on a curved path, the influence of the vehicle's outline is not considered, resulting in inaccurate projection calculation of the obstacle in the Frenet coordinate system.

[0027] Stop judgment: If an obstacle is within the stopping range during the approach of an obstacle, the vehicle stops immediately, which often results in an uncomfortable speed planning and does not take into account slowing down in advance when an obstacle is approaching.

[0028] Longitudinal trajectory tracking PID control (Proportional Integral Derivative Controller): Calculates braking and torque commands based on planned information and vehicle feedback. It has many control parameters, making parameter tuning complex. Moreover, it often triggers replanning due to large tracking errors, leading to a decrease in system performance.

[0029] Integrated horizontal and vertical planning design: Directly outputs steering, torque and braking commands, designs different performance indicators and weights, introduces constraints, and uses optimization theory to solve the problem. However, it has high requirements for computing resources and may fail to solve the problem.

[0030] In summary, most existing integrated planning and control methods have some limitations, such as not fully considering the impact of obstacles on the path, ignoring the influence of vehicle contours, inaccurate calculation of obstacle projection in the Frenet coordinate system, insufficient speed planning, easy triggering of replanning when calculating braking and torque commands, and high requirements for computing resources.

[0031] Therefore, some embodiments of this application provide a vehicle control method that unifies the calculation of obstacle distances for straight and curved driving paths, unifies collision and non-collision cases based on the comprehensive distance of obstacles, comprehensively considers the influence of vehicle outline and obstacles on path planning, and improves the accuracy of obstacle projection calculation in the Frenet coordinate system; moreover, the planning module fully considers the performance characteristics of the chassis, directly calculates acceleration commands based on path information, perception information and other information, the method is simple and reliable, consumes very few computing resources, and avoids triggering longitudinal replanning; the control module only retains parking control near the end point, simplifying the control design.

[0032] Specifically, in this embodiment, a first planned path corresponding to the rear axle of the vehicle is obtained based on the initial planned path of the vehicle, and obstacle information around the vehicle is obtained; a second planned path corresponding to the front end of the vehicle is determined based on the first planned path; the minimum projection distance between the obstacle and the first and second planned paths is determined based on the obstacle information; the comprehensive distance between the obstacle and the initial planned path is determined based on the displacement of the obstacle relative to the first planned path and the minimum projection distance; and the vehicle is controlled to drive at the corresponding acceleration or according to the corresponding braking parameters based on the comprehensive distance.

[0033] This application's embodiments calculate a second planned path for the vehicle's front end based on a first planned path for the rear axle, and evaluate the impact of obstacles on vehicle control based on the first and second planned paths, thus comprehensively considering the influence of vehicle contours and obstacles on the driving path. By determining the minimum projected distances between obstacles and the first and second planned paths respectively, and based on the displacement of the obstacle relative to the first planned path and the minimum projected distance, the comprehensive distance between the obstacle and the initial planned path is determined. This achieves unified processing of obstacle distance calculations in straight and curved paths. Furthermore, the vehicle is directly controlled based on this comprehensive distance, reducing the consumption of computing resources. The technical solution of this application's embodiments can reduce the demand for computing resources while fully considering the comprehensive influence of vehicle contours and obstacles on the planned path, improving the efficiency of vehicle control command output and response, and fully leveraging the performance advantages of the planning and control modules.

[0034] Example 1 This application provides a vehicle control method. Please refer to the following embodiments. Figure 1 This includes the following steps: S110: Obtain the first planned path corresponding to the rear axle of the vehicle based on the initial planned path of the vehicle, and obtain obstacle information around the vehicle.

[0035] In this embodiment of the application, the initial planned path of the vehicle is obtained, and the first planned path corresponding to the rear axle of the vehicle is obtained based on the initial planned path.

[0036] In this system, each vehicle has a corresponding rear axle. In path planning, the midpoint of the rear axle is typically used as a reference point to consider the vehicle's overall pose. Therefore, the first planned path corresponding to the rear axle is the planned path corresponding to the midpoint of the rear axle. By obtaining the first planned path, the vehicle's position information is further determined, thereby acquiring information about obstacles surrounding the vehicle.

[0037] Among them, the first planned path, vehicle location information, and obstacle information around the vehicle are all information in the navigation coordinate system, including information such as position and heading angle in the navigation coordinate system.

[0038] S120: Determine the second planning path corresponding to the front end of the vehicle based on the first planning path.

[0039] In this embodiment, the vehicle has a corresponding front end, i.e., the position at the very front of the vehicle body. By comprehensively considering the first planning path corresponding to the rear axle and the second planning path corresponding to the front end, this embodiment can fully consider the influence of the vehicle outline in the planning process, compared to the prior art which only considers the rear axle (i.e., treats the vehicle as a reference point).

[0040] In one embodiment, before determining the second planned path, the first planned path, vehicle position information, and obstacle information around the vehicle can be converted into the first planned path, vehicle position information, and obstacle information around the vehicle in the vehicle coordinate system. The second planned path corresponding to the front end of the vehicle in the vehicle coordinate system is then calculated based on the converted first planned path.

[0041] In one example, the second planned path corresponding to the front end of the vehicle can be calculated using the following formulas (1) and (2): (1) (2) in, , , Let be the position and heading angle of the first planned path in the vehicle coordinate system. , , Let be the position and heading angle of the second planned path in the vehicle coordinate system, and k be the k-th data point in the first planned path currently being traversed. It is the distance from the center of the rear axle to the frontmost part of the vehicle.

[0042] S130: Based on the obstacle information, determine the minimum projection distance between the obstacle and the first planned path and the second planned path, respectively.

[0043] In step S130, based on the obstacle information around the vehicle in the vehicle coordinate system, the first planned path, and the second planned path, the displacement s of each obstacle relative to the first planned path and the first projected distance between each obstacle and the first planned path are calculated. and the second projected distance between each obstacle and the second planned path In one example, the calculation can be performed according to the following formula (3): (3) in, , , , The position, heading angle, and Euclidean distance between the obstacle and the first planned path are given. , , , The position, heading angle, and Euclidean distance between the obstacle and the second planned path are given. Let x and y represent the displacement of the nearest projection point of the obstacle on the first planned path, where x and y are the positions of the obstacle in the vehicle coordinate system, and s is the displacement of the obstacle relative to the first planned path. The first projected distance is the distance between the obstacle and the first planned path. The second projected distance is the distance between the obstacle and the second planned path.

[0044] Reference Figure 2 This is a schematic diagram of the planned path and obstacles for a vehicle control method provided in an embodiment of this application.

[0045] like Figure 2 As shown, in the vehicle's coordinate system, the first projected distance between the first planned path corresponding to the rear axle of the vehicle and a certain obstacle is... The second projected distance between the second planned path corresponding to the front of the vehicle and the same obstacle is: .

[0046] The minimum projection distance is determined from the first projection distance and the second projection distance. In one embodiment, the minimum projection distance l can be determined as the one with the smaller absolute value between the first projection distance and the second projection distance. The minimum projection distance represents the projected distance from the obstacle to the vehicle's path. Accordingly, the planned path corresponding to the minimum projection distance is the target planned path, which is the planned path that is closer to the obstacle between the first planned path and the second planned path. For example, if the first projection distance is the minimum projection distance, then the first planned path is the target planned path; if the second projection distance is the minimum projection distance, then the second planned path is the target planned path.

[0047] S140: Determine the combined distance between the obstacle and the initial planned path based on the displacement of the obstacle relative to the first planned path and the minimum projected distance.

[0048] For each obstacle, after determining its displacement s relative to the first planned path and the minimum projected distance l, the obstacle's position in the Frenet coordinate system (s, The Frenet coordinate system is a universal coordinate system in the field of autonomous driving. Because it comprehensively considers both the first and second planned paths when calculating the position of obstacles in the Frenet coordinate system, it not only fully takes into account the influence of the vehicle's outline but also obtains a more accurate position of obstacles in the Frenet coordinate system compared to existing technologies.

[0049] Reference Figure 3 This is a Frenet coordinate system and obstacle diagram of a vehicle control method provided in an embodiment of this application.

[0050] Figure 3 The diagram shows the vehicle and several obstacles in the vicinity of the vehicle in the Frenet coordinate system. Figure 3 The obstacle marked "nearest" is the obstacle closest to the vehicle's trajectory.

[0051] Based on the obstacle's position in the Frenet coordinate system, the overall distance between the obstacle and the target planned path can be calculated, thus determining the overall distance between the obstacle and the initial planned path. In one example, the overall distance corresponding to the obstacle can be calculated using the following formula (4): (4) in, The lateral parking distance of the vehicle. denoted as , where is the longitudinal parking distance of the vehicle, k is the lateral distance weighting coefficient, s is the displacement of the obstacle relative to the first planned path, l is the target projection distance, and D is the comprehensive distance corresponding to the obstacle.

[0052] The lateral and longitudinal parking distances are pre-set parameters that can be adjusted according to actual needs. Similarly, setting different values ​​for 'k' assigns different weights to the lateral and longitudinal distances, which can also be adjusted as needed.

[0053] S150: Control the vehicle to travel at the corresponding acceleration or according to the corresponding braking parameters based on the comprehensive distance.

[0054] After determining the overall distance between the obstacle and the initial planned path, the vehicle can be controlled to travel at the corresponding acceleration or according to the corresponding braking parameters based on the overall distance, so that the vehicle can complete the parking operation.

[0055] This application's embodiments calculate a second planned path for the vehicle's front end based on a first planned path for the rear axle, and evaluate the impact of obstacles on vehicle control based on the first and second planned paths, thus comprehensively considering the influence of vehicle contours and obstacles on the driving path. By determining the minimum projected distances between obstacles and the first and second planned paths respectively, and based on the displacement of the obstacle relative to the first planned path and the minimum projected distance, the comprehensive distance between the obstacle and the initial planned path is determined. This achieves unified processing of obstacle distance calculations in straight and curved paths. Furthermore, the vehicle is directly controlled based on this comprehensive distance, reducing the consumption of computing resources. The technical solution of this application's embodiments can reduce the demand for computing resources while fully considering the comprehensive influence of vehicle contours and obstacles on the planned path, improving the efficiency of vehicle control command output and response, and fully leveraging the performance advantages of the planning and control modules.

[0056] Optionally, the vehicle has a corresponding vehicle coordinate system, and step S110 includes: Obtain the parking area of ​​the vehicle, the initial planned path of the vehicle, and the initial obstacle information of the obstacles to be screened around the vehicle; The obstacles to be screened are obtained by filtering the parking area; The initial first planning path corresponding to the rear axle of the vehicle is determined based on the initial planning path of the vehicle. The initial first planned path and the initial obstacle information corresponding to the obstacle are respectively converted to the vehicle coordinate system to obtain the first planned path corresponding to the rear axle of the vehicle and the initial obstacle information in the vehicle coordinate system; The initial obstacle information in the vehicle coordinate system is subjected to contour processing to determine the obstacle information around the vehicle.

[0057] In this embodiment of the application, it is necessary to screen the obstacles around the vehicle to determine the obstacles used for vehicle control calculations; and the information initially obtained is all collected in the navigation coordinate system, which needs to be converted to the vehicle coordinate system for processing.

[0058] Specifically, the system acquires the vehicle's parking area, initial planned path, and current position information in the navigation coordinate system. Based on the vehicle's position information, it can further determine the initial obstacle information of the surrounding obstacles to be screened in the navigation coordinate system. The parking area is the area where the vehicle needs to perform parking control.

[0059] Based on the location of the parking area, obstacles that are not within the parking area are removed from the list of obstacles to be screened, thus obtaining the obstacles that are within the parking area.

[0060] The initial first planned path corresponding to the rear axle of the vehicle is determined based on the vehicle's initial planned path. In one embodiment, since conventional path planning considers the vehicle's pose by taking the midpoint of the rear axle as a reference point, the vehicle's initial planned path can be directly used as the initial first planned path corresponding to the rear axle.

[0061] Next, the initial first planned path in the navigation coordinate system and the initial obstacle information corresponding to obstacles in the parking area are transformed to the vehicle coordinate system, thereby obtaining the first planned path corresponding to the rear axle of the vehicle in the vehicle coordinate system and the initial obstacle information in the vehicle coordinate system. In one embodiment, the transformation from the navigation coordinate system to the vehicle coordinate system can also be performed on the parking area.

[0062] In one example, the transformation from the navigation coordinate system to the vehicle coordinate system can be calculated using the following formula (5): (5) in, , , The vehicle's current position and heading angle in the navigation coordinate system. This provides the initial first planned path in the navigation coordinate system, initial obstacle information for obstacles within the parking area, or the position and heading angle of the parking area. , , This refers to the first planned path in the vehicle coordinate system, the initial obstacle information of obstacles within the parking area, or the position and heading angle of the parking area.

[0063] The initial obstacle information in the vehicle coordinate system is processed to determine the obstacle information around the vehicle.

[0064] This application embodiment only processes obstacles located within the vehicle parking area, effectively reducing computational overhead. By converting the first planned path and obstacle information to the vehicle coordinate system, it provides data support for subsequent planning calculations related to vehicle control.

[0065] Optionally, the initial obstacle information in the vehicle coordinate system includes the length and width of the obstacle, and the step of performing contour processing on the initial obstacle information in the vehicle coordinate system to determine the obstacle information around the vehicle includes: The length and width of the obstacle are expanded to obtain the target bounding box of the obstacle. The location information of the target bounding box of the obstacle is used as the obstacle information around the vehicle.

[0066] In this embodiment, specifically, the process of performing contour processing on the initial obstacle information in the vehicle coordinate system to obtain obstacle information around the vehicle includes the following steps: Based on the size and orientation information of the obstacle, the length and width of the obstacle are expanded to obtain the target bounding box corresponding to the expanded obstacle. The four edges of the target bounding box described by the expanded obstacle are traversed to calculate the edge position of the outer contour of the expanded obstacle, thereby obtaining the obstacle information around the vehicle in the vehicle coordinate system.

[0067] In one example, the position of the outer contour edge of the expanded obstacle can be calculated using the following formula (6): (6) in, , It is the starting point of the outer contour of the expanded obstacle. , is the endpoint of the outer contour edge of the expanded obstacle, n is the number of sampling points of the outer contour edge of the obstacle, x(k) and y(k) are the discretization sampling of the box edge of the expanded obstacle into sampling points. One edge can be discretized into multiple sampling points, and k is the sampling point currently traversed.

[0068] Reference Figure 4 This is a schematic diagram of obstacle handling in a vehicle control method provided in an embodiment of this application.

[0069] like Figure 4 As shown, sampling the target bounding box after the obstacle inflates within the parking area can yield multiple sampling points (e.g., , , , (etc.), among which, ( , This can be used as the starting point for the outer contour edge of the expanded obstacle. ( , () can be used as the endpoint of the outer contour of the expanded obstacle.

[0070] This application embodiment expands the outline of the obstacle and determines the obstacle position in the vehicle coordinate system based on the target bounding box of the obstacle, thereby ensuring that the impact of the obstacle on the planned path is fully considered in subsequent processing.

[0071] Optionally, prior to step S130, the method includes: Obtain the obstacle location distance threshold; Determine a first positional relationship between the obstacle and the first planned path, and a second positional relationship between the obstacle and the second planned path; The obstacle information corresponding to the first positional relationship that does not satisfy the obstacle position distance threshold and / or the second positional relationship that does not satisfy the obstacle position distance threshold is determined as information to be removed; Remove the information to be removed from the obstacle information around the vehicle.

[0072] In this embodiment, after determining the obstacle information around the vehicle and before performing subsequent calculations, the obstacles can be further filtered based on their positions in the vehicle coordinate system. Only obstacles that may affect the planned path and are close to the planned path are selected for subsequent calculations. The planned path includes a first planned path and a second planned path.

[0073] Obtain obstacle location distance thresholds, which can include lateral distance thresholds and longitudinal distance thresholds. The lateral distance threshold is the threshold for the lateral distance between the obstacle and the first or second planned path in the vehicle coordinate system, and the longitudinal distance threshold is the threshold for the longitudinal distance between the obstacle and the first or second planned path in the vehicle coordinate system.

[0074] In one embodiment, the lateral distance thresholds for the first planned path and the second planned path can be set to different values ​​or the same value; the longitudinal distance thresholds for the first planned path and the second planned path can also be set to different values ​​or the same value.

[0075] A first positional relationship between the obstacle's location and a first planned path, and a second positional relationship between the obstacle's location and a second planned path are determined. The first positional relationship includes the lateral and longitudinal distances between the obstacle's location and the first planned path, and the second positional relationship includes the lateral and longitudinal distances between the obstacle's location and the second planned path. Obstacle information corresponding to obstacles whose first positional relationship does not meet the obstacle location distance threshold and / or whose second positional relationship does not meet the obstacle location distance threshold is identified as information to be removed, and this information is then removed from the obstacle information list.

[0076] In one embodiment, the obstacle can be determined to be an obstacle that does not need to participate in subsequent calculations when the lateral distance between the obstacle and the first planned path in the vehicle coordinate system is greater than a lateral distance threshold, the lateral distance between the obstacle and the second planned path in the vehicle coordinate system is greater than a lateral distance threshold, the longitudinal distance between the obstacle and the first planned path in the vehicle coordinate system is greater than a longitudinal distance threshold, and / or the longitudinal distance between the obstacle and the second planned path in the vehicle coordinate system is greater than a longitudinal distance threshold. The specific settings for the first positional relationship not meeting the obstacle position distance threshold and / or the second positional relationship not meeting the obstacle position distance threshold can be set according to actual needs.

[0077] In this embodiment, obstacle information of obstacles whose first positional relationship and / or second positional relationship do not meet the obstacle position distance threshold is removed and not considered in subsequent processing. Only obstacles that may affect the planned path are considered, thereby reducing the consumption of computing resources.

[0078] Optionally, step S150 includes: Obtain the vehicle's current speed and the vehicle's current distance from the destination of the planned path; Identify the target obstacle with the smallest overall distance from the initial planned path, and use the overall distance corresponding to the target obstacle as the minimum overall distance; The control command for the vehicle is determined based on the minimum combined distance, the current vehicle speed, and the destination distance; According to the control command, the vehicle is controlled to travel at the corresponding acceleration or according to the corresponding braking parameters.

[0079] In this embodiment, to make the vehicle's driving process smoother and reduce computational resource consumption, when determining the vehicle's control command based on the comprehensive distance corresponding to the obstacle, only the target obstacle with the smallest comprehensive distance is selected for calculation. Specifically, after calculating the vehicle's speed limit information based on the minimum comprehensive distance corresponding to the target obstacle with the smallest comprehensive distance, the vehicle's control command can be subsequently determined using the vehicle's speed limit information, current speed, and the vehicle's current distance from the end point of the planned path. This allows the vehicle to be controlled to drive at the corresponding acceleration or according to the corresponding braking parameters.

[0080] In one embodiment, the vehicle speed limit information can be calculated according to the following formula (7): (7) in, The maximum speed of the vehicle when there are no obstacles. The rise time of the vehicle's brakes. The maximum deceleration of the vehicle. For the minimum combined distance, This provides the vehicle's speed limit information.

[0081] This application embodiment unifies the collision and non-collision scenarios based on the comprehensive distance of obstacles. During vehicle control, only the obstacle with the smallest comprehensive distance is considered, so that the control command determined based on the minimum comprehensive distance can take into account driving efficiency, safety and ride comfort. This not only makes the vehicle driving process smoother and gentler, but also further reduces the consumption of computing resources.

[0082] Optionally, the control command includes a first braking command and a torque command, wherein the first braking command is used to control the vehicle to brake according to a corresponding acceleration, and the torque command is used to control the current speed of the vehicle; The step of determining the vehicle's control command based on the minimum combined distance, the current vehicle speed, and the destination distance includes: Obtain a safe parking distance, which is the distance required for the vehicle to safely complete the parking brake; If the destination distance is greater than the safe parking distance, then the acceleration command corresponding to the vehicle is calculated based on the minimum comprehensive distance, the current vehicle speed, and the destination distance; The first braking command and the torque command are determined based on the acceleration command.

[0083] This application embodiment determines whether to control the vehicle to perform parking braking or to control the vehicle to perform normal driving and deceleration braking before parking based on a preset safe parking distance. The safe parking distance is the distance required for the vehicle to safely complete parking braking.

[0084] Distance to the finish line Greater than the safe parking distance If the vehicle does not need to stop at this point and should continue driving, decelerating as it approaches the destination, then the speed limit information is determined based on the minimum comprehensive distance. The corresponding acceleration command is calculated based on the speed limit information, the current speed, and the destination distance. This calculated acceleration command is sent to the control module, which can then determine the first braking command and torque command based on the acceleration command. The calculated first braking command and torque command are then sent to the vehicle chassis for execution. The first braking command controls the vehicle to brake at the corresponding acceleration, and the torque command controls the vehicle's current speed. The first braking command and torque command control the vehicle to continue driving along the planned path and decelerate as it approaches the destination. In one embodiment, the acceleration command can be converted into the first braking command and torque command using a linear interpolation table.

[0085] In one embodiment, the acceleration command can be calculated according to the following formula (8): (8) in, This is the distance to the end point of the path. Current vehicle speed , , These are the parameter tuning coefficients. This is the speed limit information for the vehicle. is the error integral, 'a' is the final acceleration command, 'k' is the index number corresponding to the current frame time, and 'k-1' is the index number corresponding to the previous frame time.

[0086] This application embodiment directly calculates the vehicle's acceleration command based on the minimum comprehensive distance, current vehicle speed, and destination distance, and then converts the acceleration command into a first braking command and a torque command. When the vehicle is not stopped, it is directly controlled based on the first braking command and the torque command. The process is simple and reliable, with extremely low computational resource consumption. At the same time, it avoids the need for longitudinal replanning, making the command output smoother. The characteristics of chassis delay response are fully incorporated into the planning module, which helps to improve the planning and response efficiency of control commands.

[0087] Optionally, after obtaining the safe parking distance, the method further includes: If the destination distance is less than or equal to the safe stopping distance, query the braking distance corresponding to the current vehicle speed; A second braking command is determined based on the braking distance, and the second braking command is used to control the vehicle to brake.

[0088] Distance to the finish line It is less than or equal to the safe parking distance When the vehicle is in motion, it can be determined that parking braking is required. Based on the vehicle's current speed and a calibrated braking distance interpolation table, the braking distance corresponding to the current speed is retrieved. A second braking command is calculated based on the braking distance corresponding to the current speed and sent to the vehicle chassis for execution. The second braking command is used to control the vehicle to brake, thereby bringing the vehicle to a stop.

[0089] This application embodiment only retains parking control when approaching the finish line, and realizes braking and parking control at the end through the control module. This significantly simplifies the design of control parameters, improves design efficiency, and makes the function of the control module more concise. By making full use of the high-frequency calculation advantage of the control module, the accuracy of parking control is further improved, thereby giving full play to the performance advantages of the planning module and the control module.

[0090] Example 2 To enable those skilled in the art to more clearly understand the vehicle control method shown in the embodiments of this application, the following describes... Figure 5 The present application provides an explanation of a vehicle control method illustrated in its embodiments.

[0091] Reference Figure 5 This is a planning and control flowchart of a vehicle control method provided in an embodiment of this application.

[0092] like Figure 5 As shown, the vehicle includes a planning module, a control module, and a chassis. Steps 501 to 508 are executed in the planning module, and steps 509 to 511 are executed in the control module.

[0093] Step 501: Update the vehicle's route information (i.e., the first planned route), location information, and perception information.

[0094] Step 502: Convert the information such as the first planned path, obstacles, and parking area to the vehicle coordinate system.

[0095] Step 503: Calculate the vehicle's front path (i.e., the second planned path).

[0096] Step 504: Sample obstacles and parking areas.

[0097] Step 505: Calculate the Frenet coordinates of the obstacle.

[0098] Step 506: Calculate the nearest composite distance (i.e., the minimum composite distance) to the obstacle.

[0099] Step 507: Calculate the acceleration command.

[0100] Step 508: Send acceleration commands to the control module.

[0101] Step 509: Determine if the current distance to the destination is less than the parking distance. If yes, proceed to step 5101; otherwise, proceed to step 5102.

[0102] Step 5101: Interpolate braking based on vehicle speed.

[0103] Step 5102: Interpolate braking and torque based on acceleration.

[0104] Step 511: Issue braking and torque commands to the chassis for execution.

[0105] This application's embodiments calculate a second planned path for the vehicle's front end based on a first planned path for the rear axle, and evaluate the impact of obstacles on vehicle control based on the first and second planned paths, thus comprehensively considering the influence of vehicle contours and obstacles on the driving path. By determining the minimum projected distances between obstacles and the first and second planned paths respectively, and based on the displacement of the obstacle relative to the first planned path and the minimum projected distance, the comprehensive distance between the obstacle and the initial planned path is determined. This achieves unified processing of obstacle distance calculations in straight and curved paths. Furthermore, the vehicle is directly controlled based on this comprehensive distance, reducing the consumption of computing resources. The technical solution of this application's embodiments can reduce the demand for computing resources while fully considering the comprehensive influence of vehicle contours and obstacles on the planned path, improving the efficiency of vehicle control command output and response, and fully leveraging the performance advantages of the planning and control modules.

[0106] This application also provides a vehicle control device 60, please refer to... Figure 6 ,include: The information acquisition module 610 is used to acquire the first planned path corresponding to the rear axle of the vehicle based on the initial planned path of the vehicle, and to acquire obstacle information around the vehicle. The path determination module 620 is used to determine the second planned path corresponding to the front end of the vehicle based on the first planned path. The information calculation module 630 is used to determine the minimum projected distance between the obstacle and the first planned path and the second planned path, respectively, based on the obstacle information; The distance determination module 640 is used to determine the comprehensive distance between the obstacle and the initial planned path based on the displacement of the obstacle relative to the first planned path and the minimum projection distance; The instruction determination module 650 is used to control the vehicle to travel at a corresponding acceleration or according to corresponding braking parameters based on the comprehensive distance.

[0107] Optionally, the instruction determining module 650 includes: The control parameter acquisition submodule is used to acquire the vehicle's current speed and the vehicle's current distance from the destination of the planned path. The minimum distance determination submodule is used to determine the target obstacle with the smallest comprehensive distance from the initial planned path, and to use the comprehensive distance corresponding to the target obstacle as the minimum comprehensive distance; The control command determination submodule is used to determine the control command of the vehicle based on the minimum comprehensive distance, the current vehicle speed, and the destination distance; The vehicle control submodule is used to control the vehicle to travel at a corresponding acceleration or according to corresponding braking parameters based on the control command.

[0108] Optionally, the control command includes a first braking command and a torque command, wherein the first braking command is used to control the vehicle to brake at a corresponding acceleration, and the torque command is used to control the current speed of the vehicle; the control command determination submodule is specifically used for: Obtain a safe parking distance, which is the distance required for the vehicle to safely complete the parking brake; If the destination distance is greater than the safe parking distance, then the acceleration command corresponding to the vehicle is calculated based on the minimum comprehensive distance, the current vehicle speed, and the destination distance; The first braking command and the torque command are determined based on the acceleration command.

[0109] Optionally, after obtaining the safe parking distance, the control command determination submodule is further configured to: If the destination distance is less than or equal to the safe stopping distance, query the braking distance corresponding to the current vehicle speed; A second braking command is determined based on the braking distance, and the second braking command is used to control the vehicle to brake.

[0110] Optionally, the vehicle has a corresponding vehicle coordinate system, and the information acquisition module 610 includes: The initial information acquisition submodule is used to acquire the parking area of ​​the vehicle, the initial planned path of the vehicle, and the initial obstacle information of the obstacles to be screened around the vehicle. The first obstacle filtering submodule is used to filter the obstacles to be filtered according to the parking area to obtain the obstacles located in the parking area; The path processing submodule is used to determine the initial first planned path corresponding to the rear axle of the vehicle based on the initial planned path of the vehicle. The coordinate transformation submodule is used to transform the initial first planned path and the initial obstacle information corresponding to the obstacle to the vehicle coordinate system, respectively, to obtain the first planned path corresponding to the rear axle of the vehicle and the initial obstacle information in the vehicle coordinate system; The obstacle processing submodule is used to perform contour processing on the initial obstacle information in the vehicle coordinate system to determine the obstacle information around the vehicle.

[0111] Optionally, the initial obstacle information in the vehicle coordinate system includes the length and width of the obstacle, and the obstacle processing submodule is specifically used for: The length and width of the obstacle are expanded to obtain the target bounding box of the obstacle. The location information of the target bounding box of the obstacle is used as the obstacle information around the vehicle.

[0112] Optionally, the device includes: The distance threshold acquisition module is used to acquire the distance threshold of the obstacle position; A positional relationship determination module is used to determine a first positional relationship between the obstacle and the first planned path, and a second positional relationship between the obstacle and the second planned path; The module for determining information to be removed is used to determine the obstacle information corresponding to the first positional relationship that does not meet the obstacle position distance threshold and / or the second positional relationship that does not meet the obstacle position distance threshold as information to be removed. The second obstacle filtering module is used to remove the information to be removed from the obstacle information around the vehicle.

[0113] This application also provides an electronic device 70, please refer to... Figure 7 It includes a processor 710 and a memory 720, wherein the memory 710 is used to store computer programs; and the processor 720 is used to execute the programs stored in the memory 710 to implement the vehicle control method described in any embodiment of this application.

[0114] This application also provides a vehicle that includes the electronic equipment described in this application.

[0115] In this application, "multiple" refers to two or more.

[0116] In this application, unless otherwise expressly defined, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0117] The terms “first,” “second,” “third,” “fourth,” etc., in this application (if present) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0118] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, in this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0119] Unless otherwise specified, all steps in this application may be performed sequentially or randomly. For example, if the method includes steps A and B, it means that the method may include steps A and B performed sequentially, or it may include steps B and A performed sequentially. For example, if the method may also include step C, it means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or it may include steps A, C, and B, or it may include steps C, A, and B, etc.

[0120] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for controlling a vehicle, characterized in that, The vehicle includes a rear axle and a front end, and the method includes: Based on the initial planned path of the vehicle, obtain the first planned path corresponding to the rear axle of the vehicle, and obtain the obstacle information around the vehicle; Determine the second planned path corresponding to the front end of the vehicle based on the first planned path; Based on the obstacle information, determine the minimum projected distance between the obstacle and the first planned path and the second planned path, respectively; Based on the displacement of the obstacle relative to the first planned path and the minimum projection distance, determine the comprehensive distance between the obstacle and the initial planned path; The vehicle is controlled to travel at the corresponding acceleration or according to the corresponding braking parameters based on the comprehensive distance.

2. The vehicle control method according to claim 1, characterized in that, The step of controlling the vehicle to travel at a corresponding acceleration or according to corresponding braking parameters based on the comprehensive distance includes: Obtain the vehicle's current speed and the vehicle's current distance from the destination of the planned path; Identify the target obstacle with the smallest overall distance from the initial planned path, and use the overall distance corresponding to the target obstacle as the minimum overall distance; The control command for the vehicle is determined based on the minimum combined distance, the current vehicle speed, and the destination distance; According to the control command, the vehicle is controlled to travel at the corresponding acceleration or according to the corresponding braking parameters.

3. The vehicle control method according to claim 2, characterized in that, The control commands include a first braking command and a torque command. The first braking command is used to control the vehicle to brake at a corresponding acceleration, and the torque command is used to control the current speed of the vehicle. The step of determining the vehicle's control command based on the minimum combined distance, the current vehicle speed, and the destination distance includes: Obtain a safe parking distance, which is the distance required for the vehicle to safely complete the parking brake; If the destination distance is greater than the safe parking distance, then the acceleration command corresponding to the vehicle is calculated based on the minimum comprehensive distance, the current vehicle speed, and the destination distance; The first braking command and the torque command are determined based on the acceleration command.

4. The vehicle control method according to claim 3, characterized in that, After obtaining the safe parking distance, the method further includes: If the destination distance is less than or equal to the safe stopping distance, query the braking distance corresponding to the current vehicle speed; A second braking command is determined based on the braking distance, and the second braking command is used to control the vehicle to brake.

5. The vehicle control method according to claim 1, characterized in that, The vehicle has a corresponding vehicle coordinate system. The steps of obtaining the first planned path corresponding to the rear axle of the vehicle based on the vehicle's initial planned path, and obtaining obstacle information around the vehicle, include: Obtain the parking area of ​​the vehicle, the initial planned path of the vehicle, and the initial obstacle information of the obstacles to be screened around the vehicle; The obstacles to be screened are obtained by filtering the parking area; The initial first planning path corresponding to the rear axle of the vehicle is determined based on the initial planning path of the vehicle. The initial first planned path and the initial obstacle information corresponding to the obstacle are respectively converted to the vehicle coordinate system to obtain the first planned path corresponding to the rear axle of the vehicle and the initial obstacle information in the vehicle coordinate system; The initial obstacle information in the vehicle coordinate system is subjected to contour processing to determine the obstacle information around the vehicle.

6. The vehicle control method according to claim 5, characterized in that, The initial obstacle information in the vehicle coordinate system includes the length and width of the obstacle. The process of contour processing of the initial obstacle information in the vehicle coordinate system to determine the obstacle information around the vehicle includes: The length and width of the obstacle are expanded to obtain the target bounding box of the obstacle. The location information of the target bounding box of the obstacle is used as the obstacle information around the vehicle.

7. The vehicle control method according to claim 6, characterized in that, Before determining the minimum projected distance between the obstacle and the first planned path and the second planned path based on the obstacle information, the method includes: Obtain the obstacle location distance threshold; Determine a first positional relationship between the obstacle and the first planned path, and a second positional relationship between the obstacle and the second planned path; The obstacle information corresponding to the first positional relationship that does not satisfy the obstacle position distance threshold and / or the second positional relationship that does not satisfy the obstacle position distance threshold is determined as information to be removed; Remove the information to be removed from the obstacle information around the vehicle.

8. A vehicle control device, characterized in that, The vehicle includes a rear axle and a front end, and the device includes: The information acquisition module is used to acquire the first planned path corresponding to the rear axle of the vehicle based on the initial planned path of the vehicle, and to acquire obstacle information around the vehicle. The path determination module is used to determine the second planned path corresponding to the front end of the vehicle based on the first planned path. An information calculation module is used to determine, based on the obstacle information, the minimum projected distance between the obstacle and the first planned path and the second planned path, respectively; A distance determination module is used to determine the comprehensive distance between the obstacle and the initial planned path based on the displacement of the obstacle relative to the first planned path and the minimum projection distance; The instruction determination module is used to control the vehicle to travel at the corresponding acceleration or according to the corresponding braking parameters based on the comprehensive distance.

9. An electronic device, characterized in that, Including processor and memory, among which Memory, used to store computer programs; A processor for executing a program stored in a memory to implement the vehicle control method according to any one of claims 1-7.

10. A vehicle, characterized in that, It includes the electronic device as described in claim 9.

Images