Path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field

Abstract

The present invention provides a path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field, the method comprising: limiting the sampling area to a circular area at the beginning of sampling to accelerate the convergence of the initial solution, and introducing the method of artificial potential field in the process of algorithm planning, so that the robot moves to the target position while keeping a safe distance from the obstacle. Finally, a comparative experiment is conducted on the Informed RRT* algorithm, the Informed RRT* algorithm based on target bias, and the improved Informed RRT* algorithm, and the experimental results verify the effectiveness and superiority of the improved Informed RRT* algorithm. The algorithm is more efficient, easier to obtain an initial solution, safer, and smoother than the Informed RRT* algorithm and Goal-bias-Informed RRT*.

Description

Technical Field

[0001] The present application relates to the technical field of path planning, and in particular to a path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field. Background Art

[0002] At present, with the continuous development of various high-tech technologies, the achievements of mobile robots are becoming more and more prominent. Mobile robots have not only made remarkable achievements in the industrial field, but also played an irreplaceable role in various fields such as medical care, military, rescue and smart factories. Path planning is becoming more and more important as a key technology of mobile robots. The path planning of mobile robots is to successfully plan a collision-free feasible path from the starting point to the target point based on a certain environmental model, given the starting point and the target point.

[0003] In the prior art, existing path planning algorithms include Dijkstra algorithm, A* algorithm, D* algorithm, ant colony algorithm, and genetic algorithm. However, all of the above algorithms need to model obstacles in a certain space and use the modeling to achieve path planning. However, for mobile robots, mobile robots are often in complex environments. The existing path planning algorithms are relatively simple and are only applicable to path planning in a single environment. They cannot solve the requirements of mobile robots for high-dimensional space, resulting in the inability of existing path planning algorithms to meet the driving requirements of mobile robots in complex environments. Summary of the invention

[0004] The embodiment of the present application provides a path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field to at least solve the deficiencies in the above-mentioned related technologies.

[0005] In a first aspect, an embodiment of the present application provides a path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field, comprising the following steps:

[0006] Step 1: Collect environmental information of the target object and construct a grid map based on the environmental information;

[0007] Step 2: Mark each grid in the grid map as an obstacle space or a free space, and select a starting point and a target point in the marked grid map;

[0008] Step 3: Using the constrained sampling space strategy and the target bias strategy and fusing the Informed RRT* algorithm to obtain a fusion algorithm, and sampling in the free space of the grid map through the fusion algorithm to obtain an initial path;

[0009] Step 4: After obtaining the initial path, use the fusion algorithm and the initial path to calculate an elliptical sampling space, and use an artificial potential field algorithm to perform sampling in the elliptical sampling space to obtain a first path;

[0010] Step 5: Optimizing the first path by combining the artificial potential field algorithm with the fusion algorithm to obtain an asymptotically optimal route that maintains a safe distance from obstacles;

[0011] Step 6: updating the ellipse sampling space according to the asymptotic optimality route, and sampling in the updated ellipse sampling space to obtain the asymptotic optimality path;

[0012] Step 7: Repeat the above step 6 for the asymptotically optimal path until the number of iterations is reached to obtain the final planned path of the target object.

[0013] Furthermore, the step 1 includes:

[0014] The image sensor or radar sensor of the mobile robot is used to collect the size, location, number and distribution of obstacles within the preset field of view in front of the target object;

[0015] The current position information of the target object is obtained, and a grid map of the target object is constructed based on the current position information, the size of the obstacle, the position of the obstacle, the number of obstacles, and the distribution of the obstacles.

[0016] Furthermore, the step three includes:

[0017] Using a constrained sampling space strategy to speed up the iteration of the initial solution of the Informed RRT* algorithm, obtaining a uniform circular sampling space, and performing sampling in the circular sampling space;

[0018] The target bias strategy is used to speed up the iteration of the Informed RRT* algorithm to obtain the initial path.

[0019] Furthermore, the steps of using the constrained sampling space strategy to speed up the iteration of the initial solution to obtain a uniform circular sampling space, and sampling in the circular sampling space include:

[0020] Calculate the midpoint of the straight-line distance between the starting point and the target point, and plan a uniform circular sampling space with the midpoint as the center and the straight-line distance as the diameter;

[0021] A random tree is defined, and sampling is performed in the circular sampling space using the random tree.

[0022] Further, the step of using the target bias strategy to speed up the iteration of the Informed RRT* algorithm to obtain the initial path includes:

[0023] Setting the target probability of sampling at the target point;

[0024] When the sampling point is currently randomly sampled, a current probability of uniformly sampling from the first interval is randomly generated, and it is determined whether the current probability is greater than the target probability;

[0025] If the current probability is greater than the target probability, a current sampling point is randomly generated in the circular sampling space;

[0026] If the current probability is not greater than the target probability, the target point is used as the current sampling point;

[0027] After obtaining the current sampling point, performing the next sampling, and determining whether the sampling points of the two samplings can be connected;

[0028] If the sampling points of the two samples can be connected, the sampling point of the second sampling is connected with the target point to obtain the initial path;

[0029] If the sampling points of two samplings cannot be connected, continue to perform the next sampling until the sampling points of two adjacent samplings can be connected, and connect the sampling point of the latter of the two adjacent samplings with the target point to obtain the initial path.

[0030] Furthermore, the step of determining whether the sampling points of two samples can be connected includes:

[0031] Calculate the distance between the sampling point of the second sampling and the target point, and determine whether the distance is less than the sampling step size;

[0032] If the distance is less than the sampling step, it is determined that the sampling points of the two samples cannot be connected;

[0033] If the distance is not less than the sampling step length, it is determined that the sampling points of the two samples can be connected.

[0034] Furthermore, the step 4 includes:

[0035] The length of the initial path is taken as the distance between the two vertices of the ellipse, and the distance between the starting point and the target point is taken as the distance between the two foci of the ellipse;

[0036] An ellipse sampling space is constructed according to the distance between the two vertices of the ellipse and the distance between the two foci of the ellipse.

[0037] Furthermore, the calculation formula of the midpoint is:

[0038]

[0039] In the formula, mid represents the midpoint, x1, y1 represent the known coordinates of the starting point, x2, y2 represent the coordinates of the target point, and xmid, ymid represent the desired center of the circle.

[0040] Furthermore, the expression of the current sampling point is:

[0041]

[0042] Where xrand represents the current sampling point, P represents the current probability, Pgoal represents the target probability, and xgoal represents the target point.

[0043] Compared with the related art, the path planning method based on Informed-RRT* fusion constrained sampling space and artificial potential field provided in the embodiment of the present application can reduce sampling randomness, compress sampling space, improve the convergence efficiency of the initial solution, introduce artificial potential field to keep a safe distance between the path and obstacles, so that the mobile robot can quickly find a smooth and excellent path while keeping a safe distance from obstacles; specifically, by using the constrained sampling space strategy and the target bias strategy, the number of randomly sampled nodes required can be reduced, the number of redundant nodes can be reduced, and the efficiency of obtaining the initial path can be higher; the path is optimized by using the artificial potential field algorithm, so that the path planning is safer and smoother, and the efficiency of path planning can be further improved.

[0044] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 It is a flow chart of a path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field in the first embodiment of the present invention;

[0047] Figure 2 for Figure 1 Detailed flow chart of step S101;

[0048] Figure 3 for Figure 1 Detailed flow chart of step S103;

[0049] Figure 4 This is a schematic diagram of a circular sampling space in the first embodiment of the present invention;

[0050] Figure 5 Schematic diagram of the first target bias strategy in the first embodiment of the present invention;

[0051] Figure 6 Schematic diagram of the second target bias strategy in the first embodiment of the present invention;

[0052] Figure 7 for Figure 1 Detailed flow chart of step S104;

[0053] Figure 8 This is a schematic diagram of an elliptical sampling space in the first embodiment of the present invention;

[0054] Fig. 9 A schematic diagram of path planning based on an artificial potential field in the first embodiment of the present invention;

[0055] Fig.10 This is a diagram of the Informed RRT* algorithm path planning experiment in a simple environment in the first embodiment of the present invention;

[0056] Fig.11 This is a diagram of the path planning experiment of the improved Informed RRT* algorithm in a simple environment in the first embodiment of the present invention;

[0057] Fig.12 This is an experimental diagram of the path planning of the Informed RRT* algorithm under dense obstacles in the first embodiment of the present invention;

[0058] Fig.13 This is an experimental diagram of the improved Informed RRT* algorithm path planning under dense obstacles in the first embodiment of the present invention;

[0059] Fig.14 It is a structural block diagram of a path planning system based on Informed-RRT* fusion constraint sampling space and artificial potential field in the second embodiment of the present invention;

[0060] Fig.15 It is a structural block diagram of a computer device in the third embodiment of the present invention.

[0061] Description of main component symbols:

[0062]

[0063]

[0064] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0066] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0067] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0068] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0069] Embodiment 1

[0070] See also Figure 1 , which shows a path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field in the first embodiment of the present invention, and the method specifically includes steps S101 to S107:

[0071] S101, collecting environmental information of a target object, and constructing a grid map based on the environmental information;

[0072] For further information, please refer to Figure 2 , the step S101 specifically includes steps S1011 to S1012:

[0073] S1011, using an image sensor or a radar sensor of the mobile robot to collect obstacle sizes, obstacle positions, obstacle quantities, and obstacle distribution conditions within a preset field of view in front of the target object;

[0074] S1012, obtaining the current position information of the target object, and constructing a grid map of the target object based on the current position information, the size of the obstacle, the position of the obstacle, the number of obstacles, and the distribution of the obstacles.

[0075] In the specific implementation, the laser radar sensor or depth camera sensor of the mobile robot is used to collect environmental information around the target object (in this embodiment, the target object is a vehicle), and the environmental information includes the size, position, number, and distribution of obstacles. A grid map is established based on the current position information of the target object and the size, position, number, and distribution of the obstacles.

[0076] S102, marking each grid in the grid map as an obstacle space or a free space, and selecting a starting point and a target point in the marked grid map;

[0077] In the specific implementation, each grid in the above grid map is marked as an obstacle space or a free space, and a starting point x is selected in the marked grid map. start and the target point x goal .

[0078] S103, using the constrained sampling space strategy and the target bias strategy and fusing the Informed RRT* algorithm to obtain a fusion algorithm, and sampling in the free space of the grid map by using the fusion algorithm to obtain an initial path;

[0079] For further information, see Figure 3 , the step S103 specifically includes steps S1031 to S1032:

[0080] S1031, using a constrained sampling space strategy to speed up the iteration of the initial solution of the Informed RRT* algorithm to obtain a uniform circular sampling space, and performing sampling in the circular sampling space;

[0081] S1032: Use the target bias strategy to speed up the iteration of the Informed RRT* algorithm to obtain the initial path.

[0082] In the specific implementation, the constrained sampling space strategy is used to speed up the iteration of the initial solution. Specifically, before the InformedRRT* algorithm obtains the first path, the straight-line distance between the two points is calculated based on the starting point and the target point, and the midpoint of the straight line is calculated by the following formula. Then, the midpoint is used as the center of the circle and the starting point x is used as the starting point. start and the target point x goal A uniform circular area is planned with half of the line distance as the radius, that is, the circular sampling space (such as Figure 4 shown):

[0083]

[0084] In the formula, mid represents the midpoint, x1, y1 represent the known coordinates of the starting point, x2, y2 represent the coordinates of the target point, and x mid,y mid Indicates the desired center of the circle.

[0085] In the global environment, this application calculates the straight-line distance between the starting point (x1, y1) and the target point (x2, y2), and uses the above formula to find the midpoint of the straight line mid(x mid ,y mid ), and then plan a uniform circular area with the midpoint as the center O and half the distance between the starting point and the target point as the radius R.

[0086] A random tree is defined, and sampling is performed in the circular sampling space using the random tree.

[0087] Furthermore, the target probability P of the target point sampling is set goal , and when the current random sampling obtains the sampling point, randomly generates a current probability P of uniform sampling from the first interval (in this embodiment, the first interval is [0, 1]), and determines whether the current probability P is greater than the target probability P goal ;

[0088] If the current probability P is greater than the target probability P goal , then a current sampling point x is randomly generated in the above circular sampling space rand ;

[0089] If the current probability P is not greater than the target probability P goal , then the target point x goal As the current sampling point x rand ;

[0090] The expression of the current sampling point is:

[0091]

[0092] In the above formula, x rand represents the current sampling point, P represents the current probability, P goal represents the target probability, x goal Indicates the target point.

[0093] See also Figure 5 , after getting the current sampling point x rand After that, the next sampling is performed. In the next sampling process, a current probability and a corresponding sampling point are randomly generated, and it is judged whether the current probability obtained by the next sampling is greater than the target probability P goal ;

[0094] If the current probability obtained by the next sampling is not greater than the target probability P goal , then calculate the sampling point x obtained by the next sampling rand 1With the target point x above goal and determine whether the distance d1 is less than the sampling step length R;

[0095] If the distance d1 is less than the sampling step length R, it is determined that the sampling points of the two samples cannot be connected, and the next sampling is continued (such as Figure 6 As shown), until the distance d2 between two adjacent sampling points is not less than the sampling step length R, the sampling point of the last sampling is aligned with the target point x goal Connect them to get the initial path;

[0096] For example: Assuming that the distance d1 is less than the sampling step length R, continuing the next sampling will obtain a new sampling point x rand 2 And the sampling point x rand 2 With the target point x above goal If the distance d2 is not less than the sampling step R, the sampling point x rand 2 With the target point x above goal Connect them to get the initial path.

[0097] S104, after obtaining the initial path, using the fusion algorithm and the initial path to calculate an elliptical sampling space, and using an artificial potential field algorithm to perform sampling in the elliptical sampling space to obtain a first path;

[0098] For further information, see Figure 7 , the step S104 specifically includes steps S1041 to S1042:

[0099] S1041, taking the length of the initial path as the distance between two vertices of the ellipse, and taking the distance between the starting point and the target point as the distance between two foci of the ellipse;

[0100] S1042: construct an ellipse sampling space according to the distance between two vertices of the ellipse and the distance between two foci of the ellipse.

[0101] In the specific implementation, after the initial path is obtained, the length c of the initial path is best As the distance between the two vertices of the ellipse 2a, and the distance from the starting point to the end point c min The distance between the two foci of the ellipse is 2c, and then an ellipse sampling space is calculated by the following formula (see Figure 8 ):

[0102] The standard ellipse equation is:

[0103]

[0104] The focal coordinates are (±c, 0), the major axis length is a, and the minor axis length is b. They satisfy the following condition: the sum of the distances from any point on the ellipse to the two foci is equal to 2a. We can get:

[0105] a 2 -c 2 =b 2 ;

[0106] In the Informed-RRT* algorithm, starting point x start and the end point x goal As the focus of the ellipse, let a be equal to half the length of the initial path, that is, a = c best / 2, then c=c min / 2, All the parameters of the ellipse equation can be obtained.

[0107] In subsequent iterations, each time a shorter path is found, the length of this shorter path is used as the new c best , update the sampling ellipse.

[0108] Furthermore, sampling is performed in the elliptical sampling space to obtain a first path, and the sampling process is combined with an artificial potential field algorithm to make the path smoother and safer.

[0109] S105, optimizing the first path by combining the artificial potential field algorithm with the fusion algorithm to obtain an asymptotically optimal route that maintains a safe distance from obstacles;

[0110] For specific implementation, please refer to Fig. 9 , the first path is optimized by combining the artificial potential field algorithm with the above-mentioned fusion algorithm, so as to quickly obtain a smoother, safer and shorter path, that is, an asymptotically optimal route that keeps a safe distance from obstacles.

[0111] In this embodiment, an artificial potential field algorithm is used to generate a gravitational field at the target position and a repulsive field at the obstacle, so that the mobile robot can be safely guided to the target position under the action of the gravitational field and the repulsive field;

[0112] 1.1 Gravitational field

[0113] The purpose of the gravitational field is to attract the mobile robot to move to the target position. The gravitational potential function U att It is usually defined as:

[0114]

[0115] Where: α is the gravitational gain coefficient, q represents the current position, q g represents the target position, d(q,q g ) represents the distance from the current position to the target position.

[0116] The gravitational force at each point in the mobile robot's workspace can be obtained from the gravitational potential function gradient, and its gravitational force is expressed as:

[0117]

[0118] 1.2 Repulsive field

[0119] Repulsive potential function U rep The purpose is to generate a repulsive field around each obstacle in the robot's workspace. However, when the mobile robot is far enough away from the obstacle, it will not affect the movement of the mobile robot. Therefore, this paper defines the repulsive potential function as:

[0120]

[0121] Where η is the repulsion gain coefficient,

[0122] ρ(q) is the distance between point q and its nearest obstacle, and ρ0 is the obstacle distance threshold. Obstacles greater than this distance will not produce repulsive effects.

[0123] The repulsive force F generated by each obstacle rep It can be expressed as:

[0124]

[0125] After obtaining the initial path, the Informed RRT* algorithm compresses the sampling space into an elliptical sampling space, so that the algorithm performs sampling in the elliptical sampling space.

[0126] Then, when the Informed RRT* algorithm expands the node, it constructs the target gravity function F for the node att and obstacle repulsion function F rep , so that the extended random number can be safely extended toward the target point according to the trend guided by the potential field under the combined force of gravity and repulsion. This reduces the blindness and randomness of the search, improves the search efficiency, speeds up the convergence of the algorithm, and improves the smoothness of the path.

[0127] S106, updating the ellipse sampling space according to the asymptotic optimality route, and performing sampling in the updated ellipse sampling space to obtain an asymptotic optimality path;

[0128] In specific implementation, the above-mentioned asymptotic optimality route is used to update the ellipse sampling space, and sampling is performed in the updated ellipse sampling space to obtain a safer and better asymptotic optimality path.

[0129] S107, repeating the above step S106 for the asymptotically optimal path until the number of iterations is reached to obtain the final planned path of the target object.

[0130] In the specific implementation, the above-mentioned asymptotic optimality path repeats the above-mentioned step S106 until the number of iterations is reached to obtain the final planning path of the target object.

[0131] See also Fig.10 , shown is the experimental diagram of the Informed RRT* algorithm planned in a simple environment of a 50*50 map, where the black area represents the obstacle area, the white area is the feasible area, L2 (light line) is the final planned path, and L1 (dark line) is the trajectory finally obtained by the algorithm. Through the green trajectory, the study found that its sampling points are relatively loose and the path is relatively messy, which means that it is indeed randomly sampling in the entire global area at the beginning. Due to its randomness, the sampling points are scattered in the workspace, the path is very close to the obstacle area and the path is poor.

[0132] Please refer to 11, which shows the experimental diagram of the improved Informed RRT* algorithm proposed in this application in a simple environment of a 50*50 map. Fig.11 It can be observed that the sampled points and paths are very clustered, and the algorithm keeps moving toward the target position while maintaining a safe distance from obstacles. This shows that the improved algorithm of the present application can obtain the initial solution more easily in a simple environment, and the planned path is safer, the trajectory is smoother, and the path is better than the original Informed RRT* algorithm and the Goal-bias-Informed RRT* algorithm.

[0133] See also Fig.12 , which shows the experimental diagram of the Informed RRT* algorithm in a dense obstacle environment of a 50*50 map. Fig.12 It can be found that in a dense obstacle environment, the sampling of the Informed RRT* algorithm is still very scattered and messy, and the final planned trajectory is still not smooth and cannot maintain a safe distance from obstacles.

[0134] See also Fig.13 , which shows the experimental diagram of the planning of the improved Informed RRT* algorithm in this application in a dense obstacle environment of a 50*50 map. It can be found that in this dense obstacle environment, this algorithm can still quickly find an optimal path that is both safe and smooth. This shows that the improved algorithm in this application is still well applicable in complex situations such as dense obstacles and meets the conditions for the implementation of the algorithm.

[0135] In summary, the path planning method based on Informed-RRT* fusion constrained sampling space and artificial potential field in the above embodiments of the present invention reduces sampling randomness, compresses sampling space, improves the convergence efficiency of the initial solution, and introduces an artificial potential field to maintain a safe distance between the path and obstacles, so that the mobile robot can quickly find a smooth and excellent path while maintaining a safe distance from obstacles; specifically, by utilizing the constrained sampling space strategy and the target bias strategy, the number of randomly sampled nodes required can be reduced, the number of redundant nodes can be reduced, and the efficiency of obtaining the initial path can be higher; the path is optimized by utilizing the artificial potential field algorithm, so that the path planning is safer and smoother, and the efficiency of path planning can be further improved.

[0136] Embodiment 2

[0137] On the other hand, the present invention also proposes a path planning system based on Informed-RRT* fusion constraint sampling space and artificial potential field, see Fig.14 , which is shown as a path planning system in a second embodiment of the present invention, comprising:

[0138] A grid map construction module 11 is used to collect environmental information of a target object and construct a grid map based on the environmental information;

[0139] Furthermore, the grid map construction module 11 is specifically used for:

[0140] The image sensor or radar sensor of the mobile robot is used to collect the size, location, number and distribution of obstacles within the preset field of view in front of the target object;

[0141] The current position information of the target object is obtained, and a grid map of the target object is constructed based on the current position information, the size of the obstacle, the position of the obstacle, the number of obstacles, and the distribution of the obstacles.

[0142] A grid map marking module 12 is used to mark each grid in the grid map as an obstacle space or a free space, and select a starting point and a target point in the marked grid map;

[0143] A first sampling module 13 is used to utilize the constrained sampling space strategy and the target bias strategy and fuse the InformedRRT* algorithm to obtain a fusion algorithm, and to perform sampling in the free space of the grid map through the fusion algorithm to obtain an initial path;

[0144] Furthermore, the first sampling module 13 includes:

[0145] A first strategy unit is used to use a constrained sampling space strategy to speed up the iteration of the initial solution of the Informed RRT* algorithm, obtain a uniform circular sampling space, and perform sampling in the circular sampling space;

[0146] The second strategy unit is used to use the target bias strategy to speed up the iteration of the Informed RRT* algorithm to obtain the initial path.

[0147] Furthermore, the first strategy unit is specifically used for:

[0148] Calculate the midpoint of the straight-line distance between the starting point and the target point, and plan a uniform circular sampling space with the midpoint as the center and the straight-line distance as the diameter;

[0149] A random tree is defined, and sampling is performed in the circular sampling space using the random tree.

[0150] Furthermore, the second strategy unit is specifically used for:

[0151] Setting the target probability of sampling at the target point;

[0152] When the sampling point is currently randomly sampled, a current probability of uniformly sampling from the first interval is randomly generated, and it is determined whether the current probability is greater than the target probability;

[0153] If the current probability is greater than the target probability, a current sampling point is randomly generated in the circular sampling space;

[0154] If the current probability is not greater than the target probability, the target point is used as the current sampling point;

[0155] After obtaining the current sampling point, performing the next sampling, and determining whether the sampling points of the two samplings can be connected;

[0156] If the sampling points of the two samples can be connected, the sampling point of the second sampling is connected with the target point to obtain the initial path;

[0157] If the sampling points of two samplings cannot be connected, continue to perform the next sampling until the sampling points of two adjacent samplings can be connected, and connect the sampling point of the latter of the two adjacent samplings with the target point to obtain the initial path.

[0158] Furthermore, the second strategy unit is further used for:

[0159] Calculate the distance between the sampling point of the second sampling and the target point, and determine whether the distance is less than the sampling step size;

[0160] If the distance is less than the sampling step, it is determined that the sampling points of the two samples cannot be connected;

[0161] If the distance is not less than the sampling step length, it is determined that the sampling points of the two samples can be connected.

[0162] A second sampling module 14 is used to calculate an elliptical sampling space using the fusion algorithm and the initial path after obtaining the initial path, and to perform sampling in the elliptical sampling space using an artificial potential field algorithm to obtain a first path;

[0163] Furthermore, the second sampling module 14 is specifically used for:

[0164] The length of the initial path is taken as the distance between the two vertices of the ellipse, and the distance between the starting point and the target point is taken as the distance between the two foci of the ellipse;

[0165] An ellipse sampling space is constructed according to the distance between the two vertices of the ellipse and the distance between the two foci of the ellipse.

[0166] A path optimization module 15, configured to optimize the first path by combining the artificial potential field algorithm with the fusion algorithm to obtain an asymptotically optimal route that maintains a safe distance from obstacles;

[0167] A third sampling module 16, configured to update the ellipse sampling space according to the asymptotic optimality route, and perform sampling in the updated ellipse sampling space to obtain an asymptotic optimality path;

[0168] The path planning module 17 is used to repeat the above step 6 for the asymptotically optimal path until the number of iterations is reached to obtain the final planned path of the target object.

[0169] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and will not be repeated here.

[0170] The path planning system provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0171] Embodiment 3

[0172] The present invention also provides a computer device, see Fig.15, shown is a computer device in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field is implemented.

[0173] Among them, the memory 10 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 10 may be an internal storage unit of the vehicle in some embodiments, such as a hard disk of the vehicle. The memory 10 may also be an external storage device in other embodiments, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Further, the memory 10 may also include both an internal storage unit of the vehicle and an external storage device. The memory 10 may be used not only to store application software and various types of data installed in the vehicle, but also to temporarily store data that has been output or is to be output.

[0174] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs, etc.

[0175] It should be pointed out that Fig.15 The structure shown does not constitute a limitation on the computer device. In other embodiments, the computer device may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0176] An embodiment of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field as described above.

[0177] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a system based on a computer device, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0178] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer device memory.

[0179] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0180] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0181] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A path planning method based on Informed-RRT* fusion constraint sampling space and artificial potential field, characterized in that: The following steps are involved: Step 1: Collect environmental information of the target object and construct a grid map based on the environmental information; Step 2: Mark each grid in the grid map as an obstacle space or a free space, and select a starting point and a target point in the marked grid map; Step 3: Using the constrained sampling space strategy and the target bias strategy and fusing the Informed RRT* algorithm to obtain a fusion algorithm, and sampling in the free space of the grid map through the fusion algorithm to obtain an initial path, wherein the step 3 includes: Using a constrained sampling space strategy to speed up the iteration of the initial solution of the Informed RRT* algorithm, obtaining a uniform circular sampling space, and performing sampling in the circular sampling space; Using the target bias strategy to speed up the iteration of the Informed RRT* algorithm to obtain the initial path; The steps of using a constrained sampling space strategy to speed up the iteration of the initial solution of the Informed RRT* algorithm to obtain a uniform circular sampling space and sampling in the circular sampling space include: Calculate the midpoint of the straight-line distance between the starting point and the target point, and plan a uniform circular sampling space with the midpoint as the center and the straight-line distance as the diameter; defining a random tree, and using the random tree to perform sampling in the circular sampling space; The step of using the target bias strategy to speed up the iteration of the Informed RRT* algorithm to obtain the initial path includes: Setting the target probability of sampling at the target point; When the sampling point is currently randomly sampled, a current probability of uniformly sampling from the first interval is randomly generated, and it is determined whether the current probability is greater than the target probability; If the current probability is greater than the target probability, a current sampling point is randomly generated in the circular sampling space; If the current probability is not greater than the target probability, the target point is used as the current sampling point; After obtaining the current sampling point, performing the next sampling, and determining whether the sampling points of the two samplings can be connected; If the sampling points of the two samples can be connected, the sampling point of the second sampling is connected with the target point to obtain the initial path; If the sampling points of two samplings cannot be connected, continue to perform the next sampling until the sampling points of two adjacent samplings can be connected, and connect the sampling point of the latter of the two adjacent samplings with the target point to obtain the initial path; The step of determining whether the sampling points of two samples can be connected comprises: Calculate the distance between the sampling point of the second sampling and the target point, and determine whether the distance is less than the sampling step size; If the distance is less than the sampling step, it is determined that the sampling points of the two samples cannot be connected; If the distance is not less than the sampling step length, it is determined that the sampling points of the two samples can be connected; Step 4: After obtaining the initial path, use the fusion algorithm and the initial path to calculate an elliptical sampling space, and use an artificial potential field algorithm to perform sampling in the elliptical sampling space to obtain a first path; Step 5: Optimizing the first path by combining the artificial potential field algorithm with the fusion algorithm to obtain an asymptotically optimal route that maintains a safe distance from obstacles; Step 6: updating the ellipse sampling space according to the asymptotic optimality route, and sampling in the updated ellipse sampling space to obtain the asymptotic optimality path; Step 7: Repeat the above step 6 for the asymptotically optimal path until the number of iterations is reached to obtain the final planned path of the target object.

2. The path planning method according to claim 1, characterized in that: The step one comprises: The mobile robot's built-in image sensor or radar sensor is used to collect the size, location, number and distribution of obstacles within a preset field of view in front of the target object; The current position information of the target object is obtained, and a grid map of the target object is constructed based on the current position information, the size of the obstacle, the position of the obstacle, the number of obstacles, and the distribution of the obstacles.

3. The path planning method according to claim 1, characterized in that: The fourth step comprises: The length of the initial path is taken as the distance between the two vertices of the ellipse, and the distance between the starting point and the target point is taken as the distance between the two foci of the ellipse; An ellipse sampling space is constructed according to the distance between the two vertices of the ellipse and the distance between the two foci of the ellipse.

4. The path planning method according to claim 1, characterized in that: The midpoint calculation formula is: In the formula, mid represents the midpoint, x1, y1 represent the known coordinates of the starting point, x2, y2 represent the coordinates of the target point, and x mid ,y mid Indicates the desired center of the circle.

5. The path planning method according to claim 1, characterized in that: The expression of the current sampling point is: In the formula, x rand represents the current sampling point, P represents the current probability, P goal represents the target probability, x goal Indicates the target point.

Images