A path planning method and device

Abstract

This invention discloses a path planning method and apparatus, relating to the field of path planning technology. The specific implementation of this invention includes: dividing the passable area between a target starting point and a target ending point into multiple segments; sequentially performing a reverse path search for each segment to obtain the nodes included in the segment and calculating the first cumulative distance from each node to the end point of the segment, establishing a mapping relationship between each node and the minimum first cumulative distance, and performing a forward path search based on the mapping relationship to obtain the target short path from the starting point to the end point of the segment; and sequentially concatenating the target short paths corresponding to multiple segments to obtain a long path from the target starting point to the target ending point. This implementation overcomes the drawbacks of traditional long path planning, such as high computational load, low search efficiency, and slow response, thereby achieving a balance between path planning speed and planning quality while maintaining path optimality (or suboptimality).

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and in particular to a path planning method and apparatus. Background Technology

[0002] Existing path planning typically employs a two-layer solution architecture: the bottom layer plans the complete long path from the start point to the end point in one go, the upper layer adds constraints after detecting path conflicts, and the bottom layer replans the entire path again; in addition, the current rolling segmented path planning method still requires a complete long path search during replanning.

[0003] Existing long-path planning methods have significant drawbacks: 1. Increased vehicle and path lengths lead to a sharp increase in computational complexity, making it difficult to meet real-time scheduling requirements; 2. A The algorithm relies on Manhattan / Euclidean distance as a heuristic, which leads to large estimation biases, resulting in a large number of invalid searches and low pathfinding efficiency; 3. When the environment changes dynamically, the entire path needs to be recalculated, which is not flexible enough and has a slow response; 4. Long pathfinding consumes a lot of computing power and memory, making it difficult to implement in resource-constrained scenarios.

[0004] In summary, existing technologies are limited by repeated planning of long paths and insufficient heuristic accuracy, and there is an urgent need for improved path planning solutions. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a path planning method and apparatus, which overcomes the drawbacks of large computational load, low search efficiency and slow response in traditional long path planning by segmenting to reduce the path search scale, constructing realistic heuristics through reverse search and fast forward path finding. Thus, while maintaining the optimality (or suboptimality) of the path, a balance is achieved between the speed and quality of path planning.

[0006] To achieve the above objectives, according to one aspect of the present invention, a path planning method is provided, comprising: dividing a passable area between a target starting point and a target ending point into multiple segments, each segment having a fixed starting point and an ending point, wherein the starting point of the first segment is the target starting point, the ending point of the last segment is the target ending point, and the ending point of the preceding segment is the starting point of the next adjacent segment. For each segment, reverse path search is performed sequentially to obtain each node included in the segment and calculate the first cumulative distance from each node to the end of the segment. A mapping relationship is established between each node and the minimum first cumulative distance. Based on the mapping relationship, forward path search is performed to obtain the target short path from the start of the segment to the end of the segment. By sequentially concatenating the target short paths corresponding to the multiple segments, a long path is obtained from the target starting point to the target ending point.

[0007] Optionally, dividing the passable area between the target starting point and the target ending point into multiple segments includes: Identify all passable nodes within the passable area; Based on the preset sampling distance, multiple path points are determined from the passable nodes; The passable area is divided into multiple segments using the target starting point, the target ending point, and multiple waypoints as segmentation nodes.

[0008] Optionally, the step of sequentially performing a reverse path search for each segment to obtain all nodes included in the segment and calculating the first cumulative distance from each node to the end point of the segment includes: Starting from the end of the segment, traverse in reverse order all nodes included in the segment, and determine the actual distance between each pair of adjacent nodes based on the traversal results; Based on the actual distance, calculate the first cumulative distance from each node to the endpoint of the segment.

[0009] Optionally, establishing the mapping relationship between each node and the minimum first cumulative distance includes: A heuristic function is constructed based on the mapping relationship. Each node is used as the input of the heuristic function. The heuristic function is used to determine the minimum first cumulative distance corresponding to the input node and output the minimum first cumulative distance as the heuristic value of the heuristic function.

[0010] Optionally, the step of performing a forward path search based on the mapping relationship to obtain the target shortest path from the start point to the end point of the segment includes: Starting from the beginning of the segment, perform a forward path search and determine the adjacent nodes of the starting point of the segment among the nodes of the segment. Based on the heuristic values ​​corresponding to the adjacent nodes, the target node is determined from the adjacent nodes; Next, identify the adjacent nodes of the target node and repeat the previous step until the identified target node is the end point of the segment. By connecting the starting point of the segment and all target nodes in sequence, the target short path is obtained.

[0011] Optionally, determining the target node from the neighboring nodes based on the heuristic values ​​corresponding to the neighboring nodes includes: If the number of adjacent nodes is one, then the adjacent node is determined as the target node; If there are multiple adjacent nodes, calculate the second cumulative distance between each adjacent node and the starting point of the segment, calculate the sum of the second cumulative distance and the heuristic value corresponding to the adjacent node, and select the adjacent node with the smallest sum as the target node.

[0012] Optionally, obtaining the nodes included in the segment includes: determining the heat value of each node on the real-time route map, and selecting the nodes with heat values ​​lower than a preset threshold as the nodes included in the segment.

[0013] Optionally, the method further includes: Starting from the first segment, path planning is performed sequentially for each segment, and the target short paths obtained from the path planning are sequentially issued to the target intelligent mobile devices whose starting point is the target node and whose destination is the target endpoint, so that the target intelligent mobile devices can move from the target starting point to the target endpoint along multiple target short paths.

[0014] Optionally, the method further includes: Before the target smart mobile device has started executing this mobile task, path planning is performed for the first segment and the corresponding target short path is sent to the target smart mobile device. If the remaining distance between the target smart mobile device and the destination of the target path is less than a preset threshold, path planning is performed for the next segment, and the corresponding target short path is issued. Repeat the previous step until the target short path is sent to the target smart mobile device, and its destination is the target endpoint.

[0015] To achieve the above objectives, according to another aspect of the present invention, a path planning apparatus is provided, comprising: a segmentation module and a path planning module, wherein, The segment division module is used to divide the passable area between the target starting point and the target ending point into multiple segments. Each segment has a fixed starting point and ending point. The starting point of the first segment is the target starting point, the ending point of the last segment is the target ending point, and the ending point of the previous segment is the starting point of the next adjacent segment. The path planning module is used to sequentially perform a reverse path search for each segment to obtain each node included in the segment and calculate the first cumulative distance from each node to the end point of the segment, establish a mapping relationship between each node and the minimum first cumulative distance, and perform a forward path search based on the mapping relationship to obtain the target short path from the start point to the end point of the segment; and sequentially concatenate the target short paths corresponding to multiple segments to obtain a long path from the target start point to the target end point.

[0016] To achieve the above objectives, according to another aspect of the present invention, an electronic device for path planning is provided, comprising: One or more processors; 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 perform the method as described in the above embodiments.

[0017] To achieve the above objectives, according to another aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, characterized in that the program, when executed by a processor, implements the method described in the above embodiments.

[0018] To achieve the above objectives, according to another aspect of the present invention, a computer program product is provided, comprising a computer program, characterized in that, when the program is executed by a processor, it implements the method described in the above embodiments.

[0019] One embodiment of the above invention has the following advantages or beneficial effects: by reducing the path search scale through segmentation, constructing realistic heuristics through reverse search, and fast forward path finding, it overcomes the drawbacks of large computational load, low search efficiency, and slow response in traditional long path planning, thereby achieving a balance between path planning speed and planning quality while maintaining the optimality (or suboptimality) of the path.

[0020] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0021] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the main steps of a path planning method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of dividing the passable area between A and S into three segments AF, FM and MS according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the nodes A, B, C, D, E and F included in segment AF according to an embodiment of the present invention, their connection relationships and the actual distances between the nodes; Figure 4 This is a schematic diagram of a segment including nodes, node connection relationships, and actual distances between nodes according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the main modules of a path planning device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the operational logic of an exemplary system architecture according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the main steps of path planning in an exemplary system architecture according to an embodiment of the present invention; Figure 8 This is another exemplary system architecture diagram to which embodiments of the present invention can be applied; Figure 9 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0022] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in this disclosed technical solution all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0024] It should be noted that, unless otherwise specified, the embodiments of the present invention and the technical features thereof can be combined with each other.

[0025] Figure 1 This is a schematic diagram of the main steps of the path planning method according to an embodiment of the present invention.

[0026] like Figure 1 As shown, the path planning method of this embodiment mainly includes steps S101-S103, wherein, Step S101: Divide the passable area between the target starting point and the target ending point into multiple segments. Each segment has a fixed starting point and ending point. The starting point of the first segment is the target starting point, and the ending point of the last segment is the target ending point. The ending point of the previous segment is the starting point of the next adjacent segment. Step S102: For each segment, perform reverse path search to obtain the nodes included in the segment and calculate the first cumulative distance from each node to the end of the segment. Establish the mapping relationship between each node and the minimum first cumulative distance, and perform forward path search based on the mapping relationship to obtain the target short path from the start of the segment to the end of the segment. Step S103: The target short paths corresponding to multiple segments are sequentially spliced ​​together to obtain the long path from the target starting point to the target ending point.

[0027] The path planning method provided in this embodiment is typically deployed on a central scheduling system in a warehousing and logistics center or on the onboard terminal of an automated guided vehicle (AGV) with edge computing capabilities. This path planning method is primarily applicable to dynamic scenarios with high real-time requirements and relatively limited computing resources, such as busy e-commerce warehouses, automotive parts production lines, or logistics sorting centers. In these scenarios, the environmental structure is complex, with numerous dynamic obstacles (such as other moving AGVs, forklifts, or temporarily stacked goods). Traditional long-path one-time planning algorithms often fail to meet real-time obstacle avoidance and scheduling requirements due to excessive computational demands.

[0028] To address the aforementioned background, this embodiment proposes a path planning method based on segmentation and bidirectional search collaboration. The core idea of ​​this method is to decompose a complex long-distance planning task into several easily manageable short-distance sub-tasks. Specifically, the passable area between the target starting point and the target ending point is first logically divided to obtain multiple interconnected segments. For ease of understanding, consider a warehouse AGV traveling from entrance A to exit S: assuming the distance between A and S is large, direct planning would lead to a computing node explosion. This embodiment divides the passable area between A and S into multiple interconnected segments based on the road network topology or a preset grid size. For example, the passable area between A and S can be divided into "entrance segment AF," "middle segment FM," and "exit segment MS," as shown below. Figure 2 The diagram illustrates the division of the passable area from A to S into three segments: AF, FM, and MS. A is the target starting point, S is the target ending point, and F and M are waypoints. The starting point of the first segment is the target starting point A, and the ending point of the last segment is the target ending point S. Furthermore, the ending point of one segment is precisely the starting point of the next segment, ensuring the geometric and logical continuity of the path. This division method is similar to breaking down a long journey into "segment one, segment two," etc., with each segment having a clear start and end point, thus transforming a large global problem into multiple local problems.

[0029] After segmenting, a reverse path search is performed for each segment. In traditional algorithms, the heuristic function (the output heuristic value used to guide the path search direction) is usually based on the straight-line distance between two points (such as Euclidean distance or Manhattan distance). However, this often deviates significantly from the actual feasible path length when obstacles exist, leading to a large amount of ineffective blind searching. In this embodiment, the reverse path search utilizes the real distance information between nodes obtained from the reverse traversal to pre-calculate the first cumulative distance from any node in the current segment (including the start and end points of the segment) to the end point of the segment. Furthermore, there may be multiple paths from a node to the end point of the segment (i.e., multiple first cumulative distances from that node to the end point of the segment). The first cumulative distance (i.e., the real distance) considers the "real cost" after obstacles, so using it to guide subsequent forward searches can greatly narrow the search range and prevent the algorithm from wasting computational power in the wrong direction. Figure 3 The diagram shows the nodes A, B, C, D, E, and F included in segment AF, their connection relationships, and the actual distances between nodes (obtained through reverse path search). Table 1 shows a table of each node and its corresponding first cumulative distance; Table 2 shows a table of mapping relationships between each node and its corresponding minimum first cumulative distance.

[0030] Table 1

[0031] Table 2

[0032] Subsequently, based on the established mapping relationship, a forward path search is performed on the current segment. Guided by the actual distance of the mapping relationship, the algorithm can converge quickly and find the optimal or suboptimal path from the starting point to the ending point of the segment, i.e., the target short path. After all segments have been processed in sequence, the system concatenates the target short paths corresponding to each segment in order to finally form a complete "long path" from the target starting point to the target ending point.

[0033] This embodiment achieves the following technical effects through its "segmentation, reverse distance exploration, forward path search, and path splicing" operation process: First, it effectively solves the problems of high computational complexity and slow response in long path planning. When sudden obstacles appear in the environment, the system only needs to replan the affected subsequent segments without recalculating the entire path, significantly improving response speed. Second, the real distance mapping constructed using reverse search replaces the traditional geometric distance estimation, eliminating invalid searches caused by estimation bias, significantly improving pathfinding efficiency, and reducing the computational requirements of path search. Finally, the paths generated by this method not only have good connectivity but can also flexibly adapt to dynamically changing environments, providing a stable and efficient path planning foundation for the collaborative scheduling of multiple mobile devices, achieving a balance between planning speed and path quality.

[0034] In an optional embodiment of the present invention, the passable area between the target starting point and the target ending point is divided into multiple segments, including: determining all passable nodes within the passable area; determining multiple waypoints from the passable nodes according to a preset sampling distance; and dividing the passable area into multiple segments using the target starting point, the target ending point, and the multiple waypoints as segmentation nodes.

[0035] To facilitate understanding, let's first explain the key terms: "Passable nodes" refer to all grid center points or coordinate points in the map data that are not occupied by obstacles (such as stacks of goods, other vehicles, walls, etc.). Together, they constitute the "free space" in which intelligent mobile devices, such as AGVs or other mobile intelligent agents, can move; while "waypoints" are key nodes selected from these passable nodes and used as area segments. They are not randomly selected, but determined based on a preset sampling distance.

[0036] Specifically, firstly, all passable nodes within the passable area are scanned to establish an initial node set; then, based on a preset sampling distance (which can be dynamically adjusted according to map scale, obstacle density, and the driving speed of the smart mobile device), starting from the starting point, a point is selected as a waypoint at fixed intervals among the passable nodes. Figure 2 F and M are the waypoints.

[0037] Taking warehouse AGV path planning as an example, suppose the AGV needs to travel from point V in the shelving area to point VE, and there is a complex network of passageways between the two points. The system first identifies all unobstructed grid center points around point V and along the route as passable nodes. Then, setting the sampling distance to 50 meters (i.e., selecting a point every 50 meters), the system starts from point V and selects a point every 50 meters among the passable nodes, obtaining points VS1, VS2, VS3... until approaching point VE. These points (V, VS1, VS2, VS3...VE) are the segment nodes. Based on these segment nodes, the passable area between V and VE is logically divided into multiple segments such as V to VS1, VS1 to VS2, VS2 to VS3, ... VSn to VE.

[0038] The region segmentation strategy in this embodiment is particularly suitable for scenarios such as warehousing and logistics, ports and docks, or complex urban roads. In these scenarios, map data is usually composed of massive discrete grids or nodes. Directly performing long path searches on all nodes would quickly exhaust computing resources. This embodiment, through waypoint extraction and segmentation based on sampling distance, decomposes a massive global path planning task into several manageable local short path planning tasks. This ensures that the endpoint of the previous segment seamlessly connects to the starting point of the next segment, maintaining the geometric connectivity of the path. It also provides clear boundary constraints for subsequent reverse and forward pathfinding, reducing the computational complexity of a single search and improving the system's real-time response capability and planning stability in dynamic environments.

[0039] In an optional embodiment of the present invention, for each segment, a reverse path search is performed sequentially to obtain each node included in the segment and to calculate the first cumulative distance from each node to the end point of the segment, including: starting from the end point of the segment, traversing in reverse for all nodes included in the segment, and determining the true distance between each pair of adjacent nodes based on the traversal results; and calculating the first cumulative distance from each node to the end point of the segment based on the true distance.

[0040] The reverse path search and distance calculation process performed for each planning segment specifically refers to taking the end point of the segment as the starting reference point, traversing all passable nodes in the segment in reverse, determining the actual distance between every two adjacent nodes, and accumulating the distances from each node to the end point based on the road network topology and the actual distances to obtain the first cumulative distance.

[0041] To facilitate understanding, the concept of "first cumulative distance" is explained here: the first cumulative distance is not a simple geometric straight-line distance, but rather refers to the sum of the lengths of road segments traversed from any node to the end point of that segment along feasible paths. However, due to the existence of branches or multiple optional paths in the road network, there may be two or more feasible paths from a certain node to the end point of a segment. For example, suppose in a warehouse racking aisle, refer to... Figure 3 The endpoint of the segment is F. The first cumulative distance from B to F is the sum of the actual travel distances of BD and DF (i.e., the first cumulative distance corresponding to node B), and the sum of the actual travel distances of BE and EF (i.e., the first cumulative distance corresponding to node B). In other words, there are two paths from B to F, corresponding to two first cumulative distances. For the endpoint F, its own first cumulative distance is 0, which is the distance from itself to itself. In this embodiment, for each node, if it has only one first cumulative distance, then that first cumulative distance is the minimum first cumulative distance; if it has multiple first cumulative distances, then the smallest of these is taken as the minimum first cumulative distance.

[0042] The path planning method in this embodiment utilizes the true shortest distance pre-calculated by reverse search, which can greatly narrow the search range of subsequent forward search and guide the algorithm to quickly converge to the optimal or suboptimal solution.

[0043] In an optional embodiment of the present invention, establishing a mapping relationship between each node and the minimum first cumulative distance includes: constructing a heuristic function based on the mapping relationship, using each node as the input of the heuristic function, the heuristic function being used to determine the corresponding minimum first cumulative distance based on the input node, and outputting the minimum first cumulative distance as the heuristic value of the heuristic function.

[0044] Specifically, establishing a mapping relationship between each node and the minimum first cumulative distance essentially involves constructing an efficient lookup table or data structure for quickly retrieving the shortest true distance from any node to the target endpoint. Based on this mapping relationship, this embodiment further constructs a heuristic function. This function, as the core calculation module, receives any node in the current search state as input and directly outputs the minimum first cumulative distance corresponding to that node as its heuristic value. For ease of understanding, the relevant terms are explained here: "Forward path search" refers to the process of starting from the starting point and gradually advancing towards the endpoint to find a path. This process often faces the problem of an excessively large search range and easy getting trapped in local optima. "Reverse path search," on the other hand, refers to starting from the endpoint, pre-calculating and recording the cumulative distances from all nodes to the endpoint, thereby providing strong guidance for the forward search. "Heuristic function" is an algorithm that can quickly estimate the shortest distance to the destination based on the current node position. Its output "heuristic value" is the shortest true distance from the current node to the endpoint of the segment, used to guide the search algorithm to prioritize exploring more promising directions.

[0045] This embodiment successfully transforms complex global distance calculation into an instant table lookup operation through a heuristic function built on mapping relationships. This significantly reduces the computational complexity of forward path search, ensuring that the search direction always points to the true shortest path direction and avoiding blind exploration in the wrong direction. It also effectively improves the algorithm's response speed and path planning accuracy in dynamic environments.

[0046] In an optional embodiment of the present invention, a forward path search is performed based on the mapping relationship to obtain the target short path from the starting point of the segment to the ending point of the segment, including: performing a forward path search starting from the starting point of the segment; determining the adjacent nodes of the starting point of the segment among the nodes of the segment; determining the target node from the adjacent nodes based on the heuristic values ​​corresponding to the adjacent nodes; determining the adjacent nodes of the target node, and repeating the previous step until the determined target node is the ending point of the segment; and connecting the starting point of the segment and all target nodes in sequence to obtain the target short path.

[0047] The forward path search process, based on the aforementioned mapping relationship between nodes and the minimum first cumulative distance, is essentially a pathfinding algorithm that uses heuristic guidance for greedy search. This process aims to quickly pinpoint the optimal path to the end point of the current segment, starting from its origin. The specific execution steps are as follows: First, using the segment's origin as the current search position, retrieve all directly connected neighboring nodes in the road network. Then, query the heuristic value corresponding to each neighboring node in the mapping table, which is the true shortest distance from that node to the segment's end point obtained in the reverse pre-calculation stage. Next, among all neighboring nodes, prioritize selecting the node with the smallest heuristic value as the target node for the next hop. Finally, update the current node to this target node and repeat the above retrieval and selection steps until the target node is confirmed as the segment's end point. At this point, connecting all sequentially selected target nodes with the segment's origin forms the target shortest path from the origin to the end point. For ease of understanding, "neighboring node" is explained here: it refers to other nodes in the road network topology that have a direct connection relationship with the current node (such as being directly connected or reachable by a turn).

[0048] Taking an AGV in a logistics warehousing center as an example, assume the vehicle is currently located at node A, with neighboring nodes B and C. Calling a heuristic function yields a heuristic value of 7 meters for node B (the true shortest distance from node B to the segment endpoint F), while the heuristic value for node C is 9 meters. Since the heuristic value for node B is less than that for node C, the system determines node B as the target node for the next hop. Subsequently, the algorithm repeats the above operation at node B, comparing all its neighboring nodes and selecting the node with the smallest heuristic value as the new target node, until the segment endpoint is finally reached. Through this selection mechanism based on the minimum heuristic value, this embodiment successfully avoids the vehicle heading towards erroneous branches far from the endpoint, ensuring that the generated path is not only feasible but also close to the global shortest path.

[0049] The path planning method in the above embodiment may have the following problems: it does not consider the travel distance from node A to node B and from node A to node C. The two travel distances may be the same or they may differ greatly. Therefore, selecting the target node of the next hop based only on the first cumulative distance between B and C, i.e. the heuristic value, may result in the total distance from the start point to the end point of the planned segment not being the minimum value.

[0050] To address the aforementioned issues, in an optional embodiment of the present invention, the target node is determined from the adjacent nodes based on the heuristic value corresponding to the adjacent node, including: if there is only one adjacent node, then the adjacent node is determined as the target node; if there are multiple adjacent nodes, then the second cumulative distance between the adjacent node and the starting point of the segment is calculated respectively, the sum of the second cumulative distance and the heuristic value corresponding to the adjacent node is calculated, and the adjacent node with the smallest sum is selected as the target node.

[0051] First, determine the number of neighboring nodes the current node has: if there is only one, no comparison is needed, and this unique neighboring node is directly determined as the target node for the next hop; if there are more than one neighboring node, proceed to the optimization calculation stage. In the optimization calculation stage, calculate the second cumulative distance between each neighboring node and the starting point of the current segment, which is the actual walking length from the starting point to that neighboring node; then, sum the heuristic value (the actual shortest distance from that node to the destination) of that neighboring node with the aforementioned second cumulative distance to obtain the total path length from the starting point, through that neighboring node, to the destination; finally, among all candidate neighboring nodes, select the node with the smallest total path length as the target node and include it in the path sequence. Here, "second cumulative distance" refers to the accumulated actual distance from the starting point of the current segment to the currently examined neighboring node; "heuristic value" is the pre-calculated and stored shortest distance from the current neighboring node directly to the segment's destination; and "summation" represents the total path length from the starting point through that neighboring node to the destination. By comparing the sum of the values ​​of multiple adjacent nodes, the algorithm can automatically eliminate erroneous branches that, although seemingly close to the destination (small heuristic value), cause a significant increase in the total path length, thereby ensuring that the generated target short path has global optimality or suboptimality in terms of total length.

[0052] Taking the AGV (Automated Guided Vehicle) cart in a certain warehousing and logistics center as an example, refer to... Figure 4 The diagram shows the nodes, node connections, and distances between nodes in a segment. A1 is the starting point, F1 is the ending point, and B1, C1, D1, and E1 are all passable nodes. Assume the car is currently at node A1, and its adjacent nodes are nodes B1 and C1. First, obtain the heuristic values ​​for nodes B1 and C1, setting the heuristic value for B1 to 18 meters and for C1 to 15 meters. Next, calculate the second cumulative distance from starting point A1 to node B1 as 10 meters and the second cumulative distance from starting point A1 to node C1 as 14 meters. Then, calculate the sums: the sum for node B1 is 10 meters plus 18 meters equals 28 meters; the sum for node C1 is 14 meters plus 15 meters equals 29 meters. Here, the first cumulative distance can be represented by the heuristic function h(i), where i represents the node identifier, i.e., h(B1) = 18 and h(C1) = 15; the second cumulative distance can be represented by g(i), where i represents the node identifier, g(B1) = 10 and g(C1) = 14; f(i) can be represented by the sum of the first and second cumulative distances, i.e., the total path length from the starting point A1 to the ending point F1, where i represents the node identifier; therefore, the total path lengths corresponding to B1 and C1 are respectively: f(B1)=h(B1)+g(B1)=28 f(C1)=h(C1)+g(C1)=29 Although node C1 has a smaller heuristic value and appears closer to the destination, its sum (29 meters) is greater than the sum (28 meters) of node B1. According to the decision logic of this embodiment, the system selects node B1 as the target node because the total distance to the destination via node B1 is shorter. The algorithm then repeats the above operation at node B1 until the destination F1 is reached.

[0053] By minimizing the total distance summation, this embodiment successfully constructs a short target path that is both fast and economical, effectively balancing search speed and path length, and providing high-precision, low-energy-consumption path planning support for multi-vehicle collaborative operations.

[0054] In an optional embodiment of the present invention, obtaining the nodes included in the segment includes: determining the heat value of each node on the real-time route map; and selecting the nodes with heat values ​​lower than a preset threshold as the nodes included in the segment.

[0055] The process of acquiring the nodes within a segment is essentially a node filtering mechanism based on dynamic heatmap analysis. This mechanism aims to quickly extract nodes with low traffic volume from a vast amount of road network data, reflecting the current business scenario. The process first assesses the traffic volume of multiple nodes distributed on a real-time roadmap. The "real-time roadmap" refers to a road network data model that reflects the frequency and duration of access to each node at any given moment. Unlike static maps, the "real-time roadmap" captures dynamic information such as congestion and temporary closures. The "heatmap value" is a quantitative indicator representing the busyness or importance of a node, calculated based on factors such as traffic frequency, current queue size, average waiting time, and real-time traffic volume. The heatmap value for each node is compared to a preset threshold. Only nodes with heatmap values ​​below the threshold are retained as valid nodes within the current segment, while nodes with heatmap values ​​above the threshold are considered too busy or unreachable and are automatically filtered out. This embodiment removes nodes with high popularity by setting a preset threshold, which is actually a proactive defense strategy to avoid high-risk areas. Conversely, using nodes with lower popularity as candidate nodes helps improve overall traffic efficiency, realizes the dynamic congestion avoidance function of route planning, avoids the problem of decreased traffic efficiency caused by blindly entering busy areas, and improves the safety of vehicle operation and the timeliness of task completion in complex dynamic environments.

[0056] In an optional embodiment of the present invention, starting from the first segment, path planning is performed sequentially for each segment, and the target short paths obtained from the path planning are sequentially issued to the target intelligent mobile devices with the starting point as the target node and the destination as the target endpoint, so that the target intelligent mobile devices move from the target starting point to the target endpoint along multiple target short paths.

[0057] Starting from the first segment, path planning is performed sequentially for each segment, and the generated target short paths are then sent to the target smart mobile devices. This process essentially constructs a closed-loop control strategy of "segmented planning, dynamic sending, and real-time execution." The core of this strategy is that instead of generating a complete global path from the start point to the end point all at once, the entire journey is broken down into several consecutive segments, and path planning is performed only for the segment about to be executed. The specific execution process is as follows: First, path planning is completed for the current first segment to obtain the target short path for that segment. This target short path is then sent to the target smart mobile device, which executes the current movement task based on the target short path starting from the target start point. When the device triggers a preset execution condition (such as reaching the end point of the current segment or being at a preset distance from the end point of the current segment), the system immediately starts path planning for the next segment, obtains a new target short path, and sends it again. In this process, the "target intelligent mobile device" refers to an intelligent terminal with autonomous navigation and mobility capabilities, such as Automated Guided Vehicles (AGVs) commonly seen in warehousing and logistics scenarios, intelligent unmanned delivery vehicles traveling on outdoor roads, or robotic arm-type handling devices operating in indoor factories. They are capable of receiving and executing issued path instructions. "Executing sequentially for each segment" means that path planning is carried out in a rolling manner. That is, the planning of subsequent segments has not been started until the planning of the current segment has been completed or executed, or although it has been started, it has not been issued for execution. This ensures that each issued path instruction is generated based on the latest road condition information.

[0058] To facilitate understanding, an example is provided to illustrate the specific execution logic for unexpected road conditions: Suppose the target intelligent mobile device needs to travel from point A in warehouse to point Z in warehouse, and the entire journey is divided into three segments. After the device departs, the system plans for the first segment and issues a path instruction, which the device follows. When the device is about to reach the end of the first segment, the system detects that the passage connecting the first and second segments is temporarily blocked due to goods accumulation. At this time, the system will not continue to issue the originally planned path for the second segment, but will immediately execute a new path planning for the second segment containing the obstacle, calculate a new detour path, and issue the new path to the device. Upon receiving the new instruction, the device immediately adjusts its direction of travel to avoid the congestion and continues to move towards the destination. Throughout the entire process, the device always executes only the newly issued segment path and will not blindly execute old paths that have long been invalidated. Through this dynamic rolling planning method, this embodiment effectively solves the problem of path failure caused by real-time changes in the environment, improves the traffic safety and task execution continuity of the target intelligent mobile device in complex dynamic environments, and ensures that the device can always safely reach the destination along the currently optimal and feasible route.

[0059] In an optional embodiment of the present invention, the method further includes: performing path planning for the first segment and sending the corresponding target short path to the target smart mobile device before the target smart mobile device has started executing the current mobile task; performing path planning for the next segment and sending the corresponding target short path when the remaining distance between the target smart mobile device and the destination of the target path is less than a preset threshold; repeating the previous step until the target short path sent to the target smart mobile device is the target destination.

[0060] This embodiment further refines the triggering timing and control logic for issuing path instructions to the target smart mobile device. Specifically, it includes: when the target smart mobile device has not yet started the current movement task or is in a standby state, the system immediately performs path planning for the first segment and sends the planned target short path to the device (i.e., the target smart mobile device), making it ready; during the process of the device starting to move and traveling along the current target short path, the system continuously monitors the remaining distance between the device and the end point of the current segment (i.e., the starting point of the next segment); once it detects that the remaining distance is less than a preset threshold, it performs new path planning for the next segment and sends the newly generated target short path to the device, instructing the device to seamlessly switch to the new path to continue traveling; this process is repeated until the end point of the path sent to the device is the target end point of the entire task. In this process, the "preset threshold" is a key control parameter, which is usually set comprehensively based on parameters such as the target smart mobile device's driving speed, braking performance, communication latency, and the complexity of the current road segment.

[0061] The technical solution of this embodiment is mainly applicable to application scenarios with high requirements for path continuity and rapid environmental changes, such as AGV cluster scheduling in large warehousing centers, automated guided vehicle operation under container quay cranes in ports, or unmanned delivery vehicle navigation on urban roads. In these scenarios, if the equipment plans and executes the subsequent path too early when it is too far from the destination, the early planned path may quickly become invalid if the road conditions ahead change slightly (such as temporary stacking of goods or other vehicles blocking the road), causing the equipment to need to change lanes or brake urgently, affecting efficiency or even causing accidents. Conversely, if planning is only carried out when the equipment is close to the destination, the equipment may stop due to the lack of effective path guidance when approaching the destination. This solution cleverly balances the timeliness and stability of path planning by triggering the planning of the next segment only when the remaining distance is less than a preset threshold. When the equipment is still a safe distance from the end of the current segment, the system has already planned the path of the next segment in advance. At this time, after the equipment reaches the current destination, it can directly travel along the pre-issued target short path without waiting for the target short path of the next segment, realizing a smooth transition of the equipment's movement between two segments.

[0062] This embodiment ensures that the device always holds valid and immediately executable latest path instructions by reasonably setting preset thresholds, effectively avoiding path failure caused by real-time environmental changes, and improving the device's driving safety and task completion efficiency during continuous movement.

[0063] The path planning method of this invention overcomes the drawbacks of traditional long path planning, such as large computational load, low search efficiency, and slow response, by reducing the path search scale through segmentation, constructing realistic heuristics through reverse search, and fast forward path finding. Thus, it achieves a balance between path planning speed and planning quality while maintaining the optimality (or suboptimality) of the path.

[0064] Figure 5 This is a schematic diagram of the main modules of the path planning device 500 according to an embodiment of the present invention.

[0065] like Figure 5 As shown, the path planning device 500 of this embodiment includes: a segmentation module 501 and a path planning module 502, wherein, The segment division module 501 is used to divide the passable area between the target start point and the target end point into multiple segments. Each segment has a fixed start point and end point. The start point of the first segment is the target start point, the end point of the last segment is the target end point, and the end point of the previous segment is the start point of the next adjacent segment. The path planning module 502 is used to perform a reverse path search for each segment in turn to obtain each node included in the segment and calculate the first cumulative distance from each node to the end of the segment, establish a mapping relationship between each node and the minimum first cumulative distance, and perform a forward path search based on the mapping relationship to obtain the target short path from the start point to the end point of the segment; and then concatenate the target short paths corresponding to multiple segments in turn to obtain the long path from the target start point to the target end point.

[0066] In an optional embodiment of the present invention, the segmentation module 501 is further configured to determine all passable nodes within the passable area; determine multiple waypoints from the passable nodes according to a preset sampling distance; and divide the passable area into multiple segments using the target starting point, the target ending point, and the multiple waypoints as segmentation nodes.

[0067] In an optional embodiment of the present invention, the path planning module 502 is further configured to traverse all nodes included in the segment backwards from the end point of the segment, and determine the true distance between each pair of adjacent nodes based on the traversal results; and calculate the first cumulative distance from each node to the end point of the segment based on the true distance.

[0068] In an optional embodiment of the present invention, the path planning module 502 is further configured to construct a heuristic function based on the mapping relationship, with each node as the input of the heuristic function. The heuristic function is configured to determine the minimum first cumulative distance corresponding to the input node and output the minimum first cumulative distance as the heuristic value of the heuristic function.

[0069] In an optional embodiment of the present invention, the path planning module 502 is further configured to perform a forward path search starting from the starting point of the segment, determine the adjacent nodes of the starting point of the segment among the nodes of the segment; determine the target node from the adjacent nodes based on the heuristic value corresponding to the adjacent nodes; determine the adjacent nodes of the target node, repeat the previous step until the determined target node is the end point of the segment; and connect the starting point of the segment and all target nodes in sequence to obtain the target short path.

[0070] In an optional embodiment of the present invention, the path planning module 502 is further configured to determine the adjacent node as the target node if the number of adjacent nodes is one; if the number of adjacent nodes is multiple, calculate the second cumulative distance between the adjacent node and the starting point of the segment, calculate the sum of the second cumulative distance and the heuristic value corresponding to the adjacent node, and select the adjacent node with the smallest sum as the target node.

[0071] In an optional embodiment of the present invention, the path planning module 502 is further configured to determine the heat value of each node on the real-time route map, and to include nodes with heat values ​​lower than a preset threshold as nodes included in the segment.

[0072] In an optional embodiment of the present invention, the path planning module 502 is further configured to perform path planning for each segment sequentially, starting from the first segment, and to sequentially issue the target short paths obtained by the path planning to the target intelligent mobile device with the starting point as the target node and the destination as the target endpoint, so that the target intelligent mobile device moves from the target starting point to the target endpoint along multiple target short paths.

[0073] In an optional embodiment of the present invention, the path planning module 502 is further configured to perform path planning for the first segment and send the corresponding target short path to the target smart mobile device before the target smart mobile device has started executing the current mobile task; if the remaining distance between the target smart mobile device and the destination of the target path is less than a preset threshold, perform path planning for the next segment and send the corresponding target short path; repeat the previous step until the target short path sent to the target smart mobile device is the target destination.

[0074] The path planning device of this invention overcomes the drawbacks of traditional long path planning, such as large computational load, low search efficiency, and slow response, by reducing the path search scale through segmentation, constructing realistic heuristics through reverse search, and fast forward path finding. Thus, it achieves a balance between path planning speed and planning quality while maintaining the optimality (or suboptimality) of the path.

[0075] Figure 6 An exemplary system architecture 600 is shown where the path planning method or path planning apparatus of the present invention can be applied.

[0076] like Figure 6 As shown, the system architecture 600 includes a long path planning module 601, a short path planning module 602, a path distribution module 603, and an AGV 604.

[0077] The long path planning module 601 is used to divide the passable area between the target starting point and the target ending point into multiple segments. Each segment has a fixed starting point and ending point. The starting point of the first segment is the target starting point, the ending point of the last segment is the target ending point, and the ending point of the previous segment is the starting point of the next adjacent segment.

[0078] The short path planning module 602 is used to sequentially perform a reverse path search for each segment to obtain all nodes included in the segment and calculate the first cumulative distance from each node to the segment's endpoint. It then establishes a mapping relationship between each node and the minimum first cumulative distance, and performs a forward path search based on this mapping relationship to obtain the target shortest path from the segment's starting point to its endpoint. The specific path planning process is as follows: Figure 7 As shown, it includes steps S701-S705: Step S701: Monitor the location of the AGV.

[0079] The AGV is executing the movement task of the current segment based on the target short path of the current segment issued by the path issuing module.

[0080] Step S702: Based on the location of the AGV, determine whether the endpoint of the current segment where the AGV is located is the target endpoint. If yes, proceed to step S705; otherwise, proceed to step S703.

[0081] Step S703: Determine whether the distance between the AGV and the current segment endpoint is less than a preset distance threshold. If yes, proceed to step S704; otherwise, repeat step S703.

[0082] Step S704: Perform path planning for the next segment of the current segment, trigger the path distribution module to distribute the target short path of the next segment to the AGV, and execute step S701.

[0083] Step S705: End path planning.

[0084] The path distribution module 603 is used to sequentially distribute the target short paths of each segment to the AGV 604.

[0085] AGV604 moves sequentially to the target endpoint according to the target shortest path corresponding to each segment.

[0086] Figure 8 An exemplary system architecture 800 is shown where the path planning method or path planning apparatus of the present invention can be applied.

[0087] like Figure 8 As shown, the system architecture 800 may include smart mobile devices 801, 802, and 803 that send path planning requests, a network 804, and target servers 805, 806, and 807. The network 804 serves as the medium for providing communication links between the smart mobile devices 801, 802, and 803 and the target servers 805, 806, and 807. The network 804 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0088] Smart mobile devices 801, 802, and 803 interact with target servers 805, 806, and 807 via network 804 to receive or send messages, etc. Smart mobile devices 801, 802, and 803 are terminals that send path planning requests to the target servers. These path requests indicate the target start point and target end point. Upon receiving the path planning request, target servers 805, 806, and 807 divide the passable area between the target start point and target end point into multiple segments. Each segment has a fixed start point and end point. The start point of the first segment is the target start point, and the end point of the last segment is the target end point. Furthermore, the end point of the preceding segment becomes the start point of the next adjacent segment. Reverse path search is then performed sequentially for each segment. The algorithm retrieves all nodes within a segment and calculates the first cumulative distance from each node to the segment's endpoint. It then establishes a mapping relationship between each node and the minimum first cumulative distance and performs a forward path search based on this mapping relationship to obtain the target short path from the segment's starting point to its endpoint. The target short paths corresponding to multiple segments are then concatenated sequentially to obtain a long path from the target starting point to the target endpoint. The multiple target short paths are then fed back to the smart mobile devices 801, 802, and 803 in sequence. The concatenated long path can also be fed back to the smart mobile devices 801, 802, and 803.

[0089] It should be noted that the path planning method provided in the embodiments of the present invention is generally executed by the target servers 805, 806, and 807, and correspondingly, the path planning device is generally set in the target servers 805, 806, and 807.

[0090] It should be understood that Figure 8 The number of smart mobile devices, networks, and target servers shown is merely illustrative. Depending on implementation needs, any number of smart mobile devices, networks, and target servers can be included.

[0091] The following is for reference. Figure 9 It shows a schematic diagram of the structure of a computer system 900 suitable for implementing an electronic device according to embodiments of the present invention. Figure 9 The smart mobile device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0092] like Figure 9As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 902 or programs loaded from storage section 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the computer system 900. The CPU 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0093] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 910 as needed so that computer programs read from it can be installed into storage section 908 as needed.

[0094] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911. When the computer program is executed by central processing unit (CPU) 901, it performs the functions defined above in the system of this invention.

[0095] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor; for example, a processor can be described as including a segmentation module and a path planning module. The names of these modules do not necessarily limit the module itself; for example, the path planning module can also be described as "a module that sequentially concatenates the target short paths corresponding to multiple segments."

[0098] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: dividing a passable area between a target starting point and a target ending point into multiple segments, each segment having a fixed starting point and ending point, wherein the starting point of the first segment is the target starting point, the ending point of the last segment is the target ending point, and the ending point of the preceding segment is the starting point of the next adjacent segment; sequentially performing a reverse path search for each segment to obtain each node included in the segment and calculating a first cumulative distance from each node to the segment ending point, establishing a mapping relationship between each node and the minimum first cumulative distance, and performing a forward path search based on the mapping relationship to obtain a target short path from the segment starting point to the segment ending point; and sequentially concatenating the target short paths corresponding to the multiple segments to obtain a long path from the target starting point to the target ending point.

[0099] According to the technical solution of the present invention, by segmenting to reduce the path search scale, constructing real heuristics through reverse search, and fast forward path finding, the drawbacks of large computational load, low search efficiency, and slow response in traditional long path planning are overcome, thereby achieving a balance between path planning speed and planning quality while maintaining the optimality (or suboptimality) of the path.

[0100] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A path planning method, characterized in that, include: The passable area between the target starting point and the target ending point is divided into multiple segments. Each segment has a fixed starting point and ending point. The starting point of the first segment is the target starting point, the ending point of the last segment is the target ending point, and the ending point of the previous segment is the starting point of the next adjacent segment. For each segment, reverse path search is performed sequentially to obtain each node included in the segment and calculate the first cumulative distance from each node to the end of the segment. A mapping relationship is established between each node and the minimum first cumulative distance. Based on the mapping relationship, forward path search is performed to obtain the target short path from the start of the segment to the end of the segment. By sequentially concatenating the target short paths corresponding to the multiple segments, a long path is obtained from the target starting point to the target ending point.

2. The method according to claim 1, characterized in that, The process of dividing the passable area between the target starting point and the target ending point into multiple segments includes: Identify all passable nodes within the passable area; Based on the preset sampling distance, multiple path points are determined from the passable nodes; The passable area is divided into multiple segments using the target starting point, the target ending point, and multiple waypoints as segmentation nodes.

3. The method according to claim 1, characterized in that, The process of sequentially performing a reverse path search for each segment to obtain all nodes included in the segment and calculating the first cumulative distance from each node to the end point of the segment includes: Starting from the end of the segment, traverse in reverse order all nodes included in the segment, and determine the actual distance between each pair of adjacent nodes based on the traversal results; Based on the actual distance, calculate the first cumulative distance from each node to the endpoint of the segment.

4. The method according to claim 1, characterized in that, The establishment of the mapping relationship between each node and the minimum first cumulative distance includes: A heuristic function is constructed based on the mapping relationship. Each node is used as the input of the heuristic function. The heuristic function is used to determine the minimum first cumulative distance corresponding to the input node and output the minimum first cumulative distance as the heuristic value of the heuristic function.

5. The method according to claim 4, characterized in that, The step of performing a forward path search based on the mapping relationship to obtain the target shortest path from the start point to the end point of the segment includes: Starting from the beginning of the segment, perform a forward path search and determine the adjacent nodes of the starting point of the segment among the nodes of the segment. Based on the heuristic values ​​corresponding to the adjacent nodes, the target node is determined from the adjacent nodes; Next, identify the adjacent nodes of the target node and repeat the previous step until the identified target node is the end point of the segment. By connecting the starting point of the segment and all target nodes in sequence, the target short path is obtained.

6. The method according to claim 5, characterized in that, The step of determining the target node from the neighboring nodes based on the heuristic values ​​corresponding to the neighboring nodes includes: If the number of adjacent nodes is one, then the adjacent node is determined as the target node; If there are multiple adjacent nodes, calculate the second cumulative distance between each adjacent node and the starting point of the segment, calculate the sum of the second cumulative distance and the heuristic value corresponding to the adjacent node, and select the adjacent node with the smallest sum as the target node.

7. The method according to claim 1, characterized in that, The step of obtaining each node included in the segment includes: Determine the heat value of each node on the real-time route map; Nodes with a heat value lower than a preset threshold among multiple nodes are included in the segment.

8. The method according to claim 1, characterized in that, Also includes: Starting from the first segment, path planning is performed sequentially for each segment, and the target short paths obtained from the path planning are sequentially issued to the target intelligent mobile devices whose starting point is the target node and whose destination is the target endpoint, so that the target intelligent mobile devices can move from the target starting point to the target endpoint along multiple target short paths.

9. The method according to claim 8, characterized in that, Also includes: Before the target smart mobile device has started executing this mobile task, path planning is performed for the first segment and the corresponding target short path is sent to the target smart mobile device. If the remaining distance between the target smart mobile device and the destination of the target path is less than a preset threshold, path planning is performed for the next segment, and the corresponding target short path is issued. Repeat the previous step until the target short path is sent to the target smart mobile device, and its destination is the target endpoint.

10. A path planning device, characterized in that, include: The segmentation module and the path planning module, among which, The segment division module is used to divide the passable area between the target starting point and the target ending point into multiple segments. Each segment has a fixed starting point and ending point. The starting point of the first segment is the target starting point, the ending point of the last segment is the target ending point, and the ending point of the previous segment is the starting point of the next adjacent segment. The path planning module is used to sequentially perform a reverse path search for each segment to obtain each node included in the segment and calculate the first cumulative distance from each node to the end point of the segment, establish a mapping relationship between each node and the minimum first cumulative distance, and perform a forward path search based on the mapping relationship to obtain the target short path from the start point of the segment to the end point of the segment; and sequentially concatenate the target short paths corresponding to multiple segments to obtain a long path from the target start point to the target end point.

11. An electronic device for path planning, characterized in that, include: One or more processors; 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 as described in any one of claims 1-9.

12. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-9.

13. A computer program product, comprising a computer program, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-9.

Images