Multi-unmanned vehicle cooperative path planning and scheduling method, device, equipment and medium

Abstract

The embodiment of the invention relates to the technical field of unmanned vehicles, and discloses a multi-unmanned-vehicle cooperative path planning and scheduling method, device and equipment and a medium. According to the embodiment of the invention, on one hand, the joint search and global path reservation mechanism is introduced, so that the overlapping of the paths of multiple unmanned vehicles in time and space can be relieved fundamentally, the active collision prevention and congestion prevention of the global unmanned vehicles can be realized, and the system safety is improved. And on the other hand, the scheme of the embodiment of the invention can be moved up to the cloud, and the cloud control platform performs centralized decision making, so that the advantages of cloud computing can be inherited, the hardware cost of the single vehicle can be reduced, and the maximum total throughput and the shortest total task completion time of the system under multi-vehicle cooperation can be ensured (different from the target of realizing the shortest path of the single vehicle generally focused in the prior art); the global optimization value of cloud control is brought into play, and intensive and efficient utilization of computing power and road resources is realized.

Description

Technical Field

[0001] This invention relates to the field of unmanned vehicle technology, and in particular to a method, apparatus, equipment and medium for multi-unmanned vehicle cooperative path planning and scheduling. Background Technology

[0002] With the deep integration of smart logistics and intelligent manufacturing, unmanned vehicles (referred to as unmanned vehicles, such as AGVs and AMRs) are undertaking critical material handling tasks in closed or semi-closed environments such as factories, warehouses, and ports. Path planning, as the core technology of autonomous navigation for unmanned vehicles, mainly aims to generate an optimal or feasible collision-free driving path based on the vehicle's current position and the target point within a given environmental map.

[0003] Currently, there are two main path planning schemes for autonomous vehicles, each with its own limitations:

[0004] 1. Vehicle-side independent planning mode

[0005] In this mode, each autonomous vehicle is equipped with an independent computing unit and map data storage module, and runs path planning algorithms (such as Dijkstra's algorithm) based on local information. This distributed architecture has at least the following inherent drawbacks.

[0006] (1) Redundancy and high cost of computing resources: Each vehicle needs to be equipped with a high-performance computing unit. As the fleet size expands, the hardware cost and overall energy consumption increase significantly.

[0007] (2) Difficulty in updating and maintaining map data: When the scene layout changes (such as temporary closure of passage or adjustment of work points), the local map of each vehicle needs to be updated one by one. The process is cumbersome and may easily cause navigation failure or even safety accidents due to version inconsistency.

[0008] (3) Lack of system coordination capability: There is no effective communication and information sharing mechanism between vehicles. They can only rely on local sensors to avoid obstacles and cannot carry out forward-looking path coordination. This can easily cause traffic deadlock or congestion at bottleneck sections and intersections, resulting in low overall system operating efficiency.

[0009] 2. Simplified cloud command mode

[0010] Some systems attempt to incorporate cloud-based scheduling, but the cloud's role is weakened to that of a "command relay station," only responsible for issuing the starting and ending coordinates of the task to the vehicle. The core path planning algorithm is still executed on the vehicle. This model is merely a simple cloudification of the communication link, without moving the core planning and decision-making functions to the cloud. Therefore, it cannot overcome the fundamental shortcomings of the vehicle-side model in terms of computing power utilization, map management, and collaborative planning. Summary of the Invention

[0011] The purpose of this invention is to provide a method, apparatus, device and medium for multi-vehicle cooperative path planning and scheduling, which can at least alleviate the problems of path conflict, low efficiency and safety hazards caused by independent planning of multiple vehicles in the prior art, achieve optimal overall traffic efficiency of unmanned vehicles, reduce the risk of unmanned vehicle collisions and improve system throughput.

[0012] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for multi-unmanned vehicle cooperative path planning and scheduling, comprising at least:

[0013] Acquire a dynamic regional topology map that integrates real-time traffic information and a set of tasks for fully autonomous vehicles across the entire region.

[0014] Based on the global autonomous vehicle task set, the global autonomous vehicle real-time status data, and the dynamic regional topology map, task lane mapping is performed, and the execution time of each task lane is estimated, so as to realize the joint search, conflict resolution, path update and reservation of global task lanes, and thus obtain global reserved task lanes.

[0015] The entire reservation task lanes are aggregated and encapsulated into a sequence of passage areas that at least include the expected passage time points according to the road network structure of the dynamic regional topology map;

[0016] Each unmanned vehicle is scheduled to perform its corresponding unmanned vehicle task based on the sequence of the access area, and the unmanned vehicles in the entire area are dynamically monitored during the task execution.

[0017] Optionally, the acquisition of the dynamic regional topology map integrating the whole-domain unmanned vehicle task set, the whole-domain unmanned vehicle real-time status data, and real-time traffic information includes at least:

[0018] Receive a task request initiated by at least a Web front-end or management system in any scenario, and determine the set of all-domain unmanned vehicle tasks based on the task request, which includes at least the target vehicle ID, destination coordinates and task priority identifier;

[0019] The real-time status data of the all-domain unmanned vehicle is obtained at least through the Internet of Vehicles, including high-precision latitude and longitude coordinates, heading angle, instantaneous speed, historical average speed, remaining battery power and current task ID.

[0020] The dynamic regional topology map is obtained through a map management system in at least any scenario. It includes at least road speed limits, a global path reservation table recording the real-time occupancy status of each lane segment, and static connection relationships between lanes, nodes, and edges.

[0021] Optionally, the step of mapping task lanes based on the global autonomous vehicle task set, the global autonomous vehicle real-time status data, and the dynamic regional topology map, and estimating the execution time of each task lane to achieve joint search, conflict resolution, path update, and reservation of global task lanes, thereby obtaining global reserved task lanes, includes at least:

[0022] The current coordinates of the target vehicle are obtained based on the target vehicle ID, the current coordinates of the target vehicle are used as the starting point of the path, and the coordinates of the destination are used as the ending point of the path.

[0023] A nearest neighbor search is performed using a preset spatial indexing algorithm to determine multiple candidate lane start points that are adjacent to the path start point and multiple candidate lane end points that are adjacent to the path end point, so as to construct multiple candidate lanes.

[0024] At least the vertical distance between the starting point of the path and each of the candidate lanes, and the vertical distance between the ending point of the path and each of the candidate lanes are calculated. The starting point of the candidate lane with the shortest vertical distance is taken as the starting lane node, and the ending point of the candidate lane with the shortest vertical distance is taken as the target lane node. Then, task lane mapping is performed based on the starting lane node and the target lane node.

[0025] The time window for the target vehicle at at least one critical lane node in each task lane is estimated based on at least the instantaneous speed, the historical average speed, and the road speed limit.

[0026] Optionally, the step of mapping task lanes based on the global autonomous vehicle task set, the global autonomous vehicle real-time status data, and the dynamic regional topology map, and estimating the execution time of each task lane to achieve joint search, conflict resolution, path update, and reservation of global task lanes, thereby obtaining global reserved task lanes, may at least include:

[0027] Using the starting lane node as the search start point and the target lane node as the search end point, the target vehicle traverses each of the key lane nodes on each of the task lanes based on a preset cost function to search for and construct the optimal spatiotemporal path of the target.

[0028] Based on the target optimal spatiotemporal path, a reservation mark is made in the global path reservation table to obtain the reservation optimal spatiotemporal path;

[0029] The optimal time-space path for all target vehicles is integrated to obtain the global reservation task lane.

[0030] Optionally, the preset cost function is at least extended to the following form:

[0031] f(n) = g(n) + h(n) + c(n);

[0032] In the formula, f(n) represents the preset cost function; g(n) represents the actual cost from the search starting point to the nth critical lane node, and g(n) is at least related to the travel distance of the target vehicle and the lane attribute weight; h(n) represents the estimated cost from the nth critical lane node to the search endpoint, and h(n) takes at least the shortest time considering the road speed limit as a heuristic function; c(n) represents the conflict cost sub-function, which is determined at least by querying the global path reservation table. When any critical lane node and the corresponding task lane are repeatedly reserved by multiple target vehicles, the conflict cost sub-function is assigned a high value so that the algorithm actively avoids the already occupied spatiotemporal resources.

[0033] Optionally, after scheduling each autonomous vehicle to execute its corresponding autonomous vehicle task based at least on the traffic area sequence and dynamically monitoring all autonomous vehicles in the region during task execution, the method further includes:

[0034] During the dynamic monitoring of unmanned vehicles across the entire area, the actual location of each target vehicle is compared with its reserved location in real time.

[0035] When the deviation between the actual location and the reserved location of any of the target vehicles exceeds a set threshold, dynamic event response and collaborative replanning, and / or full-link visualization and system intervention are triggered.

[0036] Optionally, the dynamic event response and collaborative replanning are implemented in at least the following forms:

[0037] Event triggering conditions: When a serious delay of the target vehicle is detected, a temporary obstacle is added to the reserved optimal time and space path, or an unmanned vehicle task with a preset task priority is inserted, dynamic event response and collaborative replanning will be executed.

[0038] Local adjustments: Fine-tuning the target vehicles affected by dynamic event response and collaborative replanning, including at least instructing the affected target vehicles to stop and wait in a preset safe area, or adjusting the vehicle speed to resynchronize the planning;

[0039] Collaborative replanning: If local adjustments cannot resolve conflicts between multiple target vehicles, then cancel the global autonomous vehicle path reservation and, starting from the current global autonomous vehicle status, re-execute the joint search of the task lane, conflict resolution, path update and reservation for the conflicting vehicles, and update the global path reservation table.

[0040] The end-to-end visualization and system intervention are implemented in at least the following forms:

[0041] The system displays the real-time location of the fully autonomous vehicle and the fully reserved task lanes, and visualizes the global route reservation table at least in the form of a timeline or heat map, so that the dispatcher can at least perceive the traffic load of the entire road network in a preset future time period, thereby facilitating the dispatcher to perform manual intervention operations, which at least include setting temporary traffic control and dynamically adjusting task priorities.

[0042] Based on the same concept, in a second aspect, the present invention also provides a multi-unmanned vehicle cooperative path planning and scheduling device for performing the multi-unmanned vehicle cooperative path planning and scheduling method as described in any of the first aspects.

[0043] The multi-unmanned vehicle cooperative path planning and scheduling device includes at least:

[0044] The data acquisition module is used to acquire the task set of the fully autonomous vehicle, the real-time status data of the fully autonomous vehicle, and the dynamic regional topology map integrating real-time traffic information;

[0045] The lane reservation module is used to map task lanes based on the whole-domain unmanned vehicle task set, the real-time status data of the whole-domain unmanned vehicle, and the dynamic regional topology map, and to estimate the execution time of each task lane, so as to realize the joint search, conflict resolution, path update and reservation of whole-domain task lanes, and thus obtain whole-domain reserved task lanes.

[0046] The encapsulation sequence module is used to aggregate and encapsulate the full-domain reservation task lanes according to the road network structure of the dynamic regional topology map into a passage area sequence that at least includes the expected passage time points;

[0047] The scheduling and monitoring module is used at least to schedule each unmanned vehicle to perform its corresponding unmanned vehicle task based on the sequence of the passage area, and to dynamically monitor all unmanned vehicles in the entire area during the task execution.

[0048] Based on the same concept, in a third aspect, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the program to implement the steps in the multi-unmanned vehicle cooperative path planning and scheduling method of any one of the first aspects.

[0049] Based on the same concept, in a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the multi-unmanned vehicle cooperative path planning and scheduling methods in the first aspect.

[0050] The technical solution provided by this invention firstly acquires a global autonomous vehicle task set, real-time status data of global autonomous vehicles, and a dynamic regional topology map integrating real-time traffic information; secondly, it performs task lane mapping based on the global autonomous vehicle task set, real-time status data, and dynamic regional topology map, and estimates the execution time of each task lane to achieve joint search, conflict resolution, path updating, and reservation of global task lanes, thereby obtaining global reserved task lanes; then, it aggregates and encapsulates the global reserved task lanes according to the road network structure of the dynamic regional topology map into a sequence of passage areas that at least includes the expected passage time; finally, it schedules each autonomous vehicle to execute the corresponding autonomous vehicle task based at least on the sequence of passage areas, and dynamically monitors the global autonomous vehicles during task execution.

[0051] Therefore, this invention, by introducing a joint search and global path reservation mechanism, can fundamentally alleviate the spatiotemporal overlap of multiple unmanned vehicle paths, facilitating proactive collision avoidance and congestion prevention for fully autonomous vehicles and improving system safety. Furthermore, the solution of this invention can be moved to the cloud, with centralized decision-making by a cloud control platform. This not only inherits the advantages of cloud computing and reduces the hardware cost per vehicle, but also ensures maximum total system throughput and minimum total task completion time under multi-vehicle collaboration (unlike existing technologies that typically focus on minimizing the path length for a single vehicle). This allows for leveraging the global optimization value of cloud control and achieving intensive and efficient utilization of computing power and road resources. Attached Figure Description

[0052] Figure 1 This is a flowchart of a multi-unmanned vehicle cooperative path planning and scheduling method provided in an embodiment of the present invention;

[0053] Figure 2 This is a flowchart of another multi-unmanned vehicle cooperative path planning and scheduling method provided in an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of the structure of a multi-unmanned vehicle cooperative path planning and scheduling device provided in an embodiment of the present invention;

[0055] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0058] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0059] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0060] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0061] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0062] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0063] Figure 1This is a flowchart of a multi-unmanned vehicle collaborative path planning and scheduling method provided by an embodiment of the present invention. This embodiment is at least applicable to planning and scheduling scenarios when unmanned vehicle clusters perform tasks such as material handling and warehousing sorting in closed or semi-closed environments such as factories, warehouses, and ports. This multi-unmanned vehicle collaborative path planning and scheduling method can be, but is not limited to, executed by the multi-unmanned vehicle collaborative path planning and scheduling device in this embodiment of the present invention as the execution subject. This execution subject can be implemented using software and / or hardware. Figure 1 As shown, the multi-unmanned vehicle cooperative path planning and scheduling method includes at least the following steps:

[0064] S1. Obtain the task set of the unmanned vehicle in the whole domain, the real-time status data of the unmanned vehicle in the whole domain, and the dynamic regional topology map integrating real-time traffic information.

[0065] The task set of fully autonomous vehicles can be composed of the exclusive tasks of each autonomous vehicle in the aforementioned autonomous vehicle cluster, and the real-time status data of fully autonomous vehicles can also be composed of the real-time status data of each autonomous vehicle in the aforementioned autonomous vehicle cluster.

[0066] In one specific implementation, optionally, the aforementioned step S1 includes at least:

[0067] (1-1) Receive task requests initiated by at least the Web front-end or management system (such as MES) in any scenario, and determine a set of all-domain unmanned vehicle tasks that includes at least the target vehicle ID, destination coordinates and task priority identifier based on the task request;

[0068] (1-2) At least the real-time status data of the unmanned vehicle in the whole domain, including high-precision latitude and longitude coordinates, heading angle, instantaneous speed, historical average speed, remaining battery power and current task ID, should be obtained through the vehicle network;

[0069] (1-3) Obtain at least a dynamic regional topology map (e.g., loaded to the latest version of the factory area routing map) through the map management system in at least any scenario, including road speed limits, a global path reservation table recording the real-time occupancy status of each lane segment, and static connection relationships between lanes, nodes, and edges.

[0070] S2. Based on the task set of the autonomous vehicle in the whole domain, the real-time status data of the autonomous vehicle in the whole domain, and the dynamic regional topology map, the task lane is mapped, and the execution time of each task lane is estimated, so as to realize the joint search, conflict resolution, path update and reservation of the task lane in the whole domain, and thus obtain the reserved task lane in the whole domain.

[0071] Each driverless vehicle can be assigned to multiple task lanes.

[0072] In another specific implementation, optionally, the aforementioned step S2 includes at least:

[0073] (2-1) Obtain the current coordinates of the target vehicle based on the target vehicle ID, use the current coordinates of the target vehicle as the starting point of the path, and use the destination coordinates as the ending point of the path;

[0074] (2-2) Use a preset spatial indexing algorithm (such as kd-tree) to perform nearest neighbor search to determine multiple candidate lane starting points that are close to the starting point of the path and multiple candidate lane ending points that are close to the ending point of the path, so as to construct multiple candidate lanes (a candidate lane can be composed of a candidate lane starting point and different candidate lane ending points, or it can be composed of a fixed candidate lane starting point and candidate lane ending point).

[0075] (2-3) At least calculate the vertical distance between the starting point of the path and each candidate lane, and the vertical distance between the ending point of the path and each candidate lane. Take the starting point of the candidate lane with the shortest vertical distance as the starting lane node, and take the ending point of the candidate lane with the shortest vertical distance as the target lane node. Then perform task lane mapping based on the starting lane node and the target lane node. (In other embodiments, in addition to the vertical distance, the lateral distance between the starting point of the path and each candidate lane, and the lateral distance between the ending point of the path and each candidate lane can also be calculated. It can be understood that the vertical distance is used to find the candidate lane with the shortest distance from the starting point of the path from multiple candidate lanes as the task lane, and the lateral distance can determine the distance between the target vehicle and the starting point of the task lane. Only after finding its projection position can the target vehicle determine its positional relationship with the task lane.)

[0076] (2-4) Estimate the time window of the target vehicle at at least one critical lane node (e.g., the intersection of multiple task lanes) in each task lane based on instantaneous speed, historical average speed and road speed limit. (e.g., the time when any target vehicle arrives at each critical lane node.)

[0077] In yet another specific implementation, step S2 may optionally include at least:

[0078] (2-5) Using the starting lane node as the search start point and the target lane node as the search end point, traverse each key lane node of the target vehicle in each task lane based on the preset cost function to search for and construct the optimal spatiotemporal path of the target.

[0079] (2-6) Based on the target optimal spatiotemporal path, mark the reservation in the global path reservation table to obtain the reservation optimal spatiotemporal path;

[0080] (2-7) Integrate the optimal time and space paths of all target vehicles to obtain the reservation task lanes for the entire region.

[0081] In the process of searching for the optimal spatiotemporal path of the target, the attributes of each key lane node are no longer a single spatial attribute, but can be expressed as a binary spatiotemporal array in the form of "(lane spatial node, target vehicle arrival time)".

[0082] More specifically, in yet another specific implementation, the preset cost function may optionally be extended to at least the following form:

[0083] f(n) = g(n) + h(n) + c(n);

[0084] In the formula, f(n) represents the preset cost function; g(n) represents the actual cost from the search starting point to the nth critical lane node, and g(n) is at least related to the travel distance of the target vehicle and the lane attribute weight; h(n) represents the estimated cost from the nth critical lane node to the search endpoint, and h(n) takes at least the shortest time considering the road speed limit as the heuristic function; c(n) represents the conflict cost sub-function, which is determined at least by querying the global path reservation table. When any critical lane node and its corresponding task lane are repeatedly reserved by multiple target vehicles, the conflict cost sub-function is assigned a high value so that the algorithm actively avoids the already occupied spacetime resources.

[0085] Therefore, this embodiment can naturally avoid lane nodes with high conflict costs when traversing open and closed sets through step S2, and finally find not only a shortest path in space, but also an optimal spatiotemporal path without conflict in time.

[0086] In addition, in the aforementioned steps (2-6), the obtained target optimal spatiotemporal path is formally "reserved" in the global path reservation table, that is, the corresponding target vehicle is marked to occupy the target optimal spatiotemporal path Lane_A in the time period [t1,t2], occupy the target optimal spatiotemporal path Lane_B in the time period [t2,t3], and so on.

[0087] S3. Aggregate and encapsulate the entire domain reservation task lanes into a sequence of passage areas that includes at least the expected passage time points, according to the road network structure of the dynamic regional topology map.

[0088] Specifically, the planned lane segment sequence and its expected passage time (i.e., the aforementioned lanes for the full-domain reservation task) can be serialized and encapsulated according to the predefined Protocol Buffers (Proto) message format. It is understood that this encapsulated message not only contains path geometry information but also embeds crucial time constraint information, enabling precise tracking by the vehicle.

[0089] S4. At least based on the sequence of traffic areas, schedule each unmanned vehicle to execute the corresponding unmanned vehicle task, and dynamically monitor the unmanned vehicles in the entire area during the task execution.

[0090] Specifically, serialized global path messages (i.e., the aforementioned passage area sequence) can be sent to the corresponding unmanned vehicles, and dynamic monitoring of all unmanned vehicles in the entire region can be performed at least by comparing the actual location of all unmanned vehicles with the reserved location in real time.

[0091] The technical solution provided in this embodiment firstly acquires a global autonomous vehicle task set, real-time status data of global autonomous vehicles, and a dynamic regional topology map integrating real-time traffic information; secondly, it performs task lane mapping based on the global autonomous vehicle task set, real-time status data, and dynamic regional topology map, and estimates the execution time of each task lane to achieve joint search, conflict resolution, path updating, and reservation of global task lanes, thereby obtaining global reserved task lanes; then, it aggregates and encapsulates the global reserved task lanes according to the road network structure of the dynamic regional topology map into a sequence of passage areas that at least includes the expected passage time; finally, it schedules each autonomous vehicle to execute the corresponding autonomous vehicle task based at least on the sequence of passage areas, and dynamically monitors the global autonomous vehicles during task execution.

[0092] Therefore, this embodiment, by introducing a joint search and global path reservation mechanism, can fundamentally alleviate the spatiotemporal overlap of multiple unmanned vehicle paths, facilitating proactive collision avoidance and congestion prevention for fully autonomous vehicles and improving system safety. Furthermore, the solution in this embodiment can be moved to the cloud, with centralized decision-making by the cloud control platform. This not only inherits the advantages of cloud computing and reduces the hardware cost per vehicle, but also ensures the maximum total system throughput and the shortest total task completion time under multi-vehicle collaboration (unlike existing technologies that typically focus on achieving the shortest path for a single vehicle). This allows for leveraging the global optimization value of cloud control and achieving intensive and efficient utilization of computing power and road resources.

[0093] It should be noted that, in another specific implementation, after step S4, the multi-unmanned vehicle cooperative path planning and scheduling method further includes: during the dynamic monitoring of unmanned vehicles across the entire domain, comparing the actual position and the reserved position of each target vehicle in real time; when the deviation between the actual position and the reserved position of any target vehicle exceeds a set threshold, triggering dynamic event response and cooperative replanning, and / or full-link visualization and system intervention.

[0094] Based on this Figure 2 This is a flowchart of another multi-unmanned vehicle cooperative path planning and scheduling method provided in an embodiment of the present invention, such as... Figure 2 As shown, the multi-unmanned vehicle cooperative path planning and scheduling method includes at least the following steps:

[0095] S1. Obtain the task set of the unmanned vehicle in the whole domain, the real-time status data of the unmanned vehicle in the whole domain, and the dynamic regional topology map integrating real-time traffic information.

[0096] S2. Based on the task set of the autonomous vehicle in the whole domain, the real-time status data of the autonomous vehicle in the whole domain, and the dynamic regional topology map, the task lane is mapped, and the execution time of each task lane is estimated, so as to realize the joint search, conflict resolution, path update and reservation of the task lane in the whole domain, and thus obtain the reserved task lane in the whole domain.

[0097] S3. Aggregate and encapsulate the entire domain reservation task lanes into a sequence of passage areas that includes at least the expected passage time points, according to the road network structure of the dynamic regional topology map.

[0098] S4. At least based on the sequence of traffic areas, schedule each unmanned vehicle to execute the corresponding unmanned vehicle task, and dynamically monitor the unmanned vehicles in the entire area during the task execution.

[0099] S5. During the dynamic monitoring of unmanned vehicles across the entire area, the actual location of each target vehicle is compared with the reserved location in real time.

[0100] S6. When the deviation between the actual location and the reserved location of any target vehicle exceeds a set threshold, dynamic event response and collaborative replanning, and / or full-link visualization and system intervention are triggered.

[0101] Among them, the aforementioned steps S5 to S6 can at least improve the robustness of the multi-unmanned vehicle cooperative path planning and scheduling method in response to unexpected events in the practical scenarios of unmanned vehicles.

[0102] Specifically, in another specific implementation, dynamic event response and collaborative replanning may optionally be implemented in at least the following forms:

[0103] Event triggering conditions: When a serious delay of the target vehicle is detected, a temporary obstacle is added to the reserved optimal time and space path (e.g., a certain road segment is marked as impassable), or an unmanned vehicle task with a preset task priority is inserted, dynamic event response and collaborative replanning will be determined to be executed.

[0104] Local adjustments: Fine-tuning the target vehicles affected by dynamic event response and collaborative replanning, including at least instructing the affected target vehicles to stop and wait in a preset safe area, or adjusting the vehicle speed to resynchronize the planning;

[0105] Collaborative replanning: If local adjustments cannot resolve conflicts between multiple target vehicles, then the global autonomous vehicle route reservation is cancelled, and starting from the current global autonomous vehicle state, the joint search, conflict resolution, route update, and reservation for the task lane are re-executed for the conflicting vehicles (which can be one or multiple) (i.e., a new set of conflict-free global paths are generated), and the global path reservation table is updated (during this process, arbitration can be performed according to task priority to ensure that important tasks pass first; in other words, at the task scheduling level, the departure order of vehicles can be adjusted according to the global traffic load or a "detour but not congested" route can be selected for them, thereby minimizing the formation of congestion and achieving the shortest total task completion time).

[0106] End-to-end visualization and system intervention are implemented in at least the following forms:

[0107] Display the real-time location of the fully autonomous vehicle and the fully reserved task lanes, and visualize the global route reservation table at least in the form of a timeline or heat map, so that the dispatcher can at least perceive the traffic load of the entire road network within a preset future time period (e.g., 1 minute, 0.5 hours, etc.), thereby facilitating the dispatcher to perform manual intervention operations, which at least include setting temporary traffic control and dynamically adjusting task priorities.

[0108] Therefore, this embodiment, by introducing a joint search and global path reservation mechanism, can fundamentally alleviate the spatiotemporal overlap of multiple unmanned vehicle paths, facilitating proactive collision avoidance and congestion prevention for fully autonomous vehicles and improving system safety. Furthermore, the solution in this embodiment can be moved to the cloud, with centralized decision-making by the cloud control platform. This not only inherits the advantages of cloud computing and reduces the hardware cost per vehicle, but also ensures maximum total system throughput and minimum total task completion time under multi-vehicle collaboration, leveraging the global optimization value of cloud control and achieving intensive and efficient utilization of computing power and road resources. Moreover, this embodiment, through an event-triggered dynamic replanning mechanism, can flexibly respond to various emergencies in environments such as factory areas, ensuring the robustness and high availability of the method. Finally, it provides managers with a global view integrating future traffic conditions, achieving a leap from "monitoring" to "insight and prediction," supporting more efficient AI-driven hybrid decision-making.

[0109] It should also be noted that, based on the core technical concept of this invention, at least the following improvements or technical substitutions can be made:

[0110] 1. Replacement and enhancement of search algorithms: The search algorithms in the above embodiments or implementations can be replaced with any algorithm suitable for graph search, such as Dijkstra's algorithm, bidirectional search algorithm, or more advanced spatiotemporal algorithms, conflict-based search (CBS) multi-agent pathfinding (MAPF) algorithm, etc., as long as the search process takes into account spatiotemporal constraints and aims to avoid conflicts.

[0111] 2. Diversification of conflict cost model (i.e., the aforementioned preset cost function): The conflict cost sub-function c(n) in the preset cost function can have multiple implementation forms. It can be a binary function (the cost is infinite when there is a conflict, and it is completely avoided) or a continuous function (different levels of punishment are given according to the severity of the conflict, such as the length of overlap time, the priority of the conflicting vehicles, etc.), so as to realize a more flexible scheduling strategy.

[0112] Figure 3 This is a schematic diagram of a multi-unmanned vehicle collaborative path planning and scheduling device provided in an embodiment of the present invention. This embodiment is at least applicable to planning and scheduling scenarios where unmanned vehicle clusters perform tasks such as material handling and warehousing sorting in closed or semi-closed environments such as factories, warehouses, and ports. This multi-unmanned vehicle collaborative path planning and scheduling device can be implemented using software and / or hardware. Figure 3 As shown, the multi-unmanned vehicle cooperative path planning and scheduling device is used to execute the multi-unmanned vehicle cooperative path planning and scheduling method described in any of the foregoing embodiments or implementation methods. The multi-unmanned vehicle cooperative path planning and scheduling device includes at least:

[0113] Data acquisition module 110 is used to acquire the task set of the unmanned vehicle in the whole domain, the real-time status data of the unmanned vehicle in the whole domain, and the dynamic regional topology map integrating real-time traffic information;

[0114] The lane reservation module 120 is used to map task lanes based on the whole-domain unmanned vehicle task set, the real-time status data of the whole-domain unmanned vehicle and the dynamic regional topology map, and to estimate the execution time of each task lane, so as to realize the joint search, conflict resolution, path update and reservation of the whole-domain task lanes, and thus obtain the whole-domain reserved task lanes.

[0115] The encapsulation sequence module 130 is used to aggregate and encapsulate the lanes of the whole-domain reservation task into a passage area sequence that includes at least the expected passage time points according to the road network structure of the dynamic regional topology map.

[0116] The scheduling and monitoring module 140 is used at least to schedule each unmanned vehicle to perform its corresponding unmanned vehicle task based on the sequence of traffic areas, and to dynamically monitor the unmanned vehicles in the entire area during the task execution.

[0117] Optionally, the data acquisition module 110 is used for at least:

[0118] Receive task requests initiated by at least a web front-end or management system in any scenario, and determine a set of all-domain unmanned vehicle tasks that includes at least the target vehicle ID, destination coordinates, and task priority identifier based on the task request; obtain real-time status data of all-domain unmanned vehicles that includes at least high-precision latitude and longitude coordinates, heading angle, instantaneous speed, historical average speed, remaining battery power, and current task ID through at least the vehicle network; and obtain a dynamic regional topology map that includes at least road speed limits, a global path reservation table recording the real-time occupancy status of each lane segment, and static connection relationships between lanes, nodes, and edges through at least the map management system in any scenario.

[0119] Optionally, the lane reservation module 120 is used for at least:

[0120] The target vehicle's current coordinates are obtained based on its ID. These coordinates are used as the starting point of the path, and the destination coordinates are used as the ending point. A nearest neighbor search is performed using a pre-defined spatial indexing algorithm to determine multiple candidate lane starting points adjacent to the path starting point and multiple candidate lane ending points adjacent to the path ending point, thus constructing multiple candidate lanes. The vertical distance between the path starting point and each candidate lane, as well as the vertical distance between the path ending point and each candidate lane, are calculated at least. The starting point of the candidate lane with the shortest vertical distance is used as the starting lane node, and the ending point of the candidate lane with the shortest vertical distance is used as the target lane node. Then, task lane mapping is performed based on the starting lane node and the target lane node. The time window for the target vehicle to be at least one key lane node in each task lane is estimated based on the instantaneous speed, historical average speed, and road speed limit.

[0121] Optionally, the lane reservation module 120 is also used for at least:

[0122] Starting with the initial lane node as the search starting point and the target lane node as the search ending point, the system traverses each key lane node of the target vehicle in each task lane based on a preset cost function to search for and construct the target optimal spatiotemporal path; based on the target optimal spatiotemporal path, the system marks the reservation in the global path reservation table to obtain the reservation optimal spatiotemporal path; and integrates the reservation optimal spatiotemporal paths of all target vehicles to obtain the global reservation task lane.

[0123] Optionally, the preset cost function is at least extended to the following form:

[0124] f(n) = g(n) + h(n) + c(n);

[0125] In the formula, f(n) represents the preset cost function; g(n) represents the actual cost from the search starting point to the nth critical lane node, and g(n) is at least related to the travel distance of the target vehicle and the lane attribute weight; h(n) represents the estimated cost from the nth critical lane node to the search endpoint, and h(n) takes at least the shortest time considering the road speed limit as the heuristic function; c(n) represents the conflict cost sub-function, which is determined at least by querying the global path reservation table. When any critical lane node and its corresponding task lane are repeatedly reserved by multiple target vehicles, the conflict cost sub-function is assigned a high value so that the algorithm actively avoids the already occupied spacetime resources.

[0126] Optionally, the multi-unmanned vehicle cooperative path planning and scheduling device also includes:

[0127] The real-time comparison module 150 is used to compare the actual location of each target vehicle with the scheduled location in real time during the dynamic monitoring of unmanned vehicles in the whole area.

[0128] The planning intervention module 160 is used to trigger dynamic event response and collaborative replanning, and / or full-link visualization and system intervention when the deviation between the actual location and the scheduled location of any target vehicle exceeds a set threshold.

[0129] Optionally, dynamic event response and collaborative replanning may be implemented in at least the following forms:

[0130] Event triggering conditions: When a serious delay of the target vehicle is detected, a temporary obstacle is added to the reserved optimal time and space path, or an unmanned vehicle task with a preset task priority is inserted, dynamic event response and collaborative replanning will be executed.

[0131] Local adjustments: Fine-tuning the target vehicles affected by dynamic event response and collaborative replanning, including at least instructing the affected target vehicles to stop and wait in a preset safe area, or adjusting the vehicle speed to resynchronize the planning;

[0132] Collaborative replanning: If local adjustments cannot resolve conflicts between multiple target vehicles, then cancel the global autonomous vehicle path reservation and, starting from the current global autonomous vehicle status, re-execute the joint search of the task lane, conflict resolution, path update and reservation for the conflicting vehicles, and update the global path reservation table.

[0133] End-to-end visualization and system intervention are implemented in at least the following forms:

[0134] Display the real-time location of the fully autonomous vehicle and the fully reserved task lanes, and visualize the global route reservation table at least in the form of a timeline or heat map, so that the dispatcher can at least perceive the traffic load of the entire road network in the preset future time period, thereby facilitating the dispatcher to perform manual intervention operations, which at least include setting temporary traffic control and dynamically adjusting task priorities.

[0135] The technical solution provided in this embodiment firstly acquires a global autonomous vehicle task set, real-time status data of global autonomous vehicles, and a dynamic regional topology map integrating real-time traffic information through a data acquisition module. Secondly, a lane reservation module maps task lanes based on the global autonomous vehicle task set, real-time status data of global autonomous vehicles, and dynamic regional topology map, and estimates the execution time of each task lane to achieve joint search, conflict resolution, path update, and reservation of global task lanes, thereby obtaining global reserved task lanes. Then, an encapsulation sequence module aggregates and encapsulates the global reserved task lanes according to the road network structure of the dynamic regional topology map into a sequence of passage areas that at least includes the expected passage time. Finally, a scheduling and monitoring module schedules each autonomous vehicle to execute the corresponding autonomous vehicle task based at least on the passage area sequence, and dynamically monitors the global autonomous vehicles during task execution.

[0136] Therefore, this embodiment, by introducing a joint search and global path reservation mechanism, can fundamentally alleviate the spatiotemporal overlap of multiple unmanned vehicle paths, facilitating proactive collision avoidance and congestion prevention for fully autonomous vehicles and improving system safety. Furthermore, the solution in this embodiment can be moved to the cloud, with centralized decision-making by the cloud control platform. This not only inherits the advantages of cloud computing and reduces the hardware cost per vehicle, but also ensures the maximum total system throughput and the shortest total task completion time under multi-vehicle collaboration (unlike existing technologies that typically focus on achieving the shortest path for a single vehicle). This allows for leveraging the global optimization value of cloud control and achieving intensive and efficient utilization of computing power and road resources.

[0137] This embodiment provides an electronic device. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. See also: Figure 4The electronic device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above-mentioned multi-unmanned vehicle cooperative path planning and scheduling methods are performed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanism (not shown). The memory 1002 stores a computer program that can be executed by the processor. When the electronic device 1000 is running, the processor 1001 executes the computer program to execute the multi-unmanned vehicle cooperative path planning and scheduling method in any optional implementation of the above embodiments, so as to achieve at least the following functions: acquiring a set of unmanned vehicle tasks, real-time status data of unmanned vehicles in the whole domain, and a dynamic regional topology map integrating real-time traffic information; mapping task lanes according to the set of unmanned vehicle tasks, real-time status data of unmanned vehicles in the whole domain, and dynamic regional topology map, and estimating the execution time of each task lane, so as to realize the joint search, conflict resolution, path update and reservation of task lanes in the whole domain, thereby obtaining the whole domain reserved task lanes; aggregating and encapsulating the whole domain reserved task lanes according to the road network structure of the dynamic regional topology map into a sequence of passage areas that at least includes the expected passage time; scheduling each unmanned vehicle to execute the corresponding unmanned vehicle task based at least on the sequence of passage areas, and dynamically monitoring the unmanned vehicles in the whole domain during the task execution.

[0138] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the multi-unmanned vehicle cooperative path planning and scheduling method provided in all embodiments of this application: acquiring a global unmanned vehicle task set, global unmanned vehicle real-time status data, and a dynamic regional topology map integrating real-time traffic information; mapping task lanes based on the global unmanned vehicle task set, global unmanned vehicle real-time status data, and dynamic regional topology map, and estimating the execution time of each task lane to achieve joint search, conflict resolution, path update, and reservation of global task lanes, thereby obtaining global reserved task lanes; aggregating and encapsulating the global reserved task lanes according to the road network structure of the dynamic regional topology map into a sequence of passage areas containing at least the expected passage time; scheduling each unmanned vehicle to execute the corresponding unmanned vehicle task based at least on the passage area sequence, and dynamically monitoring the global unmanned vehicles during task execution.

[0139] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. 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 (a non-exhaustive list) of computer-readable storage media include: 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 document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0140] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0141] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0142] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-unmanned vehicle cooperative path planning and scheduling method, characterized in that, At least comprising: acquiring a global unmanned vehicle task set, a global unmanned vehicle real-time state data, and a dynamic regional topology map integrated with real-time traffic information; According to the global unmanned vehicle task set, the global unmanned vehicle real-time state data and the dynamic regional topology map, task lane mapping is carried out, and time estimation is carried out for each task lane, to realize joint search, conflict resolution, path update and reservation of global task lane, and then global reserved task lane is obtained; According to the road network structure of the dynamic regional topology map, the global reserved task lane is aggregated and encapsulated into a traffic area sequence containing at least a predicted passing time point; At least based on the traffic area sequence, each unmanned vehicle is dispatched to execute the corresponding unmanned vehicle task, and the global unmanned vehicle is dynamically monitored during task execution.

2. The method of claim 1, wherein, The acquisition of the global unmanned vehicle task set, the global unmanned vehicle real-time state data, and the dynamic regional topology map integrated with real-time traffic information at least comprises: Receiving a task request initiated by at least a Web front end or a management system in any scenario, to determine the global unmanned vehicle task set containing at least a target vehicle ID, a destination coordinate and a task priority identifier according to the task request; At least through the Internet of Vehicles, the global unmanned vehicle real-time state data including high-precision latitude and longitude coordinates, heading angle, instantaneous speed, historical average speed, remaining power and current task ID is acquired; At least through a map management system in any scenario, the dynamic regional topology map including road speed limit, global path reservation table recording real-time occupancy state of each lane segment, and static connection relationship of lane-node-edge is acquired.

3. The method of claim 2, wherein, The task lane mapping according to the global unmanned vehicle task set, the global unmanned vehicle real-time state data and the dynamic regional topology map, and the time estimation for each task lane, to realize joint search, conflict resolution, path update and reservation of global task lane, and then global reserved task lane is obtained, at least comprises: According to the target vehicle ID, the target vehicle current coordinate is acquired, the target vehicle current coordinate is taken as the path starting point, and the destination coordinate is taken as the path ending point; Using a preset spatial index algorithm to perform nearest neighbor search to determine a plurality of candidate lane starting points adjacent to the path starting point and a plurality of candidate lane ending points adjacent to the path ending point, to construct a plurality of candidate lanes; At least calculate the vertical distance between the path starting point and each candidate lane, and the vertical distance between the path ending point and each candidate lane, take the candidate lane starting point of the candidate lane with the shortest vertical distance as the starting lane node, and take the candidate lane ending point of the candidate lane with the shortest vertical distance as the target lane node, and then perform task lane mapping based on the starting lane node and the target lane node; At least according to the instantaneous speed, the historical average speed and the road speed limit, the time window of the target vehicle at least one key lane node on each task lane is estimated.

4. The method of claim 3, wherein, The task lane mapping is performed according to the global unmanned vehicle task set, the global unmanned vehicle real-time state data and the dynamic area topology map, and the time estimation is performed on each task lane, so as to realize the joint search, conflict resolution, path update and reservation of the global task lane, and further obtain the global reserved task lane, and at least includes: Taking the starting lane node as a search starting point and the target lane node as a search ending point, each key lane node of the target vehicle on each task lane is traversed based on a preset cost function, so as to search and construct a target optimal space-time path; Based on the target optimal space-time path, a reservation mark is made in the global path reservation table, and a reserved optimal space-time path is obtained; The reserved optimal space-time paths of all target vehicles are integrated to obtain the global reserved task lane.

5. The method of claim 4, wherein, The preset cost function is at least expanded in the following form: f(n) = g(n) + h(n) + c(n); In the formula, f(n) represents the preset cost function; g(n) represents an actual cost from the search starting point to the nth key lane node, and g(n) is at least related to the driving distance of the target vehicle and the lane attribute weight; h(n) represents an estimated cost from the nth key lane node to the search ending point, and h(n) at least takes the shortest time considering the road speed limit as a heuristic function; c(n) represents a conflict cost sub-function, and the conflict cost sub-function is at least determined by querying the global path reservation table. When any key lane node and the corresponding task lane are repeatedly reserved by multiple target vehicles, the conflict cost sub-function is assigned a high value, so that the algorithm actively avoids the occupied space-time resources.

6. The method of claim 1, wherein, After the at least based on the passing area sequence scheduling each unmanned vehicle to execute the corresponding unmanned vehicle task, and dynamically monitoring the global unmanned vehicle during task execution, further comprising: During the dynamic monitoring of the global unmanned vehicle, the actual position and the reserved position of each target vehicle are compared in real time; When the deviation between the actual position and the reserved position of any target vehicle exceeds a set threshold, a dynamic event response and collaborative re-planning, and / or a global link visualization and system intervention are triggered.

7. The method of claim 6, wherein, The dynamic event response and collaborative re-planning are at least implemented in the following form: Event trigger condition: when it is detected that the target vehicle is seriously delayed, a new temporary obstacle is added on the reserved optimal space-time path, or an unmanned vehicle task with a preset task priority identifier is inserted, it is determined to execute the dynamic event response and collaborative re-planning; Local adjustment: fine-tuning the target vehicle affected by the dynamic event response and collaborative re-planning, at least including instructing the affected target vehicle to stop and wait in a preset safety area, or adjusting the vehicle speed to resynchronize the planning; Collaborative re-planning: if the local adjustment cannot solve the conflict among multiple target vehicles, the global unmanned vehicle path reservation is released, and the joint search, conflict resolution, path update and reservation of the task lane are performed again on the conflict vehicles based on the current global unmanned vehicle state as a starting point, and the global path reservation table is updated; The global link visualization and system intervention are at least implemented in the following form: displaying real-time positions of all global unmanned vehicles and the global reserved task lanes, and visualizing the global path reservation table in at least a timeline or a heat map form to at least enable a dispatcher to perceive traffic load of a whole road network in a preset future period, thereby facilitating the dispatcher to perform a manual intervention operation, the manual intervention operation at least including setting a temporary traffic control and dynamically adjusting a task priority.

8. A multi-unmanned vehicle cooperative path planning and scheduling device, characterized in that, The method for performing the multi-unmanned vehicle cooperative path planning and scheduling method according to any one of claims 1-7; The multi-unmanned vehicle cooperative path planning and scheduling device at least comprises: a data acquisition module configured to acquire global unmanned vehicle task sets, global unmanned vehicle real-time state data, and a dynamic regional topological map integrated with real-time traffic information; a lane reservation module configured to perform task lane mapping according to the global unmanned vehicle task sets, the global unmanned vehicle real-time state data, and the dynamic regional topological map, and perform time estimation for each task lane, so as to realize joint search, conflict resolution, path update, and reservation of global task lanes, thereby obtaining global reserved task lanes; a packaging sequence module configured to aggregate and package the global reserved task lanes into a passing region sequence containing at least a predicted passing time point according to a road network structure of the dynamic regional topological map; a scheduling and monitoring module configured to schedule each unmanned vehicle to perform a corresponding unmanned vehicle task based on the passing region sequence, and dynamically monitor global unmanned vehicles during task execution.

9. An electronic device comprising a memory and a processor, said memory storing a computer program operable on said processor, characterized in that, The processor executes the program to realize the steps in the multi-unmanned vehicle cooperative path planning and scheduling method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps in the multi-unmanned vehicle cooperative path planning and scheduling method according to any one of claims 1-7.

Images