Unmanned vehicle cluster path point generation method and device based on road network, and medium
By abstracting the road map into an undirected graph and correcting the starting point and target point, and combining the A* algorithm for path search and expansion, the path point generation problem of multi-unmanned vehicle formations in road environment is solved, achieving efficient Path planning and formation maintenance.
Patent Information
- Application Number
- CN202410920124.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-26
AI Technical Summary
The prior art is difficult to effectively solve the problems of correction, searching and driving path point solving of multi-unmanned vehicle formation path points in road environments, especially when the starting point and target point are not on the road network.
By abstracting the road map into an undirected graph, modifying and remapping the starting point and target point, changing it to the point on the road network closest to the specified point, and using the A* algorithm to search and expand the shortest path to generate multiple The path points of the unmanned vehicles ensure the maintenance and transformation of formations.
The efficiency of multi-unmanned vehicle path planning is achieved, the time required for path planning is reduced, and the situation of unsolvable planning is avoided. It ensures that the unmanned vehicle clusters drive in the designated formation on the road, and can flexibly adjust and restore teams. shape, especially at the turn.
Smart Images

Figure CN119024832A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of robot formation technology, and in particular to a method, device and medium for generating path points of an unmanned vehicle cluster based on a road network. Background Art
[0002] In recent years, with the development of robotics technology and the in-depth study of multi-agent system theory, multi-unmanned vehicle formations have been widely used in industrial production fields such as warehousing and handling, logistics and distribution. In the military field, a lot of research has also been carried out in the fields of path planning and regional exploration in complex environments based on multi-unmanned vehicle formations. In actual environments, when performing tasks such as high-speed travel, search, and reconnaissance, multiple unmanned vehicles need to perform a series of actions on a given passable road, including maintaining and changing formations, to ensure that the task is completed efficiently without collision. The generation of formation path points plays a vital role in maintaining formation, changing formations, and planning and controlling multi-unmanned vehicle formations.
[0003] At present, domestic and foreign scholars have conducted extensive research on multi-unmanned vehicle formation and planning, focusing on formation planning methods based on local vision and speed planning, etc. These methods can effectively solve the problem of multiple unmanned vehicles tracking the desired formation. However, when the given starting point and target point are not on the road network, how to effectively solve the correction of the path points of the multi-unmanned vehicle formation in the road environment, search for feasible path points, and calculate the driving path points of each unmanned vehicle, there is no relevant technology. Summary of the invention
[0004] In view of this, the present invention provides a method, device and medium for generating path points of an unmanned vehicle cluster based on a road network, which can realize the correction and generation of path points of multiple unmanned vehicles, and the maintenance and transformation of formations.
[0005] To achieve the above purpose, the present invention provides the following technical solutions:
[0006] A method for generating path points of an unmanned vehicle cluster based on a road network comprises the following steps:
[0007] Step 1: According to the starting point and target point of the specified task and the topological map, the global path point is corrected, searched and expanded; wherein the starting point and target point are corrected and changed to the point on the road network closest to the specified point;
[0008] Step 2: Take the first control point F1 obtained in step 1 as the initial formation assembly point. According to the target formation, the target assembly point of each unmanned vehicle is calculated by the expected distance of multiple unmanned vehicles relative to the formation control point F1. After that, each unmanned vehicle drives to the target point according to the speed and angular velocity provided by the controller to form an initial formation.
[0009] Step 3: After the multiple unmanned vehicles are assembled in formation, the coordinates of the next control point in the control point set obtained in step 1 are first used as the next center point of the multi-unmanned vehicle formation, and then the target assembly point of each unmanned vehicle is solved according to the method in step 2. Then, the controller is used to control each unmanned vehicle to drive to its corresponding target assembly point; when the unmanned vehicle is driving in a straight line on the road, the speed increases from 0 to the maximum speed v max And maintain the maximum speed, keep the initial formation unchanged during the driving process, and the formation center point O always moves on the edge of the topological map.
[0010] In step 2, the control points F1 on the edge (A, B) are assembled in an isosceles triangle formation, and each unmanned vehicle target assembly point P1 (x P ,y P ), Q1(x Q ,y Q ), R1(x R ,y R ) is calculated as follows:
[0011] (1) First, the angle θ between the edge where the formation center point O is located and the X-axis is calculated based on the vertex coordinates A(x1,y1) and B(x2,y2) of the edge (A,B):
[0012]
[0013] (2) Based on the geometric relationship, the coordinates of each unmanned vehicle target assembly point P1, Q1, and R1 are calculated as follows:
[0014]
[0015]
[0016] Among them, the coordinates of the formation control point F1(x F ,y F ), the distance d1 between the top corner unmanned vehicle and the center of the formation, the distance d2 between the bottom corner unmanned vehicle and the center of the formation, and the angle between the line connecting the bottom corner unmanned vehicle and the center of the formation and the formation direction
[0017] Among them, in the step 1, the entire road map is abstracted into an undirected graph, and the road is abstracted into the edge of the undirected graph. The undirected graph is represented by G(V,E), where V represents the set of all vertices in the undirected graph, and E represents the set of all edges in the undirected graph; then the starting point and the target point are corrected when the given starting point and the target point are outside the road: first, the vertical distance from the given point to each edge of the undirected graph is calculated, and then the foot of the perpendicular corresponding to the minimum value is selected as the new given point, and it is used as the new vertex of the undirected graph to complete the augmentation of the undirected graph.
[0018] Among them, in step 1, the specific correction process is: in an undirected graph, each edge is represented by an unordered pair of two vertices, V = {A, B, C} is the set of all vertices, E = {(A, B), (B, C)} is the set of all edges; let n be the number of edges in the undirected graph, and calculate the distance from the starting point S and the target point T to each edge E respectively. i The vertical distance l S1 ,l S2 ,...,l Sn and l T1 ,l T2 ,...,l Tn , take the minimum value l S_min =min{l S1 ,l S2 ,...,l Sn} and l T_min =min{l T1 ,l T2 ,...,l Tn}The corresponding edge is taken as the mapping target, and the foot of the perpendicular line from the point to the edge is taken as the corrected starting point S' and target point T';
[0019] For the starting point S(x S ,y S ) and edge (A,B), calculated as follows:
[0020] Assume A(x1,y1), B(x2,y2), C(x3,y3), then the distance from point S to edge (A,B) is:
[0021]
[0022] The distance from point S to edge (B,C) is:
[0023]
[0024] After calculating the distance from point S to all edges, the minimum distance is:
[0025] l S_min =min{l S1 ,l S2}
[0026] The destination point is remapped in the same way as the origin point.
[0027] Among them, in the step 1, the specific process of augmentation is:
[0028] After obtaining the remapped starting point S' and target point T', the topological map is augmented. Specifically, S' and T' are added to the original undirected graph G(V,E) as new vertices. Each new vertex divides the original edge into two segments as two new edges to complete the augmentation of the undirected graph. The new undirected graph is denoted as G'(V',E'), where the vertex set V'={A,S',B,T',C} and the edge set E'={(A,S'),(S',B),(B,T'),(T',C)}.
[0029] Wherein, in step 1, the A* algorithm or the optimized or improved A* algorithm is used to search for the shortest path, and the search result is a series of path points Path={S', B, T'}, which are composed of multiple vertices in an undirected graph.
[0030] Among them, in step 1, the specific process of expansion is:
[0031] A certain distance L is extended in both directions along the side where the path point is located. The starting point and the target point are only extended along one side of the path. The size of the extended distance L is designed according to the distance between the front and rear vehicles, and a series of control points Control_points = {F1, D, F2, E} are obtained. The control point is the point where the formation state is changed.
[0032] Wherein, in step 3, if the road turning point B is encountered, the following operations are performed:
[0033] (1) When the center point O of the formation reaches the control point D, which is the closest to the vertex of the map at the turning point, that is, point B, the speed is reduced to 0;
[0034] (2) Similar to the calculation method in step 2, each unmanned vehicle calculates the three target assembly points P2, Q2, and R2 around the next formation assembly point F2 based on the relative position relationship of the formation;
[0035] (3) Each unmanned vehicle drives along the planned route until all arrive at the corresponding target assembly point, at which time the initial formation is restored;
[0036] (4) The multi-unmanned vehicle formation follows the above rules and travels along the planned path Path = {S', B, T'} and control points Control_points = {F1, D, F2, E} until the formation center point O reaches the last control point E and stops.
[0037] The present invention also provides an electronic device, which includes a processor and a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the road network-based unmanned vehicle cluster path point generation method described in the present invention.
[0038] The present invention also provides a computer-readable storage medium, which stores a computer program, and the computer program is used to execute the method for generating path points of an unmanned vehicle cluster based on a road network described in the present invention.
[0039] Beneficial effects:
[0040] 1. The method of the present invention realizes the path planning and formation of multiple unmanned vehicles, wherein the correction and generation of the path points of multiple unmanned vehicles can reduce the time required for path planning and avoid the situation where the planning is unsolvable; the driving of multiple unmanned vehicles in formation can ensure that the unmanned vehicle cluster drives in a certain formation on the road, and can flexibly adjust the formation at the turn, and restore the formation in time after the turn. In the road environment, the present invention can ensure that multiple unmanned vehicles maintain a certain formation along the road by solving the driving path points of each vehicle, and can flexibly adjust the formation at the turn, and restore the formation in time after the turn.
[0041] 2. In the method of the present invention, the path point generation and formation of the unmanned vehicle cluster are realized based on the road network. The road map is represented by an undirected graph, and the starting point and target point correction method when the given starting point and target point are outside the road is used to complete the augmentation of nodes and edges in the undirected graph. Combined with the shortest path search and the target point solution of multiple unmanned vehicles, the unmanned vehicle cluster can move in a specified formation on the road.
[0042] 3. Compared with the formation method in the traditional environment, the present invention takes into account the formation path point generation of multiple unmanned vehicles in the road environment, and can solve the formation problem of unmanned vehicles in multi-scenario road environments. In the road environment, if the starting point and target point of multiple unmanned vehicles are not on any road, the nearest neighbor road is searched, and the starting point and target point are remapped to the road closest to them to obtain new initial points and target points. Compared with the traditional path point planning method, this process will reduce the time required for path planning and avoid the situation where planning has no solution.
[0043] 4. The device of the present invention is used to implement the method of the present invention. The correction and generation of path points of multiple unmanned vehicles can reduce the time required for path planning and avoid the situation where planning has no solution. The platoon driving of multiple unmanned vehicles can ensure that the unmanned vehicle cluster drives in a certain formation on the road, and can flexibly adjust the formation at the turn, and restore the formation in time after the turn.
[0044] 5. The medium of the present invention is used to implement the method of the present invention. The correction and generation of path points of multiple unmanned vehicles can reduce the time required for path planning and avoid the situation where planning has no solution; the platoon driving of multiple unmanned vehicles can ensure that the unmanned vehicle cluster drives in a certain formation on the road, and can flexibly adjust the formation at the turn, and restore the formation in time after the turn. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 This is a flow chart of formation assembly and driving in the method of an embodiment of the present invention.
[0046] Figure 2 The figure is a schematic diagram of the path point correction and generation process according to an embodiment of the present invention.
[0047] Figure 3 Schematic diagram of remapping of the starting point and the target point in an embodiment of the present invention.
[0048] Figure 4 Schematic diagram of the shortest path search and expansion results in an embodiment of the present invention.
[0049] Figure 5 Schematic diagram of calculation of assembly points of each unmanned vehicle formation in an embodiment of the present invention.
[0050] Figure 6 Schematic diagram of an unmanned vehicle turning in an embodiment of the present invention.
[0051] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0052] The present invention is described in detail below with reference to the accompanying drawings and embodiments.
[0053] The present invention provides a method for generating path points of unmanned vehicle clusters based on a road network. The formation assembly and driving process are as follows: Figure 1 As shown, the method of the present invention comprises the following steps:
[0054] Step 1: According to the starting point and target point of the specified task and the topological map, global path point correction, search and expansion are performed.
[0055] Specifically, in a road environment, it is stipulated that multiple unmanned vehicles should travel along the road network, but the starting point and target point issued by the task are often not necessarily on the road network. This requires the starting point and target point to be corrected (remapped), that is, to change them to the points on the road network closest to the specified point. In this embodiment, the entire road map is abstracted into an undirected graph, and the roads are abstracted into the edges of the undirected graph. The undirected graph is represented by G(V,E), where V represents the set of all vertices in the undirected graph, and E represents the set of all edges in the undirected graph. Then, based on this assumption, the correction of the starting point and target point is proposed when the given starting point and target point are outside the road. The process is as follows: Figure 2 First, calculate the vertical distance from the given point to each edge of the undirected graph, then select the foot of the perpendicular corresponding to the minimum value as the new given point, and use it as the new vertex of the undirected graph to complete the augmentation of the undirected graph. The implementation method is as follows:
[0056] (1)Amendment:
[0057] Define the given road network as an undirected graph G(V,E), and define the roads in the road network as the edges of the undirected graph. In an undirected graph, each edge is represented by an unordered pair of two vertices (e.g. (A,B)), V = {A,B,C} is the set of all vertices, and E = {(A,B), (B,C)} is the set of all edges. Let n be the number of edges in the undirected graph, and calculate the distance from the starting point S and the target point T to each edge E respectively. i The vertical distance l S1 ,l S2 ,...,l Sn and l T1 ,l T2 ,...,l Tn , take the minimum value l S_min =min{l S1 ,l S2 ,...,l Sn} and l T_min =min{l T1 ,l T2 ,...,l Tn} is used as the mapping target, and the foot of the perpendicular line from the point to the edge is used as the corrected starting point S' and target point T'. The starting point and target point are remapped as follows Figure 3 As shown, starting point S(x S ,y S ) and edge (A, B) as an example, the calculation method is as follows: Let A(x1, y1), B(x2, y2), C(x3, y3), then the distance from point S to edge (A, B) is:
[0058]
[0059] The distance from point S to edge (B,C) is:
[0060]
[0061] After calculating the distance from point S to all edges, the minimum distance is:
[0062] l S_min =min{l S1 ,l S2} (3)
[0063] The destination point is remapped in the same way as the origin point.
[0064] (2) Expansion:
[0065] After obtaining the remapped starting point S' and target point T', the topological map is augmented. Specifically, S' and T' are added to the original undirected graph G(V,E) as new vertices. Each new vertex divides the original edge into two segments as two new edges to complete the augmentation of the undirected graph. The new undirected graph is denoted as G'(V',E'), where the vertex set V'={A,S',B,T',C} and the edge set E'={(A,S'),(S',B),(B,T'),(T',C)}.
[0066] (3) Search:
[0067] The A* algorithm is used to search for the shortest path. The search result is a series of path points Path = {S', B, T'}, which are composed of multiple vertices in an undirected graph.
[0068] (4) Extension:
[0069] The searched path point Path is extended along the road direction, that is, a certain distance L is extended in both directions along the side where the path point is located. The starting point and the target point are only extended along one side of the path. The size of the extended distance L is designed according to the distance between the front and rear vehicles, and a series of control points Control_points = {F1, D, F2, E} are obtained. The control point is the point where the formation state is changed, including assembly, transformation, stop, etc. The shortest path search and expansion results are as follows: Figure 4 shown.
[0070] Step 2: Multiple unmanned vehicle formations autonomously maneuver to form an initial formation, as follows:
[0071] The first control point F1 obtained in step 1 is used as the initial formation assembly point. According to the target formation, the target assembly point of each unmanned vehicle is calculated by the expected distance of multiple unmanned vehicles relative to the formation control point F1. After that, each unmanned vehicle drives to the target point according to the speed and angular velocity provided by the controller to form an initial formation.
[0072] Taking the isosceles triangle formation as an example, the control point F1 on the edge (A, B) is known according to the formation requirements: the coordinates of the formation control point (center point) F1 (x F ,y F ), the distance d1 between the top corner unmanned vehicle and the center of the formation, the distance d2 between the bottom corner unmanned vehicle and the center of the formation, and the angle between the line connecting the bottom corner unmanned vehicle and the center of the formation and the formation direction Then the target assembly point P1(x P ,y P ), Q1(x Q ,y Q ), R1(x R ,y R) is calculated as follows:
[0073] (1) First, calculate the angle θ between the edge where the formation center point O is located and the X-axis based on the vertex coordinates A(x1,y1) and B(x2,y2) of the edge (A,B)
[0074]
[0075] (2) Based on the geometric relationship, the coordinates of each unmanned vehicle target assembly point P1, Q1, and R1 are calculated as follows:
[0076]
[0077] The calculation of each unmanned vehicle formation assembly point is as follows Figure 5 shown.
[0078] Step 3: Multiple unmanned vehicles drive along the generated path points in a fixed formation:
[0079] After the multiple unmanned vehicles are assembled in formation, the coordinates of the next control point in the control point set obtained in step 1 are first used as the next center point of the multi-unmanned vehicle formation, and then the target assembly point of each unmanned vehicle is solved according to the method in step 2. Then, the controller is used to control each unmanned vehicle to drive to its corresponding target assembly point. When the unmanned vehicle is driving in a straight line on the road, the speed increases from 0 to the maximum speed v max And maintain the maximum speed, keep the initial formation unchanged during driving, and keep the formation center O always moving on the edge of the topological map. If you encounter a road turning point, take point B as an example, do the following:
[0080] (1) When the formation center point O reaches the control point (point D) closest to the map vertex (point B) at the turning point, the speed is reduced to 0.
[0081] (2) Similar to the calculation method in step 2, each unmanned vehicle calculates the three target assembly points P2, Q2, and R2 around the next formation assembly point (point F2) based on the relative position relationship of the formation.
[0082] (3) Each unmanned vehicle drives along the planned route until all arrive at the corresponding target assembly point, at which time the initial formation is restored.
[0083] (4) The multi-unmanned vehicle formation follows the above rules and travels along the planned path Path = {S', B, T'} and control points Control_points = {F1, D, F2, E} until the formation center point O reaches the last control point E and stops.
[0084] Furthermore, when searching for the shortest path, an optimized or improved A* algorithm can be used; in the initial assembly formation, other formations such as a straight line or an inverted triangle can be selected. The method of the present invention can be applied to single-vehicle autonomous maneuvers and multi-vehicle following tasks after global path point correction, augmentation, and search.
[0085] The embodiment of the present application also provides an electronic device, Figure 7 The structure of the electronic device provided by the embodiment of the present invention is shown. For example, the electronic device 70 may include a processor 71, a memory 72 and a transmission device 73. The processor 71 is used to execute the unmanned vehicle cluster path point generation method based on the road network mentioned in the above embodiment, wherein the processor and the memory may be connected by a bus or other means, taking the bus connection as an example. The transmission device may be connected to the processor and the memory by wire or wirelessly. The memory, as a non-transient computer-readable storage medium, may be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the unmanned vehicle cluster path point generation method based on the road network in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the unmanned vehicle cluster path point generation method based on the road network in the above method embodiment is realized. The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The one or more modules are stored in the memory, and when executed by the processor, the method for generating path points of unmanned vehicle clusters based on a road network in the embodiment is executed.
[0086] As another aspect, the present application also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the device described in the above embodiment; or it may be a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium may be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method for generating path points for unmanned vehicle clusters based on a road network described in the present application.
[0087] In summary, the above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for generating path points for unmanned vehicle clusters based on road networks. It is characterized in that The steps include: Step 1: According to the starting point and target point of the specified task and the topological map, the global path point is corrected, searched and expanded; wherein the starting point and target point are corrected and changed to the point on the road network closest to the specified point; Step 2: The first control point F obtained in step 1 1 As the initial formation assembly point, according to the target formation formation, multiple unmanned vehicles are relative to the formation control point F 1 The target assembly point of each unmanned vehicle is calculated by the expected distance, and then each unmanned vehicle drives to the target point according to the speed and angular velocity provided by the controller to form an initial formation; Step 3: After the multiple unmanned vehicles are assembled in formation, the coordinates of the next control point in the control point set obtained in step 1 are first used as the next center point of the multi-unmanned vehicle formation, and then the target assembly point of each unmanned vehicle is solved according to the method in step 2. Then, the controller is used to control each unmanned vehicle to drive to its corresponding target assembly point; when the unmanned vehicle is driving in a straight line on the road, the speed increases from 0 to the maximum speed v max And maintain the maximum speed, keep the initial formation unchanged during the driving process, and the formation center point O always moves on the edge of the topological map.
2. The method according to claim 1, It is characterized in that In step 2, the control point F on the edge (A, B) 1 Gather in an isosceles triangle formation, each unmanned vehicle targets the assembly point P 1 (x P ,y P ), Q 1 (x Q ,y Q ), R 1 (x R ,y R ) is calculated as follows: (1) First, according to the vertex coordinates A(x 1 ,y 1 ), B(x 2 ,y 2 ) Calculate the angle θ between the side where the formation center point O is located and the X-axis as: (2) According to the geometric relationship, calculate the target assembly point P of each unmanned vehicle separately 1 ,Q 1 ,R 1 The coordinates are as follows: Among them, the coordinates of the formation control point F 1 (x F ,y F ), the distance d between the top corner unmanned vehicle and the center of the formation 1 , the distance d between the bottom corner unmanned vehicle and the center of the formation 2 , the angle between the line connecting the bottom corner unmanned vehicle and the center point of the formation and the formation direction 3. The method according to claim 1 or 2, Features In the step 1, the entire road map is abstracted into an undirected graph, and the road is abstracted into the edge of the undirected graph. The undirected graph is represented by G(V,E), where V represents the set of all vertices in the undirected graph, and E represents the set of all edges in the undirected graph; then the starting point and the target point are corrected when the given starting point and the target point are outside the road: first, the vertical distance from the given point to each edge of the undirected graph is calculated, and then the foot of the perpendicular corresponding to the minimum value is selected as the new given point, and it is used as the new vertex of the undirected graph to complete the augmentation of the undirected graph.
4. The method according to claim 3, It is characterized in that In step 1, the specific correction process is as follows: in an undirected graph, each edge is represented by an unordered pair of two vertices, V = {A, B, C} is the set of all vertices, E = {(A, B), (B, C)} is the set of all edges; let n be the number of edges in the undirected graph, and calculate the distance from the starting point S and the target point T to each edge E respectively. i The vertical distance l S1 ,l S2 ,…,l Sn and l T1 ,l T2 ,…,l Tn , take the minimum value l S_min =min{l S1 ,l S2 ,…,l Sn } and l T_min =min{l T1 ,l T2 ,…,l Tn }The corresponding edge is taken as the mapping target, and the foot of the perpendicular line from the point to the edge is taken as the corrected starting point S' and target point T'; For the starting point S(x S ,y S ) and edge (A,B), calculated as follows: Let A(x 1 ,y 1 ), B(x 2 ,y 2 ), C(x 3 ,y 3 ), then the distance from point S to edge (A,B) is: The distance from point S to edge (B,C) is: After calculating the distance from point S to all edges, the minimum distance is: L S_min =min{l S1 ,L S2 } The destination point is remapped in the same way as the origin point.
5. The method according to claim 4, It is characterized in that In step 1, the specific process of augmentation is: after obtaining the remapped starting point S' and target point T', the topological map is augmented. Specifically, S' and T' are added to the original undirected graph G(V,E) as new vertices. Each new vertex divides an original edge into two segments as two new edges, completing the augmentation of the undirected graph. The new undirected graph is denoted as G'(V',E'), where the vertex set V'={A,S',B,T',C}, and the edge set E'={(A,S'),(S',B),(B,T'),(T',C)}.
6. The method according to claim 5, It is characterized in that In step 1, the A* algorithm or the optimized or improved A* algorithm is used to search for the shortest path, and the search result is a series of path points Path={S', B, T'}, which are composed of multiple vertices in an undirected graph.
7. The method according to claim 6, It is characterized in that In step 1, the specific process of expansion is: extending a certain distance L along the two directions of the edge where the path point is located, the starting point and the target point are only extended along one side of the path, and the size of the extended distance L is designed according to the distance between the front and rear vehicles, and a series of control points Control_points = {F 1 ,D,F 2 ,E}, the control point is the point where the formation state is changed.
8. The method according to claim 7, It is characterized in that In step 3, if the road turning point B is encountered, the following operations are performed: (1) When the center point O of the formation reaches the control point D, which is the closest to the vertex of the map at the turning point, that is, point B, the speed is reduced to 0; (2) Similar to the calculation method in step 2, each unmanned vehicle calculates the next formation assembly point F according to the relative position relationship of the formation. 2 Three target gathering points P around point 2 ,Q 2 ,R 2 ; (3) Each unmanned vehicle drives along the planned route until all arrive at the corresponding target assembly point, at which time the initial formation is restored; (4) The multi-unmanned vehicle formation follows the above rules and moves along the planned path Path = {S', B, T'} and control points Control_points = {F 1 ,D,F 2 ,E} until the formation center point O reaches the last control point E and stops.
9. An electronic device, It is characterized in that The electronic device includes a processor and a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the road network-based unmanned vehicle cluster path point generation method as described in any one of claims 1 to 8 above.
10. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, and the computer program is used to execute the method for generating path points of an unmanned vehicle cluster based on a road network as described in any one of claims 1 to 8 above.
Citation Information
Cited By
Unmanned vehicle formation path planning method considering multiple factors
CN120445243A
A multi-factor considering unmanned vehicle formation path planning method
CN120445243B
