Parking path planning method, device, electronic device and storage medium

Abstract

The present invention relates to a parking path planning method, device, electronic device and storage medium, and relates to the field of intelligent driving technology. The method comprises: obtaining environmental perception information around a parking space to be parked, and determining the parking end point of a target vehicle in the parking space to be parked and obstacle information around the parking space to be parked according to the environmental perception information; determining a relay point set corresponding to the target vehicle based on the parking end point and obstacle information; calculating the cost value of each relay point in the relay point set, and sorting the cost value of each relay point in the relay point set, and determining candidate relay points according to the sorting result; performing path planning based on each relay point in the candidate relay points to obtain a parking path for the target vehicle. In this way, the complex parking environment can be better adapted to the path planning process and the surrounding obstacles can be avoided, so that the optimal parking path can be accurately planned, so that the parking path is closer to the actual parking demand.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a parking path planning method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous improvement of intelligent driving technology, the parking path planning ability of vehicles is also constantly improving. In related technologies, parking path planning includes geometric, sampling, graph search and other methods. However, facing the increasingly complex parking environment (such as narrow space, irregular parking layout, etc.) and the frequent appearance of dynamic obstacles, the feasibility of parking path planning is low. Summary of the invention

[0003] The present invention provides a parking path planning method, device, electronic device and storage medium to solve the problem of low feasibility of parking path planning in related technologies.

[0004] In a first aspect, an embodiment of the present invention provides a parking path planning method, the method comprising:

[0005] Acquiring environmental perception information around the parking space, and determining a parking destination of the target vehicle in the parking space and obstacle information around the parking space based on the environmental perception information;

[0006] Based on the parking end point and the obstacle information, determining a relay point set corresponding to the target vehicle, wherein the relay point set is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with obstacles;

[0007] Calculating the cost value of each relay point in the relay point set, sorting the cost value of each relay point in the relay point set, and determining a candidate relay point according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold;

[0008] Path planning is performed based on each of the candidate relay points to obtain a parking path for the target vehicle.

[0009] Optionally, the determining a set of relay points corresponding to the target vehicle based on the parking end point and the obstacle information includes:

[0010] Based on the parking end point, a plurality of sampling points are determined, wherein the plurality of sampling points and the parking end point are spaced apart along the length direction of the parking space, and each of the plurality of sampling points has a different distance from the parking end point;

[0011] Taking each sampling point of the plurality of sampling points as the origin of the coordinate system in turn, a coordinate system corresponding to each sampling point is constructed, wherein a first coordinate axis of the coordinate system corresponding to each sampling point is parallel to a width direction of the parking space, and a second coordinate axis of the coordinate system corresponding to each sampling point is parallel to a length direction of the parking space;

[0012] Determine the feasible region of the target vehicle in the coordinate system corresponding to each sampling point in sequence;

[0013] Based on the obstacle information, collision detection is performed on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn, and the relay point set is determined according to the collision detection result.

[0014] Optionally, sequentially determining the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point includes:

[0015] Obtaining the front wheel turning angle and step distance corresponding to the target vehicle in the coordinate system corresponding to each sampling point;

[0016] Based on the vehicle kinematic model, the front wheel turning angle and the stepping distance, a feasible domain of the target vehicle in the coordinate system corresponding to each sampling point is determined, wherein the feasible domain includes multiple relay point series, each relay point sequence in the multiple relay point series corresponds one-to-one to the front wheel turning angle, and each relay point in each relay point sequence corresponds one-to-one to the stepping distance.

[0017] Optionally, the calculating the cost value of each relay point in the relay point set includes:

[0018] Obtaining the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set;

[0019] Based on the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set, the initial cost value and the feasible domain cost value of each relay point in the relay point set are calculated respectively, wherein the initial cost value is the sum of the heading deviation cost value and the step distance cost value, the heading deviation cost value is proportional to the difference between the heading angle of the parking starting point and the heading angle of each relay point, the step distance cost value is inversely proportional to the step distance of each relay point, and the feasible domain cost value is inversely proportional to the feasible domain area of ​​each relay point;

[0020] The product of the initial cost value and the feasible region cost value is calculated, and the calculation result is determined as the cost value of each relay point in the relay point set.

[0021] Optionally, the calculation formula of the cost value of each relay point in the relay point set is as follows:

[0022] ;

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] in, represents the cost value of the target relay point, represents the initial cost value of the target relay point, represents the feasible domain cost value of the target relay point, represents the heading deviation cost value of the target relay point, represents the step distance cost value of the target relay point, represents the heading angle of the parking starting point, represents the heading angle of the target relay point, represents the step distance of the target relay point, Indicates the preset step distance. , , , represent the actual boundary values ​​of the feasible domain in the coordinate system where the target relay point is located, and the target relay point is any relay point in the relay point set. represents the length of the feasible region in the coordinate system where the target relay point is located, Indicates the width of the feasible region in the coordinate system where the target relay point is located.

[0028] Optionally, performing path planning based on each of the candidate relay points to obtain a parking path for the target vehicle includes:

[0029] Sorting the candidate relay points in descending order of cost value;

[0030] Traversing each of the candidate relay points in turn, and performing path planning on the currently traversed relay point to obtain a path planning result;

[0031] When the path planning result indicates that the path is valid, determining a parking path for the target vehicle based on the path planning result;

[0032] When the path planning result indicates that the path is invalid, continue to traverse the next relay point among the candidate relay points, and perform path planning for the newly traversed relay point, and repeat the process until the traversal is stopped when a preset condition is met, wherein the preset condition is that all relay points among the candidate relay points have been traversed, or a relay point with a valid path is determined from the candidate relay points.

[0033] Optionally, determining the parking path of the target vehicle based on the path planning result includes:

[0034] Determine the path obtained from the path planning result as the first path between the parking starting point and the currently traversed relay point;

[0035] Determine a second path between the currently traversed relay point and the target sampling point, wherein the target sampling point is a sampling point corresponding to the coordinate system where the currently traversed relay point is located;

[0036] Determine a third path between the target sampling point and the parking end point, wherein the third path is a straight line;

[0037] A parking path of the target vehicle is determined based on the first path, the second path, and the third path.

[0038] In a second aspect, an embodiment of the present invention further provides a parking path planning device, the device comprising:

[0039] An acquisition module, used to acquire environmental perception information around the parking space, and determine the parking end point of the target vehicle in the parking space and obstacle information around the parking space according to the environmental perception information;

[0040] A determination module, configured to determine a set of relay points corresponding to the target vehicle based on the parking end point and the obstacle information, wherein the set of relay points is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with obstacles;

[0041] a calculation and sorting module, configured to calculate a cost value of each relay point in the relay point set, sort the cost values ​​of each relay point in the relay point set, and determine a candidate relay point according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold;

[0042] A path planning module is used to perform path planning based on each relay point among the candidate relay points to obtain a parking path for the target vehicle.

[0043] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0044] Memory, used to store computer programs;

[0045] The processor is used to implement the parking path planning method described in the first aspect when executing the program stored in the memory.

[0046] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the parking path planning method described in the first aspect.

[0047] The above technical solution provided by the embodiment of the present invention has the following advantages over the prior art: the method provided by the embodiment of the present invention obtains environmental perception information around the parking space to be parked, and determines the parking end point of the target vehicle in the parking space to be parked and the obstacle information around the parking space to be parked according to the environmental perception information; determines a relay point set corresponding to the target vehicle based on the parking end point and the obstacle information, wherein the relay point set is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with obstacles; calculates the cost value of each relay point in the relay point set, sorts the cost value of each relay point in the relay point set, and determines candidate relay points according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold; performs path planning based on each relay point in the candidate relay points to obtain a parking path for the target vehicle. Through the above method, according to the parking destination of the target vehicle in the parking space and the obstacle information around the parking space, a set of relay points that are within the feasible domain of the target vehicle and do not collide with obstacles can be determined, and then path rules can be made according to the candidate relay points with lower cost in the relay point set. In this way, complex parking environments can be better adapted and surrounding obstacles can be avoided during the path planning process, thereby improving the feasibility of parking path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0051] Figure 1 A schematic diagram of a parking path planning method provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a feasible domain of a target vehicle in a coordinate system corresponding to each sampling point and a corresponding area of ​​a relay point set provided by an embodiment of the present invention;

[0053] Figure 3A A schematic diagram of a two-degree-of-freedom bicycle model provided by an embodiment of the present invention;

[0054] Figure 3B A schematic diagram of a vehicle motion model provided by an embodiment of the present invention;

[0055] Figure 4 A schematic diagram of a feasible region obtained based on a vehicle kinematic model provided in an embodiment of the present invention;

[0056] Figure 5 A schematic diagram of a parking path provided by an embodiment of the present invention;

[0057] Figure 6 A schematic diagram of a flow chart of another parking path planning method provided by an embodiment of the present invention;

[0058] Figure 7 A schematic diagram of the structure of a parking path planning device provided by an embodiment of the present invention;

[0059] Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0062] In order to solve the problem of low feasibility of parking path planning in the related art, the present invention provides a parking path planning method, device, electronic device and storage medium, which can improve the feasibility of parking path planning.

[0063] See also Figure 1 , Figure 1 A flow chart of a parking path planning method provided by an embodiment of the present invention. Figure 1 As shown, the parking path planning method may include the following steps:

[0064] Step S101: Acquire environmental perception information around the parking space, and determine the parking destination of the target vehicle in the parking space and obstacle information around the parking space based on the environmental perception information.

[0065] The above-mentioned parking space refers to the parking space where the target vehicle is to park, and the parking space may be a vertical parking space, a horizontal parking space or an irregular parking space, etc., which is not specifically limited in the present invention. The above-mentioned environmental perception information refers to the information perceived by the perception device (such as a camera, a laser radar, etc.) on the target vehicle, which may include the location and shape of the parking space, and the location, type, volume and other information of surrounding obstacles.

[0066] In this step, the environmental perception information around the parking space can be first obtained through the sensing device on the target vehicle, and then the parking end point of the target vehicle in the parking space and the obstacle information around the parking space can be determined based on the environmental perception information. The parking end point here can be understood as the optimal position of the rear axle center point of the target vehicle on the parking space after the target vehicle is parked. The parking end point can be determined by the position and shape of the parking space.

[0067] Step S102: Based on the parking end point and obstacle information, determine a relay point set corresponding to the target vehicle, wherein the relay point set is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with obstacles.

[0068] The above relay point set is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with the obstacle. The feasible domain of the target vehicle refers to the area where the target vehicle can travel when the relevant constraints of the target vehicle (such as the front wheel turning angle and the stepping distance, etc.) are met. Whether the target vehicle collides with the obstacle can be obtained through collision detection. Specifically, it can be assumed that the center of the rear axle of the target vehicle is located at a certain relay point in the feasible domain, so that the state information of the target vehicle at the relay point (such as position, heading angle, etc.) can be obtained, and then the coordinates of the four corner points of the outer contour rectangle of the target vehicle are calculated according to the state information of the target vehicle at the relay point, and then it is determined whether the area formed by the four corner point coordinates overlaps with the position of the obstacle. If the area formed by the four corner point coordinates overlaps with the position of the obstacle, there is a collision; if the area formed by the four corner point coordinates does not overlap with the position of the obstacle, there is no collision.

[0069] Step S103, calculate the cost value of each relay point in the relay point set, sort the cost value of each relay point in the relay point set, and determine the candidate relay point according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold.

[0070] In this step, after determining the relay point set corresponding to the target vehicle, the cost value of each relay point in the relay point set can be calculated using a preset cost calculation formula, wherein the lower the cost value of the relay point, the more suitable the relay point is for participating in path planning; the higher the cost value of the relay point, the less suitable the relay point is for participating in path planning. Therefore, after calculating the cost value of each relay point in the relay point set, the cost value of each relay point in the relay point set can be sorted in order from low to high, and then a preset number of relay points with a higher ranking (i.e., a preset number of relay points with a lower cost value) are selected from the relay point set as candidate relay points according to the sorting result; of course, the cost value of each relay point in the relay point set can also be sorted in order from high to low, and then a preset number of relay points with a lower ranking (i.e., a preset number of relay points with a lower cost value) are selected from the relay point set as candidate relay points according to the sorting result. Among them, the preset number here can be set according to actual needs, such as 10, 20, etc., and the present invention does not make specific restrictions.

[0071] Step S104: performing path planning on each of the candidate relay points based on a preset path planning algorithm to obtain a parking path for the target vehicle.

[0072] In this step, the path from the parking start point to a candidate relay point can be planned based on the preset path planning algorithm, and then the path from the candidate relay point to the parking end point can be planned, so as to obtain the parking path of the target vehicle. Among them, the preset path planning algorithm here can be any path planning algorithm, such as a geometry-based planning algorithm, a sampling-based planning algorithm (such as a fast random tree algorithm and its optimized version algorithm, etc.) and a graph search-based planning algorithm (such as an A* algorithm, a hybrid A* algorithm, etc.). In the above manner, according to the parking end point of the target vehicle in the parking space to be parked and the obstacle information around the parking space to be parked, a set of relay points that are within the feasible domain of the target vehicle and do not collide with obstacles can be determined, and then the path rules can be made according to the candidate relay points with lower cost values ​​in the relay point set, so that it can better adapt to complex parking environments and avoid surrounding obstacles during the path planning process, thereby improving the feasibility of parking path planning.

[0073] In some optional embodiments, the above step S102, determining a set of relay points corresponding to the target vehicle based on the parking end point and obstacle information, includes:

[0074] Based on the parking end point, a plurality of sampling points are determined, wherein the plurality of sampling points and the parking end point are spaced apart along the length direction of the parking space, and each of the plurality of sampling points has a different distance from the parking end point;

[0075] Taking each sampling point of the plurality of sampling points as the origin of the coordinate system in turn, a coordinate system corresponding to each sampling point is constructed, wherein a first coordinate axis of the coordinate system corresponding to each sampling point is parallel to the width direction of the parking space to be parked, and a second coordinate axis of the coordinate system corresponding to each sampling point is parallel to the length direction of the parking space to be parked;

[0076] Determine the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn;

[0077] Based on the obstacle information, collision detection is performed on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn, and the relay point set is determined according to the collision detection results.

[0078] In one embodiment, when determining the set of relay points corresponding to the target vehicle, multiple sampling points may be determined based on the parking end point. Figure 2 As shown, Indicates the parking starting point. Indicates the parking end point. A certain distance range can be selected in the y-axis direction (i.e., the direction parallel to the length of the parking space) for sampling to obtain multiple sampling points d1, d2, d3, ..., dn, where n represents the total number of sampling points. The total number of sampling points and the interval distance here can be set according to actual needs, such as the number of sampling points is 20, and they are set at equal distances. Then, each of the multiple sampling points is used as the origin of the coordinate system in turn. , construct the coordinate system corresponding to each sampling point, and determine the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn, then based on the obstacle information, perform collision detection on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn, and determine the relay point without collision according to the collision detection result, so as to obtain the relay point set. For example, Figure 2 As shown, it is assumed that the feasible domain on the left and the feasible domain on the right of the target vehicle in the coordinate system corresponding to each sampling point are equal, but due to the influence of the lateral obstacle vehicle A in front of the right side of the parking space, the relay point set on the right is actually smaller than the relay point set on the left.

[0079] In this way, by determining the feasible domain in the coordinate system corresponding to each sampling point, and then based on the obstacle information, collision detection is performed on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn, and the actual feasible domain in the coordinate system corresponding to each sampling point is obtained, and then the relay point set of the target vehicle is determined, so that the relay point set covers a wider range of potential parking paths, which is convenient for the subsequent accurate planning of the optimal parking path from these potential parking paths, so that the parking path is closer to the actual parking demand.

[0080] In some optional embodiments, the above steps of sequentially determining the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point include:

[0081] Obtain the front wheel turning angle and step distance of the target vehicle in the coordinate system corresponding to each sampling point;

[0082] Based on the vehicle kinematic model, the front wheel turning angle and the stepping distance, the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point is determined, wherein the feasible domain includes multiple relay point series, each relay point sequence in the multiple relay point series corresponds one-to-one to the front wheel turning angle, and each relay point in each relay point sequence corresponds one-to-one to the stepping distance.

[0083] In one embodiment, when determining the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point, the front wheel turning angle and step distance corresponding to the target vehicle in the coordinate system corresponding to each sampling point can be obtained first, and then based on the vehicle kinematic model, the front wheel turning angle and step distance, the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point can be determined. As an optional implementation, the front wheel turning angle can select the maximum front wheel turning angle allowed for the target vehicle, and the step distance can select the maximum step distance allowed for the target vehicle. In this way, the maximum feasible domain of the target vehicle in the coordinate system corresponding to each sampling point can be obtained. Specifically, during parking, since the vehicle is in a low-speed motion state, the lateral force has little effect on the steering motion of the vehicle, and thus a two-degree-of-freedom bicycle model can be used as a vehicle motion model, such as Figure 3A and Figure 3B As shown. Among them, is the vehicle front overhang length (in meters), is the vehicle rear overhang length (in meters), is the vehicle wheelbase (in m), is the vehicle width (in m), is the center of the vehicle's rear axle, is the front wheel steering angle of the vehicle (in rad), are the four vertices of the vehicle's rectangular outline, from which the following kinematic formula can be obtained:

[0084] ;

[0085] in, is the centerline speed of the vehicle's rear axle, is the vehicle heading angle, For vehicles in The change in the x-axis coordinate under For vehicles in The change in the y-axis coordinate under For vehicles in The heading angle change under is the vehicle front wheel turning angle, is the vehicle wheelbase.

[0086] According to the above kinematic formula, we can get the vehicle step distance The vehicle rear axle center status is as follows:

[0087] ;

[0088] in, represents the x-axis coordinate of the vehicle after the t-th movement, represents the y-axis coordinate of the vehicle after the t-th movement, represents the heading angle of the vehicle after the tth movement, represents the x-axis coordinate of the vehicle after the t+1th movement, represents the y-axis coordinate of the vehicle at time t+1, represents the heading angle of the vehicle at time t+1, is the step distance of the vehicle each time it moves, is the front wheel turning angle of the vehicle, is the vehicle wheelbase.

[0089] Then you can turn the front wheel Discretize it, The range is divided into N steps, and the step distance Discretize it, The range is divided into M steps, where the values ​​of N and M can be set according to the actual situation and are not limited here. Then, according to the vehicle kinematic model, the vehicle is calculated under different front wheel turning angles and different stepping distances. For the convenience of calculation, the center of the rear axle of the vehicle can be used as the origin of the coordinate system, such as Figure 4 As shown in the figure, the dotted rectangular areas on the left and right are defined as the left feasible domain and the right feasible domain respectively. The length of each feasible domain is , the width of the feasible region Each dotted arrow in the feasible domain can represent a series of relay points, and each relay point corresponds to the state value of the vehicle at that point. ,in, Represents the x-axis coordinate of the vehicle at that point, Indicates the y-axis coordinate of the vehicle at that point, represents the heading angle of the vehicle at that point, represents the front wheel turning angle of the vehicle at that point, Indicates the step distance of the vehicle at that point.

[0090] Through the above method, the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point can be accurately determined, which is convenient for subsequent collision detection based on obstacle information and obtaining a set of relay points.

[0091] In some optional embodiments, the above step S103, calculating the cost value of each relay point in the relay point set, includes:

[0092] Obtain the heading angle, step distance and feasible area of ​​each relay point in the relay point set;

[0093] Based on the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set, the initial cost value and feasible domain cost value of each relay point in the relay point set are calculated respectively, wherein the initial cost value is the sum of the heading deviation cost value and the step distance cost value, the heading deviation cost value is proportional to the difference between the heading angle of the parking starting point and the heading angle of each relay point, the step distance cost value is inversely proportional to the step distance of each relay point, and the feasible domain cost value is inversely proportional to the feasible domain area of ​​each relay point;

[0094] The product of the initial cost value and the feasible region cost value is calculated, and the calculation result is determined as the cost value of each relay point in the relay point set.

[0095] In one embodiment, when calculating the cost value of each relay point in the relay point set, the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set can be obtained first, and then based on the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set, the initial cost value and feasible domain cost value of each relay point in the relay point set are calculated respectively. The initial cost value here can be the sum of the heading deviation cost value and the step distance cost value, wherein the heading deviation cost value is proportional to the difference between the heading angle of the parking starting point and the heading angle of each relay point, that is, the greater the difference between the heading angle of the parking starting point and the heading angle of each relay point, the greater the heading deviation cost value; the smaller the difference between the heading angle of the parking starting point and the heading angle of each relay point, the smaller the heading deviation cost value. The step distance cost value is inversely proportional to the step distance of each relay point, that is, the larger the step distance of each relay point, the smaller the step distance cost value; the smaller the step distance of each relay point, the larger the step distance cost value. The feasible domain cost value is inversely proportional to the feasible domain area of ​​each relay point, that is, the larger the feasible domain area of ​​each relay point, the smaller the feasible domain cost value; the smaller the feasible domain area of ​​each relay point, the larger the feasible domain cost value. Finally, calculate the product of the initial cost value and the feasible domain cost value, and determine the calculation result as the cost value of each relay point in the relay point set.

[0096] Through the above method, the influence of the heading angle, step distance and feasible domain area of ​​each relay point on the cost value of each relay point can be comprehensively considered, so that the cost value of each relay point is more accurate and closer to the actual parking path planning requirements.

[0097] In some optional embodiments, the calculation formula of the cost value of each relay point in the relay point set is as follows:

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] ;

[0103] in, represents the cost value of the target relay point, represents the initial cost value of the target relay point, represents the feasible domain cost value of the target relay point, Indicates the heading deviation cost value of the target relay point, Indicates the step distance cost value of the target relay point, Indicates the heading angle of the parking starting point, Indicates the heading angle of the target relay point, Indicates the step distance of the target relay point, Indicates the preset step distance. , , , They represent the actual boundary values ​​of the feasible domain in the coordinate system where the target relay point is located. The target relay point is any relay point in the relay point set. Indicates the length of the feasible region in the coordinate system where the target relay point is located, Indicates the width of the feasible region in the coordinate system where the target relay point is located.

[0104] According to the above formula, the heading deviation cost value is proportional to the difference between the heading angle of the parking starting point and the heading angle of each relay point, the step distance cost value is inversely proportional to the step distance of each relay point, and the feasible domain cost value is inversely proportional to the feasible domain area of ​​each relay point.

[0105] Through the above formula, the influence of the heading angle, step distance and feasible domain area of ​​each relay point on the cost value of each relay point can be comprehensively considered, so that the cost value of each relay point is more accurate and closer to the actual parking path planning requirements.

[0106] In some optional embodiments, the above step S104, performing path planning based on each relay point in the candidate relay points to obtain a parking path for the target vehicle, includes:

[0107] Sort the candidate relay points in descending order according to the cost value;

[0108] Traverse each of the candidate relay points in turn, and perform path planning on the currently traversed relay point to obtain a path planning result;

[0109] When the path planning result indicates that the path is valid, determining a parking path for the target vehicle based on the path planning result;

[0110] When the path planning result indicates that the path is invalid, continue to traverse the next relay point in the candidate relay points, and perform path planning for the newly traversed relay points, and repeat the process until the traversal is stopped when the preset conditions are met. The preset conditions are that all relay points in the candidate relay points have been traversed, or a relay point with a valid path is determined from the candidate relay points.

[0111] In one embodiment, after obtaining the candidate relay points, each relay point in the candidate relay points can be sorted in order from low to high according to the cost value, and then each relay point in the candidate relay points is traversed in turn, and the path planning is performed on the currently traversed relay point to obtain the path planning result. If the path planning result indicates that the path is valid, the parking path of the target vehicle is determined based on the path planning result; if the path planning result indicates that the path is invalid, the next relay point in the candidate relay points is traversed continuously, and the path planning is performed on the newly traversed relay point, and the cycle is repeated until all the relay points in the candidate relay points have been traversed, or when a relay point with a valid path is determined from the candidate relay points, the traversal is stopped.

[0112] In this embodiment, since the candidate relay points are sorted in order of cost value from low to high, the traversal is also performed in order of cost value from low to high, which is conducive to giving priority to points with smaller cost values ​​for path planning.

[0113] In some optional embodiments, the above step of determining the parking path of the target vehicle based on the path planning result includes:

[0114] The path planned in the path planning result is determined as the first path between the parking starting point and the currently traversed relay point;

[0115] Determine a second path between the currently traversed relay point and the target sampling point, wherein the target sampling point is a sampling point corresponding to the coordinate system where the currently traversed relay point is located;

[0116] Determine a third path between the target sampling point and the parking end point, wherein the third path is a straight line;

[0117] Based on the first path, the second path and the third path, a parking path of the target vehicle is determined.

[0118] In one embodiment, when determining the parking path of the target vehicle based on the path planning result, the path planned in the path planning result can be determined as the first path between the parking starting point and the currently traversed relay point, and based on the vehicle kinematic model, the second path between the currently traversed relay point and the target sampling point is determined, and then the third path between the target sampling point and the parking end point is determined, wherein the third path is a straight line, and finally the parking path of the target vehicle is determined based on the first path, the second path and the third path. Figure 5 As shown, a preset path planning algorithm can be used to plan a path from the parking starting point To relay point The first path and the relay points are calculated based on the vehicle kinematic model. To the target sampling point The second path between the target sampling points To the parking end The third path is a straight line, so that we can finally get the To the parking end Parking path.

[0119] Through the above method, different path planning algorithms can be perfectly compatible, and the path planning efficiency can be significantly improved, shortening the planning time.

[0120] In one embodiment, the parking path planning process may be as follows: Figure 6 As shown, the following steps may be specifically included:

[0121] Step S601: Acquire the parking end position.

[0122] Step S602: Sampling is performed based on the parking end point to obtain multiple sampling points, and the multiple sampling points are traversed in sequence.

[0123] Step S603: Sampling the vehicle status at the currently traversed sampling point.

[0124] Step S604: motion deduction obtains the relay point under the current sampling point.

[0125] Step S605: perform collision detection on the relay point.

[0126] Step S606: Determine whether there is a collision at the relay point.

[0127] If there is no collision at the relay point, execute step S607; if there is a collision at the relay point, return to step S603.

[0128] Step S607: store the relay point and calculate the initial cost value.

[0129] Step S608: Determine whether the vehicle status sampling is completed.

[0130] If the vehicle status sampling is completed, execute step S609; if the vehicle status sampling is not completed, return to step S603.

[0131] Step S609: Obtain the size of the feasible region.

[0132] Step S610: Calculate the feasible domain cost.

[0133] Step S611: superimpose the initial cost value and the feasible domain cost value.

[0134] Step S612: Determine whether the traversal of multiple sampling points is completed.

[0135] If the traversal of multiple sampling points is completed, step S613 is executed; if the traversal of multiple sampling points is not completed, the process returns to step S602.

[0136] Step S613: sort the cost values ​​of each relay point.

[0137] Step S614: Obtain candidate relay points, and traverse the candidate relay points in sequence.

[0138] Step S615: perform parking path planning based on the candidate relay points currently traversed.

[0139] Step S616: Determine whether the planned path is valid.

[0140] If the planned path is valid, the process ends; if the planned path is invalid, the process returns to step S614.

[0141] In this embodiment, in the initial stage of parking, the parking end point is prospectively deduced based on the vehicle kinematic model, and the parking feasible domain under different conditions is constructed through detailed collision detection analysis. In this process, instead of identifying a single relay point, a series of potential relay point sets are generated, which cover a wider range of path selection space. Then, through the cost value evaluation and sorting mechanism, the relay point with the lowest cost can be selected from the relay point set for subsequent parking path planning. In this way, not only is it perfectly compatible with different path planning algorithms, but it also significantly improves planning efficiency and shortens planning time. In addition, because more potential path options are considered, the final generated path is more feasible and closer to actual parking needs.

[0142] See also Figure 7 , Figure 7 The following is a schematic diagram of the structure of a parking path planning device provided by an embodiment of the present invention. Figure 7 As shown, the parking path planning device 700 includes:

[0143] The acquisition module 701 is used to acquire environmental perception information around the parking space, and determine the parking end point of the target vehicle in the parking space and obstacle information around the parking space based on the environmental perception information;

[0144] A determination module 702 is used to determine a set of relay points corresponding to the target vehicle based on the parking end point and the obstacle information, wherein the set of relay points is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with the obstacle;

[0145] The calculation and sorting module 703 is used to calculate the cost value of each relay point in the relay point set, sort the cost value of each relay point in the relay point set, and determine the candidate relay point according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold;

[0146] The path planning module 704 is used to perform path planning based on each relay point among the candidate relay points to obtain a parking path for the target vehicle.

[0147] In some optional embodiments, the determination module 702 includes:

[0148] A first determination submodule is used to determine a plurality of sampling points based on the parking end point, wherein the plurality of sampling points and the parking end point are spaced apart along the length direction of the parking space, and each of the plurality of sampling points has a different distance from the parking end point;

[0149] A construction submodule, for sequentially taking each sampling point of the plurality of sampling points as the origin of the coordinate system, to construct a coordinate system corresponding to each sampling point, wherein a first coordinate axis of the coordinate system corresponding to each sampling point is parallel to the width direction of the parking space to be parked, and a second coordinate axis of the coordinate system corresponding to each sampling point is parallel to the length direction of the parking space to be parked;

[0150] The second determination submodule is used to sequentially determine the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point;

[0151] The collision detection submodule is used to perform collision detection on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn based on the obstacle information, and determine the relay point set according to the collision detection result.

[0152] In some optional embodiments, the second determining submodule includes:

[0153] An acquisition unit, used to acquire the front wheel turning angle and step distance corresponding to the target vehicle in the coordinate system corresponding to each sampling point;

[0154] The first determination unit is used to determine the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point based on the vehicle kinematic model, the front wheel turning angle and the stepping distance, wherein the feasible domain includes multiple relay point series, each relay point sequence in the multiple relay point series corresponds one-to-one to the front wheel turning angle, and each relay point in each relay point sequence corresponds one-to-one to the stepping distance.

[0155] In some optional embodiments, the calculation and sorting module 703 includes:

[0156] The acquisition submodule is used to obtain the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set;

[0157] A first calculation submodule is used to calculate the initial cost value and the feasible domain cost value of each relay point in the relay point set based on the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set, wherein the initial cost value is the sum of the heading deviation cost value and the step distance cost value, the heading deviation cost value is proportional to the difference between the heading angle of the parking starting point and the heading angle of each relay point, the step distance cost value is inversely proportional to the step distance of each relay point, and the feasible domain cost value is inversely proportional to the feasible domain area of ​​each relay point;

[0158] The second calculation submodule is used to calculate the product of the initial cost value and the feasible domain cost value, and determine the calculation result as the cost value of each relay point in the relay point set.

[0159] In some optional embodiments, the calculation formula of the cost value of each relay point in the relay point set is as follows:

[0160] ;

[0161] ;

[0162] ;

[0163] ;

[0164] ;

[0165] in, represents the cost value of the target relay point, represents the initial cost value of the target relay point, represents the feasible domain cost value of the target relay point, Indicates the heading deviation cost value of the target relay point, Indicates the step distance cost value of the target relay point, Indicates the heading angle of the parking starting point, Indicates the heading angle of the target relay point, Indicates the step distance of the target relay point, Indicates the preset step distance. , , , They represent the actual boundary values ​​of the feasible domain in the coordinate system where the target relay point is located. The target relay point is any relay point in the relay point set. Indicates the length of the feasible region in the coordinate system where the target relay point is located, Indicates the width of the feasible region in the coordinate system where the target relay point is located.

[0166] In some optional embodiments, the path planning module 704 includes:

[0167] A sorting submodule, used to sort the candidate relay points in descending order according to the cost value;

[0168] The path planning submodule is used to traverse each of the candidate relay points in turn, and perform path planning on the currently traversed relay point to obtain a path planning result;

[0169] A third determination submodule is used to determine a parking path for the target vehicle based on the path planning result when the path planning result indicates that the path is valid;

[0170] The loop submodule is used to continue traversing the next relay point among the candidate relay points when the path planning result indicates that the path is invalid, and to perform path planning for the newly traversed relay point, and to loop in sequence until the traversal is stopped when the preset condition is met, wherein the preset condition is that all the relay points among the candidate relay points have been traversed, or a relay point with a valid path is determined from the candidate relay points.

[0171] In some optional embodiments, the third determining submodule includes:

[0172] A second determining unit is used to determine the path planned in the path planning result as a first path between the parking starting point and the currently traversed relay point;

[0173] A third determining unit is used to determine a second path between the currently traversed relay point and the target sampling point, wherein the target sampling point is a sampling point corresponding to the coordinate system where the currently traversed relay point is located;

[0174] a fourth determining unit, configured to determine a third path between the target sampling point and the parking end point, wherein the third path is a straight line;

[0175] The fifth determining unit is used to determine a parking path of the target vehicle based on the first path, the second path and the third path.

[0176] The parking path planning device 700 can implement the parking path planning method provided by any of the aforementioned method embodiments and can achieve the same technical effects, which will not be described in detail herein.

[0177] like Figure 8 As shown, an embodiment of the present invention further provides an electronic device, including a processor 811, a communication interface 812, a memory 813 and a communication bus 814, wherein the processor 811, the communication interface 812, and the memory 813 communicate with each other through the communication bus 814.

[0178] Memory 813, used for storing computer programs;

[0179] In one embodiment of the present invention, the processor 811 is configured to implement the parking path planning method provided by any one of the aforementioned method embodiments when executing the program stored in the memory 813 .

[0180] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the parking path planning method provided by any one of the aforementioned method embodiments is implemented.

[0181] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0183] It should be understood that the terms used in the text are only for the purpose of describing specific example embodiments, and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0184] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A parking path planning method, characterized in that: The method comprises: Acquiring environmental perception information around the parking space, and determining a parking destination of the target vehicle in the parking space and obstacle information around the parking space based on the environmental perception information; Based on the parking end point and the obstacle information, determining a relay point set corresponding to the target vehicle, wherein the relay point set is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with obstacles; Calculating the cost value of each relay point in the relay point set, sorting the cost value of each relay point in the relay point set, and determining a candidate relay point according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold, and the cost value of each relay point in the relay point set is related to the heading angle, step distance and feasible domain area of ​​each relay point; Performing path planning based on each of the candidate relay points to obtain a parking path for the target vehicle; Wherein, the step of determining a set of relay points corresponding to the target vehicle based on the parking end point and the obstacle information includes: Based on the parking end point, a plurality of sampling points are determined, wherein the plurality of sampling points and the parking end point are spaced apart along the length direction of the parking space, and each of the plurality of sampling points has a different distance from the parking end point; Taking each sampling point of the plurality of sampling points as the origin of the coordinate system in turn, a coordinate system corresponding to each sampling point is constructed, wherein a first coordinate axis of the coordinate system corresponding to each sampling point is parallel to a width direction of the parking space, and a second coordinate axis of the coordinate system corresponding to each sampling point is parallel to a length direction of the parking space; Determine the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in sequence, wherein the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point is determined based on the vehicle kinematic model, the front wheel turning angle and the stepping distance corresponding to the target vehicle in the coordinate system corresponding to each sampling point; Based on the obstacle information, collision detection is performed on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn, and the relay point set is determined according to the collision detection result.

2. The parking path planning method according to claim 1, characterized in that: The step of sequentially determining the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point includes: Obtaining the front wheel turning angle and step distance corresponding to the target vehicle in the coordinate system corresponding to each sampling point; Based on the vehicle kinematic model, the front wheel turning angle and the stepping distance, a feasible domain of the target vehicle in the coordinate system corresponding to each sampling point is determined, wherein the feasible domain includes multiple relay point sequences, each relay point sequence in the multiple relay point sequences corresponds one-to-one to the front wheel turning angle, and each relay point in each relay point sequence corresponds one-to-one to the stepping distance.

3. The parking path planning method according to claim 1, characterized in that: The calculating the cost value of each relay point in the relay point set includes: Obtaining the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set; Based on the heading angle, step distance and feasible domain area of ​​each relay point in the relay point set, the initial cost value and the feasible domain cost value of each relay point in the relay point set are calculated respectively, wherein the initial cost value is the sum of the heading deviation cost value and the step distance cost value, the heading deviation cost value is proportional to the difference between the heading angle of the parking starting point and the heading angle of each relay point, the step distance cost value is inversely proportional to the step distance of each relay point, and the feasible domain cost value is inversely proportional to the feasible domain area of ​​each relay point; The product of the initial cost value and the feasible region cost value is calculated, and the calculation result is determined as the cost value of each relay point in the relay point set.

4. The parking path planning method according to claim 3, characterized in that: The calculation formula of the cost value of each relay point in the relay point set is as follows: ； ； ； ； ； in, represents the cost value of the target relay point, represents the initial cost value of the target relay point, represents the feasible domain cost value of the target relay point, represents the heading deviation cost value of the target relay point, represents the step distance cost value of the target relay point, represents the heading angle of the parking starting point, represents the heading angle of the target relay point, represents the step distance of the target relay point, Indicates the preset step distance. , , , represent the actual boundary values ​​of the feasible domain in the coordinate system where the target relay point is located, and the target relay point is any relay point in the relay point set. represents the length of the feasible region in the coordinate system where the target relay point is located, Indicates the width of the feasible region in the coordinate system where the target relay point is located.

5. The parking path planning method according to claim 1, characterized in that: The performing path planning based on each of the candidate relay points to obtain the parking path of the target vehicle includes: Sorting the candidate relay points in descending order of cost value; Traversing each of the candidate relay points in turn, and performing path planning on the currently traversed relay point to obtain a path planning result; When the path planning result indicates that the path is valid, determining a parking path for the target vehicle based on the path planning result; When the path planning result indicates that the path is invalid, continue to traverse the next relay point among the candidate relay points, and perform path planning for the newly traversed relay point, and repeat the process until the traversal is stopped when a preset condition is met, wherein the preset condition is that all relay points among the candidate relay points have been traversed, or a relay point with a valid path is determined from the candidate relay points.

6. The parking path planning method according to claim 5, characterized in that: The determining of the parking path of the target vehicle based on the path planning result includes: Determine the path obtained from the path planning result as the first path between the parking starting point and the currently traversed relay point; Determine a second path between the currently traversed relay point and the target sampling point, wherein the target sampling point is a sampling point corresponding to the coordinate system where the currently traversed relay point is located; Determine a third path between the target sampling point and the parking end point, wherein the third path is a straight line; A parking path of the target vehicle is determined based on the first path, the second path, and the third path.

7. A parking path planning device, characterized in that: The device comprises: An acquisition module, used to acquire environmental perception information around the parking space, and determine the parking end point of the target vehicle in the parking space and obstacle information around the parking space according to the environmental perception information; A determination module, configured to determine a set of relay points corresponding to the target vehicle based on the parking end point and the obstacle information, wherein the set of relay points is a set of multiple relay points that are within the feasible domain of the target vehicle and do not collide with obstacles; A calculation and sorting module, used to calculate the cost value of each relay point in the relay point set, sort the cost value of each relay point in the relay point set, and determine the candidate relay point according to the sorting result, wherein the candidate relay point is a relay point in the relay point set whose cost value is less than or equal to a preset threshold, and the cost value of each relay point in the relay point set is related to the heading angle, step distance and feasible domain area of ​​each relay point; A path planning module, used for performing path planning based on each of the candidate relay points to obtain a parking path for the target vehicle; Wherein, the determination module includes: A first determination submodule is configured to determine a plurality of sampling points based on the parking end point, wherein the plurality of sampling points and the parking end point are spaced apart along the length direction of the parking space, and each of the plurality of sampling points has a different distance from the parking end point; A construction submodule, for sequentially taking each sampling point of the plurality of sampling points as an origin of a coordinate system, to construct a coordinate system corresponding to each sampling point, wherein a first coordinate axis of the coordinate system corresponding to each sampling point is parallel to a width direction of the parking space to be parked, and a second coordinate axis of the coordinate system corresponding to each sampling point is parallel to a length direction of the parking space to be parked; The second determination submodule is used to sequentially determine the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point, wherein the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point is determined based on the vehicle kinematic model, the front wheel turning angle and the stepping distance corresponding to the target vehicle in the coordinate system corresponding to each sampling point; The collision detection submodule is used to perform collision detection on each relay point in the feasible domain of the target vehicle in the coordinate system corresponding to each sampling point in turn based on the obstacle information, and determine the relay point set according to the collision detection result.

8. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the parking path planning method according to any one of claims 1 to 6 when executing the program stored in the memory.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the parking path planning method according to any one of claims 1 to 6 is implemented.

Images