Path planning method and device

Abstract

The invention provides a path planning method and device, and the method comprises the steps: determining a grid cost map in a target region based on an environment map in the target region; according to the pose information of the target vehicle and the position information of the starting point and the target point, candidate nodes meeting kinematics constraints between the starting point and the target point are generated; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree; starting from the starting point, performing node search in a node tree based on a grid cost map by using a cost function, so as to determine a target node from the node tree; determining a connection line of each target node as a target path; wherein the cost function comprises a safety cost item and a penalty cost item. According to the embodiment, under the condition that the subject faces a complex environment and has many obstacles, the path planning safety and search efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a path planning method and device. Background Art

[0002] With the rapid development of artificial intelligence technology, more and more planning algorithms combined with artificial intelligence have emerged. Among them, the hybrid A algorithm is a representative method and has been widely used in practical engineering due to its simple deployment and good path generation characteristics.

[0003] However, it is found in actual engineering that the current hybrid A algorithm mainly performs path planning based on cars, which have relatively standard parking spaces. This results in the inability of the traditional hybrid A algorithm to perform reasonable path planning for entities such as unmanned delivery vehicles in complex environments with many obstacles, and its path safety and search efficiency are both lacking. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure at least provide a path planning method, device, electronic device and storage medium, which can improve the path safety and search efficiency of path planning when the subject faces complex environments, many obstacles, etc.

[0005] In a first aspect, an embodiment of the present disclosure provides a path planning method, including:

[0006] Determining a grid cost map within the target area based on an environment map within the target area;

[0007] According to the posture information of the target vehicle and the position information of the starting point and the target point, a candidate node satisfying the kinematic constraint between the starting point and the target point is generated; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree;

[0008] Starting from the starting point, based on the grid cost map and using the cost function, a node search is performed in the node tree to determine the target node from the node tree; the connection between each of the target nodes is determined as the target path; wherein the cost function includes a safety cost item and a penalty cost item.

[0009] Optionally, performing a node search in the node tree using the cost function includes:

[0010] Determining the density of obstacles corresponding to the candidate nodes in the node tree according to the obstacle information and the parameter information of the target vehicle;

[0011] According to the density of the obstacles, a search step length of the node search is determined; and a node search is performed in the node tree according to the search step length.

[0012] Optionally, the safety cost term in the cost function is constructed based on field potential;

[0013] The method comprises:

[0014] Based on the obstacle information of the target area and the coordinate data of the target vehicle, the field potential value of the target vehicle is calculated, and the safety cost is determined based on the field potential value.

[0015] Optionally, the penalty cost term in the cost function is determined based on road line information;

[0016] The method comprises:

[0017] Based on the road line information of the target area and the coordinate data of the target vehicle, the intersection degree between the target vehicle and the road line is determined, and the penalty cost is determined based on the intersection degree.

[0018] Optionally, the cost function also includes a known cost and an heuristic cost.

[0019] Optionally, the known cost includes at least one of a path length cost, a boundary crossing cost, a no-parking zone occupancy cost, a driving direction switching cost and a turning cost.

[0020] Optionally, starting from the starting point, based on the grid cost map and using the cost function, performing a node search in the node tree to determine a target node from the node tree includes:

[0021] Taking the starting point as the current node, putting the current node into the target node list;

[0022] The following steps are executed in a loop until the child node with the smallest cost value is the target point: based on the grid cost map and using the cost function, the cost value of the child node associated with the current node in the node tree is determined, the child node with the smallest cost value is placed in the target node list, and it is determined whether the child node with the smallest cost value is the target point; if the child node with the smallest cost value is not the target point, the child node with the smallest cost value is determined as the new current node;

[0023] In the case where the child node with the smallest cost value is the target point, each node in the target node list is used as a target node.

[0024] In a second aspect, an embodiment of the present disclosure provides a path planning device, including:

[0025] A determination module, configured to determine a grid cost map within the target area based on an environment map within the target area;

[0026] A screening module is used to generate candidate nodes between the starting point and the target point that satisfy kinematic constraints according to the position information of the target vehicle and the position information of the starting point and the target point; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree;

[0027] A search module is used to start from the starting point, perform node search in the node tree based on the grid cost map and using a cost function to determine a target node from the node tree; determine the connection between each of the target nodes as a target path; wherein the cost function includes a safety cost item and a penalty cost item.

[0028] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect, or any optional implementation of the first aspect are performed.

[0029] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect, or any optional implementation of the first aspect are executed.

[0030] Any one of the above aspects or any implementation method of any one of the aspects, by determining the grid cost map in the target area based on the environmental map in the target area; generating candidate nodes between the starting point and the target point that satisfy the kinematic constraints according to the posture information of the target vehicle and the position information of the starting point and the target point; wherein each of the candidate nodes exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree; starting from the starting point, based on the grid cost map and using the cost function, a node search is performed in the node tree to determine the target node from the node tree; the connection of each of the target nodes is determined as the target path; wherein the cost function includes a safety cost item and a penalty cost item. Thus, by adding a safety cost item to the cost function, the path safety of the path planning of the subject is improved when the environment is complex and there are many obstacles.

[0031] In a further embodiment of the present disclosure, the density of obstacles corresponding to the candidate nodes in the node tree is determined according to the obstacle information and the parameter information of the target vehicle; the search step length of the node search is determined according to the obstacle density; and the node search is performed in the node tree according to the search step length. This realizes the dynamic change of the search strategy according to the actual environment, thereby improving the efficiency of the path search. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0033] Figure 1 A flow chart of a path planning method provided by an embodiment of the present disclosure is shown;

[0034] Figure 2 A schematic diagram of a path planning device provided by an embodiment of the present disclosure is shown;

[0035] Figure 3 An exemplary system architecture is shown in which embodiments of the present disclosure may be applied;

[0036] Figure 4 A schematic diagram of the structure of a computer system of a terminal device or a server used to implement an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0038] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0039] Research has found that with the rapid development of artificial intelligence technology, more and more path planning algorithms combined with artificial intelligence have emerged. Among them, the hybrid A algorithm, as a representative method, has been widely used in practical engineering due to its simple deployment and good characteristics of generating paths. The algorithm takes vehicle dynamics into account and can make the generated path meet the requirements of vehicle dynamics, greatly increasing the availability of the generated path.

[0040] However, it is found in actual engineering that the current hybrid A algorithm mainly considers the path planning process with cars as the main body. Cars often have relatively standard parking spaces, but there is no focus on unmanned delivery vehicles, data collection vehicles and other entities that need to travel and park in complex environments with many obstacles. This leads to low search efficiency in path planning using the hybrid A algorithm for such entities, and the security of the resulting path planning results is also low.

[0041] Based on the above research, the disclosed embodiment improves the safety and efficiency of the path planning process by introducing a safety cost term based on field potential and a penalty cost term based on road line information into the cost function. In addition, the density of obstacles corresponding to the candidate nodes in the node tree is determined according to the obstacle information and the parameter information of the target vehicle; the search step length of the node search is determined according to the obstacle density; and the node search is performed in the node tree according to the search step length. This realizes the dynamic change of the search strategy according to the actual environment, and further improves the node search efficiency in the path planning process.

[0042] The raising of the above problems and the solutions are the results obtained by the inventor after practice and careful research. The discovery process of the above problems and the solutions proposed for the above problems should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0043] The technical solutions in the present disclosure will be clearly and completely described below in conjunction with the drawings in the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure claimed for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0044] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0045] To facilitate understanding of this embodiment, a path planning method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the path planning method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the path planning method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0046] See also Figure 1 FIG. 1 is a flow chart of a path planning method provided by an embodiment of the present disclosure, and the method includes S101 to S103, wherein:

[0047] S101: Determine a grid cost map within the target area based on an environment map within the target area.

[0048] In the disclosed embodiment, the target area may be an area including a starting point and a target point where the subject can travel, or may be other areas where path planning is required. The environment map may indicate information such as obstacle information and road condition information included in the target area.

[0049] Before determining the grid cost map, the grid map in the target area can be determined first. The grid map is a representation method for discretizing continuous space, which is used to represent feasible areas and obstacles in the environment. Specifically, sensors such as laser radar, cameras and other devices can be used to obtain point cloud data and image data in the target area. Then the acquired sensor data can be processed into a two-dimensional grid map, where each grid represents a small area in the environment. When dividing the grid, the entire environment can be divided into grids of fixed size, each grid represents an area of ​​fixed size, and the size here can be determined by the specific application and the accuracy of the sensor. Among them, each grid can also correspond to different states, for example, a grid in an idle state can represent an area without obstacles, and the subject can pass through the grid; a grid in an obstacle state represents an area with obstacles, and the subject cannot pass through the grid; in addition, there are grids in an unknown state, which can be used to represent areas not covered by sensor data. These grids can be considered impassable or require further detection.

[0050] In the disclosed embodiment, after determining the grid map in the target area, the grid cost map can be determined. Specifically, the coordinates of the starting point and the target point can be defined first, and then a function or algorithm can be used to estimate the minimum cost of passing through each grid when mapping the target vehicle to the grid map, for example, Manhattan distance, Euclidean distance, Dijkstra algorithm, etc. can be used.

[0051] In a specific implementation, starting from the starting point, the starting point can be used as the current node, the neighboring nodes of the current node can be determined, and the above function or algorithm can be used to calculate the movement cost from the current node to the neighboring node. The cost here can be composed of two parts, namely the actual cost and the heuristic cost, where the actual cost is the cost from the starting point to the current node. When the calculation just starts, the starting point is the current node, and the cost at this time can be 0; the heuristic cost is the cost from the current node to the target point. After the total cost of each grid is calculated, it can be saved in the grid cost map. In the grid cost map, the total cost of each grid can be displayed, where the cost of obstacles and inaccessible areas can be infinite.

[0052] S102: Generate candidate nodes between the starting point and the target point that satisfy kinematic constraints based on the posture information of the target vehicle and the position information of the starting point and the target point; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree.

[0053] In this step, the candidate nodes between the starting point and the target point that satisfy the kinematic constraints can be obtained based on the predetermined position information of the starting point and the target point, combined with the position information and size parameter information of the target vehicle. The candidate nodes here are used to screen the target nodes for generating the target path. The target nodes here are each node that constitutes the target path. When the target vehicle travels along the target path, it will pass through the target node and may perform actions such as turning at the target node.

[0054] In the disclosed embodiments, kinematic constraints may refer to physical limitations or constraints imposed on the target vehicle during its motion, such as turning radius, maximum steering angle, maximum speed, etc., to ensure the stability and safety of the vehicle during its driving. These kinematic constraints are related to the target vehicle's own parameters and the environmental conditions in the target area. For example, the length, width, wheelbase, and tire characteristics of the target vehicle will affect the kinematic constraints of the target vehicle during its driving; or, for example, the turning radius in a narrow environment is bound to be different from the turning radius in an open environment, and this difference will also affect the kinematic constraints of the target vehicle during its driving.

[0055] In the disclosed embodiment, before generating candidate nodes satisfying kinematic constraints based on the pose information of the target vehicle and the position information of the starting point and the target point, the curvature sampling interval and step size for collecting the pose information may be determined first.

[0056] The curvature sampling interval refers to the interval for sampling different curvature values ​​during the path generation process. The curvature represents the degree of curvature of the path and is closely related to parameters such as the turning radius of the target vehicle. The step size refers to the incremental distance advanced during the path generation process, which has a great impact on the refinement and computational efficiency of the path.

[0057] In the embodiments of the present disclosure, dimensions such as the physical constraints of the vehicle, the path smoothness requirements, and the computational complexity of the algorithm may be considered when determining the curvature sampling interval; dimensions such as the size and motion characteristics of the vehicle, the resolution of the path planning (related to the size of each grid in the grid map, for example, if the size of each grid in the grid map is 1 meter, then the step size may be selected to be 1 meter or less than 1 meter) and algorithm efficiency may be considered when determining the sampling step size.

[0058] In a specific implementation, after determining the position information of the starting point and the target point, the starting point can be used as the root node of the node tree, that is, the starting point of the node tree. Then the position and posture information of the target vehicle at the starting point can be obtained. According to the position and posture information of the target vehicle at the starting point and the kinematic constraints, a set of new positions and postures are generated in the direction of the target point according to the predetermined curvature sampling interval and sampling step. The new position and posture here refers to the position where the target vehicle may be after a time step; each new position and posture corresponds to a child node associated with the starting point. After obtaining the child node corresponding to the starting point, each child node can be evaluated to check whether it is effectively constrained by the kinematic constraints, such as whether it collides with an obstacle, whether it is in the drivable area, whether it is less than the maximum speed, etc. For each child node that passes the check, it can be sorted from small to large according to the cost value from the starting point to the child node, and then a preset number of child nodes in the child node sequence can be used as candidate nodes, and then it can be determined whether the target point is included in the candidate nodes. If it is included, it indicates that the node tree has successfully expanded from the initial point to the target point, and the node expansion is completed; if it is not included, the determined candidate node can be added to the node tree for subsequent expansion.

[0059] In the case that the determined candidate nodes do not include the target point, several candidate nodes that are close to the target point can be selected from the candidate nodes in the current node tree, and the above steps can be repeated to continuously expand the node tree until a candidate node that has been expanded is determined as the target point, and then the expansion of the node tree can be stopped. In this way, a node tree that includes the starting point and the target point and satisfies the kinematic constraints is obtained.

[0060] S103: Starting from the starting point, based on the grid cost map and using the cost function, a node search is performed in the node tree to determine the target node from the node tree; the connection between each target node is determined as the target path; wherein the cost function includes a safety cost item and a penalty cost item.

[0061] In an embodiment of the present disclosure, a node search is performed in a node tree using a cost function, including: determining the obstacle density corresponding to the candidate nodes in the node tree based on the obstacle information and the parameter information of the target vehicle; determining the search step length of the node search based on the obstacle density; and performing a node search in the node tree according to the search step length.

[0062] In the specific implementation, in order to improve the efficiency of node search, a multi-stage dynamic adjustment strategy can be adopted when performing node search. Specifically, the path planning can be divided into multiple stages according to the obstacle information in the target area and the current position, orientation and other parameter information of the target vehicle. For example, the search strategy of different stages can be determined according to the density of obstacles; in areas with high density of obstacles, the search step length can be increased to improve the search efficiency, and in areas with fewer obstacles, the search step length can be reduced to ensure the safety of the path.

[0063] In another possible implementation, different phase search strategies may be determined according to vehicle state parameters at different phases. For example, when the target vehicle approaches the target position, the search step length may be reduced to ensure accurate parking of the vehicle.

[0064] In the disclosed embodiment, starting from the starting point, based on the grid cost map and using the cost function, a node search is performed in the node tree to determine the target node from the node tree, including: taking the starting point as the current node, and placing the current node into the target node list; looping through the following steps until the child node with the smallest cost value is the target point: based on the grid cost map and using the cost function, determining the cost value of the child nodes associated with the current node in the node tree, placing the child node with the smallest cost value into the target node list, and determining whether the child node with the smallest cost value is the target point; in the case where the child node with the smallest cost value is not the target point, determining the child node with the smallest cost value as the new current node; in the case where the child node with the smallest cost value is the target point, taking each node in the target node list as the target node.

[0065] In the specific implementation, the target node list can be initialized first, the starting point is set as the current node and placed in the target node list. Then, starting from the current node (i.e., the starting point), the cost value of the child node associated with the current node in the node tree can be determined according to the cost value in the grid cost map and the cost value calculated using the cost function, and the child node with the smallest cost value is placed in the target node list as the next node of the current node. Then, it can be determined whether the child node with the smallest cost value is the target point. If so, it indicates that the path planning has been planned to the target point, and the node search can be stopped, and each node in the target node list can be used as the target node; if not, the child node with the smallest cost value can be used as the new current node, and the cost value of the child node associated with it can be calculated continuously until the child node with the smallest cost value is the target point, and each node in the target node list is used as the target node.

[0066] In the disclosed embodiment, the cost function may include a safety cost item, and the safety cost item here may be constructed based on field potential. Field potential is a path planning technology based on the concept of physics, which regards obstacles in the environment as interacting objects and uses their repulsive and attractive effects to generate paths. Each point in the target area has a field potential value. Obstacles will generate a repulsive field, and the target point will generate an attractive field, so that the path planning principle for the target vehicle avoids obstacles and heads towards the target point, so as to avoid collisions between the target vehicle and obstacles and ensure the safety of path planning.

[0067] In a specific implementation, the field potential used to establish the safety cost item can be a Voronoi field potential, a Gaussian field potential, an inverse distance field potential, etc. In practical applications, it should be based on actual needs and be able to realize its functions. The embodiments of the present disclosure do not specifically limit this. Specifically, obstacles (such as walls, other vehicles, pedestrians, etc.) in the target area can be represented as obstacle points in the field potential. For each obstacle point, when calculating the field potential value, calculations can be performed for multiple reference points in the target vehicle, and the maximum field potential value is selected as the safety cost in the cost function, thereby ensuring the safety of path planning. Exemplarily, the field potential value can be calculated using the following formula:

[0068] v(x,y)=max[v 1 ,v 2 ,v 3 ,v 4 ];

[0069] Among them, v 1 ,v 2 ,v 3 ,v 4 They represent the potential values ​​of the endpoints of the i-th vehicle body rectangular box when the target vehicle is at (x, y); v(x, y) represents the maximum value among them as the potential value of the target vehicle at that position.

[0070] For example, taking the construction of the safety cost term using the Voronoi potential as an example, the Voronoi potential can be defined as follows:

[0071] When l>l max When V(x,y)=0;

[0072] When l <l max hour,

[0073] Where l represents the distance from the current position to the nearest obstacle; l vrepresents the distance to the nearest edge of the generalized Voronoi diagram (GVD, a commonly used method to conveniently represent the free space and obstacles in the environment; GVD divides the environment into multiple regions, and the distance from any point in each region to the nearest obstacle is equal, so the edge of the GVD represents the safe boundary of the free space to the nearest obstacle); a and l max is a constant used to control the decreasing decay rate of the potential field and limit the maximum effective range.

[0074] In the disclosed embodiment, the cost function may further include a penalty cost item, where the penalty cost item may be determined based on the road line information. Specifically, based on the pre-acquired road line information, it may be determined whether the target vehicle intersects with the road line and the degree of intersection, and different cost values ​​may be set for different degrees of intersection, thereby obtaining the penalty cost item in the cost function, thereby further improving the safety of path planning.

[0075] In the disclosed embodiment, the cost function may also include a known cost and an heuristic cost. The known cost represents the cost value from the starting point to the current node, and the heuristic cost represents the cost value from the current node to the target point. For the known cost, other sub-cost items may also be included, but too many sub-cost items will increase the amount of calculation. Therefore, in the disclosed embodiment, the sub-cost items in the known cost item may include at least one of the path length cost, the boundary crossing cost, the no-parking zone occupancy cost, the driving direction switching cost, and the turning cost. Among them, the path length cost can represent the path length cost from the starting point to the current node. The path should be as short as possible during the calculation process; the boundary crossing cost can represent the cost of crossing the left boundary of the map. By calculating this sub-cost item, it can be ensured that the path planning can correctly handle the situation of crossing the boundary; the no-parking area in the no-parking area occupancy cost can be when the target vehicle stops at the roadside, there are objective no-parking areas in the environment and subjective no-parking areas, such as school gates, unobstructed areas, etc.; the driving direction switching cost can be understood as a broken line penalty. The switching of driving direction should be minimized during the path planning process; during the target vehicle parking process, the control tracking effect may be poor due to the low speed, so as to make the direction change as little as possible during the parking process, that is, to make the steering cost as small as possible.

[0076] It should be noted that the above description of the sub-cost items in the known cost is only used as an example of a feasible implementation of the present invention, and does not constitute an improper limitation of the present invention. In the actual application process, additional adjustments can be made based on specific needs. In a specific implementation, if there are multiple sub-cost items, different weights can be set for each sub-cost item to indicate different levels of importance in the final cost function.

[0077] In summary, in the embodiment of the present disclosure, the following cost function can be constructed to perform node search in the node tree:

[0078] f(x,y)=w 1 g(x,y)+w 2 h(x,y)+w 3 v(x,y)+w 4 boundry(x,y);

[0079] Among them, w 1 、w 2 、w 3 、w 4 Represents the weight coefficient; f(x,y) represents the cost function; g(x,y) represents the known cost; h(x,y) represents the heuristic cost; v(x,y) represents the safety cost item; boundary(x,y) represents the penalty cost item. It should be noted that the various cost items in the above cost function are only used as an example of a possible implementation method in the embodiment of the present disclosure, and do not constitute an improper limitation on the present invention. In practical applications, the cost items in the cost function can be adjusted according to actual needs, such as adding time cost items, vehicle loss cost items, etc. The embodiment of the present disclosure does not make specific limitations on this, and its functions can be realized.

[0080] According to a second aspect of the embodiment of the present disclosure, Figure 2 As shown, a path planning device 200 is provided, comprising:

[0081] A determination module 201, for determining a grid cost map within a target area based on an environment map within the target area;

[0082] The screening module 202 is used to generate candidate nodes between the starting point and the target point that satisfy the kinematic constraints according to the position information of the target vehicle and the position information of the starting point and the target point; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree;

[0083] The search module 203 is used to start from the starting point, perform node search in the node tree based on the grid cost map and use the cost function to determine the target node from the node tree; determine the connection between each target node as the target path; wherein the cost function includes a safety cost item and a penalty cost item.

[0084] Optionally, the search module 203 is specifically used for:

[0085] According to the obstacle information and the parameter information of the target vehicle, the density of obstacles corresponding to the candidate nodes in the node tree is determined;

[0086] According to the density of obstacles, the search step length of the node search is determined; and the node search is performed in the node tree according to the search step length.

[0087] Optionally, the security cost term in the cost function is constructed based on the field potential;

[0088] The determination module 201 is further used for:

[0089] Based on the obstacle information in the target area and the coordinate data of the target vehicle, the field potential value of the target vehicle is calculated, and the safety cost is determined based on the field potential value.

[0090] Optionally, the penalty cost term in the cost function is determined based on road line information;

[0091] The determination module 201 is further used for:

[0092] Based on the road line information of the target area and the coordinate data of the target vehicle, the intersection degree between the target vehicle and the road line is determined, and the penalty cost is determined based on the intersection degree.

[0093] Optionally, the cost function also includes known cost and heuristic cost.

[0094] Optionally, the known cost includes at least one of a path length cost, a boundary crossing cost, a no-parking zone occupancy cost, a driving direction switching cost and a turning cost.

[0095] Optionally, the search module 203 is specifically used for:

[0096] Take the starting point as the current node and put the current node into the target node list;

[0097] The following steps are executed in a loop until the child node with the smallest cost value is the target point: based on the grid cost map and using the cost function, the cost value of the child node associated with the current node in the node tree is determined, the child node with the smallest cost value is put into the target node list, and it is determined whether the child node with the smallest cost value is the target point; if the child node with the smallest cost value is not the target point, the child node with the smallest cost value is determined as the new current node;

[0098] In the case where the child node with the smallest cost value is the target point, each node in the target node list is used as the target node.

[0099] According to the third aspect of an embodiment of the present disclosure, there is provided an electronic device for path planning, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0100] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present disclosure is implemented.

[0101] Figure 3 An exemplary system architecture 300 to which the path planning method or path planning device implemented by the present disclosure can be applied is shown.

[0102] like Figure 3 As shown, the system architecture 300 may include terminal devices 301, 302, 303, a network 304 and a server 305. The network 304 is used to provide a medium for communication links between the terminal devices 301, 302, 303 and the server 305. The network 304 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0103] Users can use terminal devices 301, 302, 303 to interact with server 305 through network 304 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 301, 302, 303, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0104] The terminal devices 301 , 302 , and 303 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0105] The server 305 may be a server that provides various services, such as a background management server (only as an example) that provides support for shopping websites browsed by users using the terminal devices 301, 302, and 303. The background management server may process the received route planning request and feed back the processing result (only as an example) to the terminal device.

[0106] It should be noted that the path planning method provided in the embodiment of the present invention is generally executed by the server 305, and accordingly, the path planning device is generally set in the server 305. The path planning method provided in the embodiment of the present invention can also be executed by the terminal devices 301, 302, and 303, and accordingly, the path planning device can be set in the terminal devices 301, 302, and 303.

[0107] It should be understood that Figure 3 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0108] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer system 400 of a terminal device suitable for implementing an embodiment of the present invention. Figure 4 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0109] like Figure 4 As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the system 400 are also stored. The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0110] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0111] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the system of the present invention are executed.

[0112] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0113] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, a processor includes a determination module, a screening module, and a search module, wherein the names of these modules do not constitute a limitation on the modules themselves in certain cases. For example, the determination module may also be described as a "module for determining the initial node between the starting point and the target point based on a grid map in the target area".

[0115] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the following method:

[0116] Based on the environment map in the target area, determine the grid cost map in the target area;

[0117] According to the posture information of the target vehicle and the position information of the starting point and the target point, a candidate node satisfying the kinematic constraint between the starting point and the target point is generated; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree;

[0118] Starting from the starting point, based on the grid cost map and using the cost function, a node search is performed in the node tree to determine the target node from the node tree; the connection between each target node is determined as the target path; wherein the cost function includes a safety cost item and a penalty cost item.

[0119] Finally, it should be noted that the above embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A path planning method, characterized in that: include: Determining a grid cost map within the target area based on an environment map within the target area; According to the posture information of the target vehicle and the position information of the starting point and the target point, a candidate node satisfying the kinematic constraint between the starting point and the target point is generated; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree; Starting from the starting point, based on the grid cost map and using the cost function, a node search is performed in the node tree to determine the target node from the node tree; the connection between each of the target nodes is determined as the target path; wherein the cost function includes a safety cost item and a penalty cost item.

2. The method according to claim 1, characterized in that Performing a node search in the node tree using the cost function includes: Determining the density of obstacles corresponding to the candidate nodes in the node tree according to the obstacle information and the parameter information of the target vehicle; According to the density of the obstacles, a search step length of the node search is determined; and a node search is performed in the node tree according to the search step length.

3. The method according to claim 1, characterized in that: The safety cost term in the cost function is constructed based on the field potential; The method comprises: Based on the obstacle information of the target area and the coordinate data of the target vehicle, the field potential value of the target vehicle is calculated, and the safety cost is determined based on the field potential value.

4. The method according to claim 1, characterized in that: The penalty cost term in the cost function is determined based on the road line information; The method comprises: Based on the road line information of the target area and the coordinate data of the target vehicle, the intersection degree between the target vehicle and the road line is determined, and the penalty cost is determined based on the intersection degree.

5. The method according to claim 1, characterized in that The cost function also includes known cost and heuristic cost.

6. The method according to claim 5, characterized in that The known cost includes at least one of a path length cost, a boundary crossing cost, a no-parking zone occupancy cost, a driving direction switching cost, and a turning cost.

7. The method according to claim 1, characterized in that Starting from the starting point, based on the grid cost map and using the cost function, performing a node search in the node tree to determine a target node from the node tree includes: Taking the starting point as the current node, putting the current node into the target node list; The following steps are executed in a loop until the child node with the smallest cost value is the target point: based on the grid cost map and using the cost function, the cost value of the child node associated with the current node in the node tree is determined, the child node with the smallest cost value is placed in the target node list, and it is determined whether the child node with the smallest cost value is the target point; if the child node with the smallest cost value is not the target point, the child node with the smallest cost value is determined as the new current node; In the case where the child node with the smallest cost value is the target point, each node in the target node list is used as a target node.

8. A path planning device, characterized in that: include: A determination module, configured to determine a grid cost map within the target area based on an environment map within the target area; A screening module is used to generate candidate nodes between the starting point and the target point that satisfy kinematic constraints according to the position information of the target vehicle and the position information of the starting point and the target point; wherein each candidate node exists in the form of a node tree, the starting point is the starting point of the node tree, and the target point is the end point of the node tree; A search module is used to start from the starting point, perform node search in the node tree based on the grid cost map and using a cost function to determine a target node from the node tree; determine the connection between each of the target nodes as a target path; wherein the cost function includes a safety cost item and a penalty cost item.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images