A logistics-oriented multi-unmanned aerial vehicle cooperative flight planning method and system

Abstract

The application discloses a kind of logistics-oriented multi-unmanned aerial vehicle cooperative flight planning method and system, by constructing task allocation-single machine planning-time and space conflict detection layered cooperative planning framework, the overall coordination problem caused by the problem that traditional method will task allocation and flight planning be split processing is broken through, multi-unmanned aerial vehicle in complex task scene under the cooperative planning and orderly execution of realization, improve the realizability and overall operation efficiency of unmanned aerial vehicle in quantity and task scale expansion case.And, the conflict detection based on time and space occupation relationship is introduced in the application, the flight path of unmanned aerial vehicle and execution time are jointly modeled, the time and space conflict risk that can appear in the flight process of multi-unmanned aerial vehicle can be accurately identified, the misjudgment or omission problem caused by the problem that only relying on space or time single dimension carries out conflict judgment is avoided, so as to significantly improve the safety and reliability of multi-unmanned aerial vehicle cooperative flight process.

Description

Technical Field

[0001] This invention relates to the field of intelligent planning and control technology for unmanned aerial vehicles (UAVs), specifically to a multi-UAV collaborative flight planning method and system for logistics. Background Technology

[0002] Unmanned Aerial Vehicles (UAVs) have been widely used in material transportation, inspection and monitoring, and emergency response due to their high mobility, flexible deployment, and low operating costs. However, with the continuous expansion of application scenarios such as smart logistics, emergency rescue, and urban management, we have placed higher demands on the ability of flight platforms to perform multiple tasks in complex environments. Furthermore, due to the expansion of task scale and application scope, the capabilities of a single UAV in terms of task coverage, execution efficiency, and continuous operation are gradually becoming limited. Therefore, the application model of completing tasks collaboratively by multiple UAVs has gradually attracted attention, leading to the emergence of multi-UAV systems. Multi-UAV systems can perform tasks in parallel over a larger spatial area, helping to improve overall operational efficiency and system flexibility, and are suitable for application needs in multi-tasking, high-density, and complex scenarios.

[0003] However, existing technologies have certain limitations in multi-UAV collaborative planning. Currently, whether in academic research or engineering applications, related technologies mostly focus on the task planning or path optimization of a single UAV, often separating task allocation from the flight planning process. They lack systematic modeling of the overall collaborative relationship of multiple UAVs and ignore the mutual influence of multiple UAVs when collaboratively performing multiple tasks in shared airspace.

[0004] However, in real-world applications, multi-UAV systems often need to operate in complex environments and under multi-tasking conditions, making mutual interference between UAVs in terms of flight paths and timing inevitable. Therefore, how to achieve reasonable task allocation among multiple UAVs under multi-tasking conditions, and on this basis, coordinate and plan the flight paths and speeds of each UAV, while effectively avoiding spatiotemporal conflicts between UAVs, and ensuring that each UAV maintains a safe, orderly, and efficient operating state while completing its designated tasks, remains a critical issue that urgently needs to be addressed. Summary of the Invention

[0005] To address the aforementioned problems in the existing technology, this invention provides a multi-UAV cooperative flight planning method for logistics. The technical problem to be solved by this invention is achieved through the following technical solution: According to a first aspect of the present invention, a multi-UAV cooperative flight planning method for logistics is provided, the method comprising: Initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information; the basic information includes: each task and its corresponding spatial location and time constraints, the identifier of each UAV and its corresponding UAV status information; Based on the task information set and the UAV status information set, an association between tasks and UAVs is established, and the association that satisfies the task constraints and UAV capability limitations is used to allocate tasks to UAVs, resulting in task allocation results for each UAV. Based on the task allocation results, path optimization is performed individually for each UAV, and a desired flight speed is set for each segment of the optimized path to obtain a path-speed candidate scheme for each UAV. Using the path-velocity candidate schemes of each UAV, the spatiotemporal occupancy relationship of each UAV within a specific time range is constructed and flight conflict detection is performed; If no flight conflict exists, determine whether the path-velocity candidate scheme meets the output conditions. If it does, output the planning result.

[0006] In one embodiment of the present invention, after constructing the spatiotemporal occupancy relationship of each UAV within a specific time range and performing flight conflict detection using the path-velocity candidate scheme of each UAV, the method further includes: When a flight conflict exists, the flight status information of the relevant UAVs is adjusted, and then the path-velocity candidate scheme is updated. The updated path-velocity candidate scheme is then subjected to continued flight conflict detection and adjustment until no flight conflict is detected. The step of determining whether the path-speed candidate scheme meets the output condition, and if so, outputting the planning result, includes: Determine whether the updated path-speed candidate scheme meets the output conditions. If it does, output the planning result.

[0007] In one embodiment of the present invention, the UAV status information includes takeoff time, arrival time of the mission's spatial location, flight speed of each flight segment, and flight path; When a flight conflict exists, the flight status information of the relevant UAVs is adjusted, including: When a flight conflict exists, the takeoff time or arrival time of the relevant UAVs is adjusted; or the flight speed of the relevant UAVs is redistributed for a certain period of time before or after the conflict segment; or the conflict flight path of the relevant UAVs is modified.

[0008] In one embodiment of the present invention, the step of establishing an association between tasks and drones based on the task information set and the drone status information set, and allocating tasks to drones based on the associations that satisfy task constraints and drone capability limitations, to obtain a task allocation result for each drone; includes: Based on the task information set and the UAV status information set, a task allocation objective function for each UAV is constructed using the task allocation cost; Under the conditions of satisfying the task constraints and UAV capability limitations, the objective function for task allocation is solved to obtain the task allocation decision variables for each UAV; The task allocation decision variables for each UAV are combined to obtain the task allocation result for the corresponding UAV.

[0009] In one embodiment of the present invention, the step of optimizing the path for each UAV individually based on the task allocation result includes: Based on the task allocation results, and under the premise of satisfying the UAV's starting position constraints, the order in which the UAV visits the spatial positions of the corresponding tasks is obtained, and the flight path of the UAV is determined. The flight path is optimized with the goal of minimizing the single-machine path cost.

[0010] In one embodiment of the present invention, the step of setting a desired flight speed for each segment of the optimized path to obtain a path-speed candidate scheme for each UAV includes: A fixed flight speed is set for each segment of the optimized path, or a specific flight speed is allocated to each segment of the optimized path according to the segment length ratio, or a regularized flight speed is set for each segment of the optimized path according to the mission time requirements, to obtain the path-speed candidate scheme for each UAV.

[0011] In one embodiment of the present invention, the step of constructing the spatiotemporal occupancy relationship of each UAV within a specific time range and performing flight conflict detection using the path-velocity candidate scheme of each UAV includes: Using the path length and segment speed in the path-speed candidate scheme, the flight time of the UAV on each segment is calculated, and the time-series trajectory of the UAV within the time constraint is obtained, thus obtaining the area occupied by the UAV in the spatiotemporal domain. Perform traversal flight conflict detection on the occupied areas of all drones.

[0012] In one embodiment of the present invention, the step of traversing the occupied areas of all UAVs for flight conflict detection includes: The occupied areas of all UAVs can be detected discretely based on time steps; or the occupied areas of all UAVs can be detected event-driven based on the arrival time of the spatial location of the critical mission; or the occupied areas of all UAVs can be detected continuously based on flight segment intervals.

[0013] In one embodiment of the present invention, the output conditions include: There are no drone pairs that violate flight safety distance constraints or reach the preset maximum number of iterations.

[0014] According to a second aspect of the present invention, a multi-UAV cooperative flight planning system for logistics is provided, the system comprising: The information initialization module is used to initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information; the basic information includes: each task and its corresponding spatial location and time constraints, the identifier of each UAV and its corresponding UAV status information; The task allocation module is used to establish the association between tasks and drones based on the task information set and the drone status information set, and to allocate tasks to drones based on the association that satisfies the task constraints and drone capability limitations, so as to obtain the task allocation result for each drone. The path-speed joint optimization module is used to optimize the path of each UAV individually based on the task allocation result, and set the expected flight speed for each segment of the optimized path to obtain the path-speed candidate scheme for each UAV. The spatiotemporal conflict detection and resolution module is used to construct the spatiotemporal occupancy relationship of each UAV within a specific time range and perform flight conflict detection and resolution by utilizing the path-velocity candidate scheme of each UAV. The output module is used to determine whether the path-speed candidate scheme meets the output conditions when there is no flight conflict. If it does, the planning result is output.

[0015] The multi-UAV cooperative flight planning method and system for logistics provided in this invention first initializes the basic information required for multi-UAV cooperative flight planning, obtaining a set of task information to be executed and a set of UAV status information. The basic information includes: each task and its corresponding spatial location and time constraints, and the identifier of each UAV and its corresponding UAV status information. Then, based on the task information set and the UAV status information set, the association between tasks and UAVs is established, and the associations that satisfy the task constraints and UAV capability limitations are used to allocate tasks to UAVs, obtaining the task allocation result for each UAV. Then, according to the task allocation result, the path is optimized for each UAV individually, and the expected flight speed is set for each segment of the optimized path, obtaining the path-speed candidate scheme for each UAV. Next, using the path-velocity candidate schemes for each UAV, the spatiotemporal occupancy relationship of each UAV within a specific time range is constructed, and flight conflict detection is performed. If no flight conflict exists, it is determined whether the path-velocity candidate scheme meets the output conditions; if so, the planning result is output. Compared with the prior art, the beneficial effects of this invention are: 1. This invention overcomes the problem of insufficient overall coordination caused by separating task allocation and flight planning in traditional methods by constructing a hierarchical collaborative planning framework of task allocation-single-machine planning (path optimization for each UAV)-spatiotemporal conflict detection. It realizes collaborative planning and orderly execution of multiple UAVs in complex mission scenarios, and improves the feasibility and overall operational efficiency of UAVs under the expansion of number and mission scale.

[0016] 2. By introducing conflict detection based on spatiotemporal occupancy, this invention jointly models the flight path and execution time of UAVs, which can accurately identify spatiotemporal conflict risks such as path intersection, time overlap and insufficient safety distance that may occur when multiple UAVs are flying. This avoids the misjudgment or omission caused by relying on only a single dimension of space or time for conflict judgment, thereby significantly improving the safety and reliability of the collaborative flight process of multiple UAVs.

[0017] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the steps of a multi-UAV cooperative flight planning method for logistics, as provided in this embodiment of the invention; Figure 2 Another flowchart of the multi-UAV cooperative flight planning method for logistics provided in this embodiment of the invention; Figure 3 This is a schematic diagram of the structure of a multi-UAV cooperative flight planning system for logistics provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] The present invention aims to propose a multi-UAV cooperative flight planning method based on task allocation and spatiotemporal conflict resolution. Under the premise of meeting the time constraints of multi-task and the requirements for safe flight of UAVs, it realizes the cooperative task execution and flight efficiency improvement of multi-UAV systems, and solves key problems such as UAV task allocation, multi-UAV flight path and speed planning, and spatiotemporal conflict coordination among UAVs in multi-task scenarios.

[0021] Example 1 Reference Figure 1 The diagram illustrates a flowchart of a multi-UAV cooperative flight planning method for logistics according to Embodiment 1 of the present invention.

[0022] The multi-UAV cooperative flight planning method for logistics in this embodiment includes the following steps: Step 101: Initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information.

[0023] The aforementioned basic information includes: each task and its corresponding spatial location and time constraints, and the identifier of each UAV and its corresponding UAV status information. Each task corresponds to a spatial location and time constraint; the time constraint can limit the earliest start time and the latest completion time of the task, which can be set according to actual needs.

[0024] This step is used to uniformly model and initialize the basic information required for multi-UAV cooperative flight planning, providing input data for subsequent task allocation, path and speed planning, and spatiotemporal conflict resolution.

[0025] Step 102: Based on the task information set and the UAV status information set, establish the association between the task and the UAV, and allocate the task to the UAV according to the association that satisfies the task constraints and UAV capability limitations, so as to obtain the task allocation result for each UAV.

[0026] This step is used to determine the allocation relationship between each task and the drones under multi-task and multi-drone conditions, providing constraint inputs for subsequent drone path and speed planning.

[0027] Step 103: Based on the above task allocation results, perform path optimization for each UAV individually, and set the expected flight speed for each segment of the optimized path to obtain the path-speed candidate scheme for each UAV.

[0028] This step is used to solve for and locally optimize the flight paths of individual UAVs that have completed task assignments within a multi-UAV collaborative planning framework. Without considering the collaborative relationships between UAVs, it generates feasible flight paths for a single UAV that satisfy the task access order constraints, providing a basic trajectory scheme for subsequent spatiotemporal conflict detection and resolution.

[0029] Step 104: Using the path-velocity candidate schemes of each UAV, construct the spatiotemporal occupancy relationship of each UAV within a specific time range and perform flight conflict detection.

[0030] This step is the global level of multi-UAV planning and is a key link in realizing multi-UAV collaborative planning. Its input is the path-velocity candidate scheme generated by each UAV at the individual level, and its output can be a collaborative flight scheme that meets the safety constraints of multiple UAVs.

[0031] Step 105: If there is no flight conflict, determine whether the above path-speed candidate schemes meet the output conditions. If they do, output the planning result.

[0032] In this embodiment, if the determined path-speed candidate scheme does not meet the output conditions, the process can return to step 102 to iterate and perform operations such as task allocation.

[0033] After the multi-UAV collaborative flight planning process is completed, this step evaluates, organizes, and outputs the final planning results, which can provide directly usable flight commands and collaborative information for the UAV system's mission execution or downstream control modules.

[0034] The multi-UAV cooperative flight planning method for logistics provided in this invention first initializes the basic information required for multi-UAV cooperative flight planning, obtaining a set of task information to be executed and a set of UAV status information. The basic information includes: each task and its corresponding spatial location and time constraints, and the identifier of each UAV and its corresponding UAV status information. Next, based on the task information set and the UAV status information set, an association between tasks and UAVs is established, and the associations that satisfy the task constraints and UAV capability limitations are used to allocate tasks to UAVs, obtaining a task allocation result for each UAV. Then, based on the task allocation result, path optimization is performed individually for each UAV, and a desired flight speed is set for each segment of the optimized path, obtaining a path-speed candidate scheme for each UAV. Next, using the path-speed candidate schemes for each UAV, the spatiotemporal occupancy relationship of each UAV within a specific time range is constructed, and flight conflict detection is performed. When no flight conflict exists, it is determined whether the path-speed candidate scheme meets the output conditions; if so, the planning result is output. Compared with the prior art, the beneficial effects of this invention are: 1. This invention overcomes the problem of insufficient overall coordination caused by separating task allocation and flight planning in traditional methods by constructing a hierarchical collaborative planning framework of task allocation-single-machine planning (path optimization for each UAV)-spatiotemporal conflict detection. It realizes collaborative planning and orderly execution of multiple UAVs in complex mission scenarios, and improves the feasibility and overall operational efficiency of UAVs under the expansion of number and mission scale.

[0035] 2. By introducing conflict detection based on spatiotemporal occupancy, this invention jointly models the flight path and execution time of UAVs, which can accurately identify spatiotemporal conflict risks such as path intersection, time overlap and insufficient safety distance that may occur when multiple UAVs are flying. This avoids the misjudgment or omission caused by relying on only a single dimension of space or time for conflict judgment, thereby significantly improving the safety and reliability of the collaborative flight process of multiple UAVs.

[0036] Example 2 The following will provide a more detailed description of the multi-UAV cooperative flight planning method for logistics implemented in this invention, such as... Figure 2 As shown, Figure 2 Another flowchart of the multi-UAV cooperative flight planning method for logistics provided in this application embodiment may include the following steps: Step 201: Initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information.

[0037] In this embodiment, the basic information required for multi-UAV collaborative planning is first set. This basic information may include: spatial location and time constraint parameters of the task, initial position and flight performance parameters of the UAVs, safe flight distance, and planning time range. Depending on the actual application scenario, the initial flight state of the UAVs can be initialized using rules or preset strategies.

[0038] For example, let the set of drones be represented as: Where U represents the total number of drones, and the set of tasks to be executed is . Where Y represents the total number of tasks, and each task For a given spatial location and time constraint, its spatial location is represented as: And let the executable time window for task i be: This is used to define the earliest start time and the latest finish time of a task.

[0039] For any drone Its initial position is represented as The flight speed of a drone is limited by its physical properties, and its speed constraint is defined as: in, This represents the flight speed of the drone u at time t. Meanwhile, to ensure flight safety, the maximum permissible flight time for the drone is set to... This will serve as a constraint in subsequent planning.

[0040] Discretize the overall planning time interval for each drone into several consecutive time intervals. Let the system planning time range be [0, T]. Divide it into K equal-length time steps, and then the time index set is represented as: The corresponding time step is: In each time step, the flight state (position, velocity) of the UAV is kept constant or approximately constant.

[0041] During the initialization phase, an initial flight trajectory and speed plan can be set for each drone. Let the position of drone u at the k-th time step be represented as: The initial trajectory can be generated using a regularized method, such as a straight-line flight trajectory based on the starting position, satisfying: in, This represents the flight direction vector of the UAV at time step k. The initial flight velocity of the UAV... It can be set to a constant value or a preset value within its allowed speed range.

[0042] To avoid collisions between drones, a minimum safe distance is set between any two drones. Then for any unmanned aerial vehicle u,v∈ If u ≠ v, then at any time step k, the following must be satisfied: This safe distance constraint will be used as an important criterion in subsequent spatiotemporal conflict detection and resolution.

[0043] Upon completion of this step, the obtained initialization information includes: a task information set—which may include each task and its spatial location and time window; and a UAV status information set—which may include the initial position and performance parameters of each UAV, the planning time range and time discrete parameters, the initial flight trajectory and speed plan of each UAV, the flight safety distance and related constraint parameters, and other parameters required for flight. The initialization results will serve as the basis for subsequent task allocation and UAV collaborative planning.

[0044] Step 202: Based on the task information set and the UAV status information set, establish the association between the task and the UAV, and allocate the task to the UAV according to the association that satisfies the task constraints and UAV capability limitations, so as to obtain the task allocation result for each UAV.

[0045] Specifically, based on the task information set and the UAV state information set, a task allocation objective function for each UAV can be constructed using the task allocation cost. Then, under the conditions of satisfying the task constraints and UAV capability limitations, the task allocation objective function is solved to obtain the task allocation decision variables for each UAV. Finally, the task allocation decision variables for each UAV are combined to obtain the task allocation result for the corresponding UAV.

[0046] For example, to describe the allocation relationship between tasks and drones, a binary decision variable is introduced: To ensure that each task is performed by only one drone, task allocation must meet the following constraints: To avoid overloading a single drone, the number of tasks each drone can perform can be limited. Let the maximum number of tasks that drone u can perform be... Then we have: Considering the differences in flight performance, starting position, and available time among various drones, task-drone combinations that do not meet the execution conditions (e.g., exceeding the safe distance, exceeding the task limit, etc.) should be prohibited from allocation; therefore, a feasibility indicator function is defined: Then we have: ,in, The determination can be made based on factors such as the drone's initial position, maximum flight time, and mission time window.

[0047] To evaluate the merits of different task allocation schemes, a task allocation cost function can be introduced. Let... Let represent the cost of assigning task i to drone u. This cost can be related to the distance from the drone to the task location, the urgency of the task, or the estimated flight time. Then, the objective function for task assignment can be expressed as: Alternatively, an objective function that maximizes the overall efficiency of the system can be equivalently constructed according to application requirements; this embodiment does not impose any restrictions.

[0048] Under the aforementioned constraints, the task allocation decision variables are obtained by solving the objective function. The methods used in the solution process for obtaining the value of include, but are not limited to, heuristic algorithms, graph neural network algorithms, and auction algorithms. For any drone u, its assigned task set is represented as: The task set This will serve as an input constraint for subsequent multi-UAV path and speed planning, used to generate the corresponding UAV's flight path and speed plan.

[0049] Step 203: Based on the above task allocation results, perform path optimization for each UAV individually, and set the expected flight speed for each segment of the optimized path to obtain the path-speed candidate scheme for each UAV.

[0050] It should be noted that this step only solves the local path problem for a single UAV, and the optimization result is not directly used as the final execution path, but rather as a candidate input scheme in multi-UAV collaborative planning. The final flight scheme needs to be further adjusted at the global level by the spatiotemporal conflict resolution module. Therefore, this module does not involve collaborative decision-making or conflict handling between multiple UAVs.

[0051] Specifically, when optimizing the path for each drone individually based on the task allocation results: the order in which the drone visits the spatial location of the corresponding task can be obtained based on the task allocation results, under the premise of satisfying the drone's starting position constraint, and the flight path of the drone can be determined; then the flight path is optimized with minimizing the single-drone path cost as the optimization objective.

[0052] For example, for any drone u, step 202 determines the set of tasks it needs to perform as follows: Each task corresponds to a unique spatial location node. The goal of path optimization is to determine the order in which the UAV visits these task nodes, while satisfying the UAV's starting position constraints, thereby forming a single UAV flight path: in, Nu represents the initial position node of the drone u, and Nu is the maximum number of tasks that the drone u can perform.

[0053] Without considering the presence of other drones, path optimization aims to minimize the path cost of a single drone. The path cost can be defined in one or more of the following forms depending on the specific application requirements: a: Minimum total flight distance b: Minimum total flight time c: Minimize the overall path cost (e.g., the weighted sum of distance and time) Path cost can be uniformly expressed as , where c(·) represents the basic flight cost between task nodes, and k represents the spatial location node of the task.

[0054] Next, heuristic or metaheuristic pathfinding methods can be used to optimize the access order among the spatial nodes of the task. Pathfinding methods include, but are not limited to: greedy construction methods, neighborhood search methods, genetic algorithms, simulated annealing or tabu search methods, and other equivalent pathfinding strategies. During the pathfinding process, it must be ensured that each task node is visited exactly once, the path starts at the initial position of the UAV, and there are no physically unreachable cases at the single UAV level.

[0055] For each drone, path optimization can output one or more candidate paths: .

[0056] After the candidate path (optimized path) is determined, a desired flight speed can be assigned to each segment of the path. Furthermore, when setting the desired flight speed for each segment of the optimized path to obtain path-speed candidate schemes for each UAV, a fixed flight speed can be set for each segment of the optimized path, or a specific flight speed can be assigned to each segment of the optimized path according to the segment length ratio, or a regularized flight speed can be set for each segment of the optimized path according to the mission time requirements, thus obtaining a path-speed candidate scheme for each UAV.

[0057] The speed configuration described above is used to generate the initial timeline of the UAV, providing a foundation for subsequent modeling of the spatiotemporal relationships of multiple UAVs.

[0058] Step 204: Using the path-velocity candidate schemes of each UAV, construct the spatiotemporal occupancy relationship of each UAV within a specific time range.

[0059] Specifically, the path length and segment speed in the above path-speed candidate scheme can be used to calculate the flight time of the UAV on each segment and obtain the time-series trajectory of the UAV within the time constraint, thereby obtaining the area occupied by the UAV in the spatiotemporal domain.

[0060] For example, let the flight speed of the UAV in each segment be... Based on the path length and segment speed, the flight time of the UAV on each segment can be calculated, and the time-series trajectory of the UAV within the planned time range can be obtained further: This allows us to construct the area occupied by the drone in the spatiotemporal domain for subsequent conflict detection.

[0061] Step 205: Conflict detection.

[0062] In this embodiment, flight conflict detection can be performed on the occupied areas of all UAVs: specifically, discrete detection based on time steps can be performed on the occupied areas of all UAVs; or event-driven detection based on the arrival time of spatial location nodes of key tasks can be performed on the occupied areas of all UAVs; or continuous time detection based on flight segment intervals can be performed on the occupied areas of all UAVs, etc.

[0063] To ensure the safety of multi-drone coordinated flight, a minimum safe distance can be set between any two drones. For any two distinct drones u and v, at any time t, if the following condition is met: The risk of a spatiotemporal flight conflict between UAV u and UAV v at time t is then determined. Based on the characteristics of the flight conflict, it can be further classified into one of the following conflict types: 1. Simultaneous arrival conflict: Multiple drones enter the same space area at similar times; 2. Path intersection type conflict: The flight paths of different UAVs intersect or overlap in space; 3. Close-following conflict: Drones fly on the same or similar paths with insufficient time intervals.

[0064] When any pair of drones is detected to have violated the safe distance constraint within a certain time interval, the corresponding conflict event is marked, and the drone identification / number, spatial location, and time interval of the conflict are recorded as input for conflict resolution.

[0065] If no flight conflict exists, proceed directly to step 206; if a flight conflict exists, proceed to step 207. Step 206: Determine whether the path-speed candidate scheme meets the output conditions. If it does, output the planning result.

[0066] In this embodiment, the output condition may be that there are no drone pairs that violate the flight safety distance constraint or that the preset maximum number of iterations has been reached.

[0067] Step 207: Adjust the flight status information of the relevant UAVs, then update the path-velocity candidate scheme and continue to detect and adjust the flight conflict on the updated path-velocity candidate scheme until no flight conflict is detected, and output the corresponding updated path-velocity candidate scheme.

[0068] The UAV status information includes takeoff time, arrival time of the mission's spatial location, flight speed of each segment, and flight path. When adjusting the flight status information of relevant UAVs, the takeoff time or arrival time of relevant UAVs can be adjusted; the flight speed of relevant UAVs before or after a certain period of time in the conflicting segments can be redistributed; or the conflicting flight paths of relevant UAVs can be modified.

[0069] In detail, for detected spatiotemporal flight conflict events, a layered and gradual resolution strategy can be adopted to coordinate and adjust the UAV's flight plan. The adjustment (resolution) strategy includes, but is not limited to, the following methods: 1. Conflict resolution based on time adjustment Prioritize adjusting the takeoff time of drones or the arrival time of key mission nodes to stagger the execution of missions on the timeline for drones with conflicting missions, thereby avoiding them entering the conflict area at the same time.

[0070] Time adjustments can be made by fine-tuning the speed of certain segments of the drone's flight path, and the adjusted speed must meet the drone's performance constraints.

[0071] 2. Conflict resolution based on velocity reallocation While keeping the path structure unchanged, the flight speeds before and after the conflict segment are redistributed, causing the time it takes for the UAV to pass through the conflict area to shift, thereby eliminating the conflict.

[0072] This method is suitable for localized conflict scenarios and has minimal impact on the overall task execution.

[0073] 3. Conflict resolution based on local path correction When time or speed adjustments fail to effectively resolve conflicts, the local paths of the relevant drones are modified to bypass the conflict area or adjust the segment connection method, and the local flight trajectory is regenerated while ensuring mission completion.

[0074] It should be noted that local path corrections are only triggered when necessary to avoid causing excessive disturbance to the overall planning structure.

[0075] After resolving a conflict, the flight trajectory and timing in the path-velocity candidate scheme of the UAV can be updated, and the spatiotemporal conflict detection and adjustment can be re-executed. This process is repeated until no flight conflict is detected, and the corresponding updated path-velocity candidate scheme is output.

[0076] Step 208: Determine whether the updated path-speed candidate solution meets the output conditions. If it does, output the planning result.

[0077] When the path planning, speed configuration, and spatiotemporal conflict detection and resolution processes meet the preset termination conditions, the system enters the result output stage, outputting a multi-UAV cooperative flight scheme that meets the mission completion requirements and flight safety constraints.

[0078] If the output conditions are not met, the process will re-enter step 202 to perform tasks such as task allocation.

[0079] The embodiments of the present invention have the following effects: 1. This invention studies the problem of collaborative flight planning for multiple tasks and multiple UAVs in shared airspace. By constructing a hierarchical collaborative planning framework of task allocation, single-aircraft planning, and spatiotemporal conflict resolution, it overcomes the problem of insufficient overall coordination caused by the separation of task allocation and flight planning in traditional methods. It realizes collaborative planning and orderly execution of multiple UAVs in complex task scenarios, and improves the feasibility and overall operational efficiency of the system when the number of UAVs and the scale of tasks are expanded.

[0080] 2. This invention introduces a conflict detection model based on spatiotemporal occupancy relationship to jointly model the flight path and execution time of UAVs. It can accurately identify spatiotemporal conflict risks that may occur when multiple UAVs are flying, such as path intersection, time overlap and insufficient safety distance. This avoids the misjudgment or omission caused by relying on only a single dimension of space or time for conflict judgment, thereby significantly improving the safety and reliability of the multi-UAV cooperative flight process.

[0081] 3. This invention proposes a spatiotemporal conflict resolution mechanism with time coordination as its core. Under the premise of maintaining the relative stability of task allocation results and single UAV path structure, it achieves staggered execution and safe separation of UAVs in the time dimension by locally adjusting flight time and segment speed. This effectively reduces the computational overhead and execution instability caused by frequent global replanning triggered by conflicts, and enhances the stability, robustness and executability of multi-UAV collaborative planning results in actual operation.

[0082] Example 3 Reference Figure 3 The diagram illustrates a multi-UAV cooperative flight planning system for logistics according to Embodiment 3 of the present invention. The system includes: The information initialization module 3001 is used to initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information; the basic information includes: each task and its corresponding spatial location and time constraints, the identifier of each UAV and its corresponding UAV status information; The task allocation module 3002 is used to establish the association between tasks and drones based on the task information set and the drone status information set, and to allocate tasks to drones based on the association that satisfies the task constraints and drone capability limitations, so as to obtain the task allocation result for each drone. The path-speed joint optimization module 3003 is used to optimize the path of each UAV individually according to the task allocation result, and set the expected flight speed for each segment of the optimized path to obtain the path-speed candidate scheme for each UAV. The spatiotemporal conflict detection and resolution module 3004 is used to construct the spatiotemporal occupancy relationship of each UAV within a specific time range and perform flight conflict detection and resolution by utilizing the path-velocity candidate scheme of each UAV. The output module 3005 is used to determine whether the path-speed candidate scheme meets the output conditions when there is no flight conflict. If it does, the planning result is output.

[0083] The system of this invention embodiment may include the above five modules and adopts a two-layer hierarchical collaborative optimization structure: the first layer determines the task allocation of multiple UAVs; the second layer performs joint path and speed optimization for each UAV under the task allocation constraints; and achieves obstacle avoidance and safe separation of multiple UAVs through spatiotemporal conflict detection and time window adjustment, and finally outputs a multi-UAV collaborative flight scheme.

[0084] Specifically, firstly, the basic information required for multi-UAV collaborative planning is set. This basic information includes: the spatial location and temporal constraints of the task, the initial position and flight performance parameters of the UAVs, the flight safety distance, and the planning time range. Depending on the actual application scenario, the initial flight state of the UAVs can be initialized using rules or preset strategies. Then, based on the task set and the UAV set, the association between tasks and UAVs is constructed, and the allocation result of tasks to UAVs is determined under the premise of satisfying task constraints and UAV capability limitations. Next, based on the flight path and speed plan of each UAV, the spatiotemporal occupancy relationship of the UAVs within the planning time range is constructed, and possible path intersections, time overlaps, or insufficient safety distances between UAVs are detected. When spatiotemporal conflicts are detected between UAVs, the conflict is resolved by adjusting the flight time, speed, or local path of the relevant UAVs, and the corresponding flight planning results are updated. Finally, the multi-UAV collaborative planning results are judged. When the planning results meet the task completion requirements and flight safety constraints, the planning process is terminated and the final result is output; when the output conditions are not met, the process returns to the aforementioned module to continue iterative updates until preset conditions are met or the maximum number of iterations is reached.

[0085] For example, in an implementation scenario such as urban logistics, inspection, or emergency response areas, there are multiple spatially distributed task points that need to be completed collaboratively by multiple drones within a given time frame. Each drone has a different initial position and flight performance parameters, and they need to operate within the same airspace.

[0086] Scenario assumption: Suppose there are T task points within the target area, and the corresponding task set is as follows: The system contains U-shaped drones, whose set is represented as: Each task point corresponds to a spatial location and an executable time window; each UAV has performance parameters such as initial position, maximum flight speed, and minimum safe distance. The system plans the time range as [0, Tmax] and performs time discretization as needed. Then, it performs operation steps similar to task allocation in Example 2, which will not be described in detail here.

[0087] Example 4 This invention also provides an electronic device, such as... Figure 4 As shown, it includes a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304. Memory 303 is used to store computer programs; When processor 301 executes program 305 stored in memory 303, it performs the following steps: Initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information; the basic information includes: each task and its corresponding spatial location and time constraints, the identifier of each UAV and its corresponding UAV status information; Based on the task information set and the UAV status information set, an association between tasks and UAVs is established, and the association that satisfies the task constraints and UAV capability limitations is used to allocate tasks to UAVs, resulting in task allocation results for each UAV. Based on the task allocation results, path optimization is performed individually for each UAV, and a desired flight speed is set for each segment of the optimized path to obtain a path-speed candidate scheme for each UAV. Using the path-velocity candidate schemes of each UAV, the spatiotemporal occupancy relationship of each UAV within a specific time range is constructed and flight conflict detection is performed; If no flight conflict exists, determine whether the path-velocity candidate scheme meets the output conditions. If it does, output the planning result.

[0088] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0089] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0090] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0091] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0092] The method provided in this invention can be applied to electronic devices. Specifically, the electronic device can be a desktop computer, a portable computer, a smart mobile terminal, a server, etc. No limitation is made herein; any electronic device that can implement this invention falls within the protection scope of this invention.

[0093] For the electronic device / storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and relevant details can be found in the description of the method embodiments.

[0094] It should be noted that the electronic device and storage medium in the embodiments of the present invention are respectively the electronic device and storage medium for applying the above-mentioned multi-UAV cooperative flight planning method for logistics. Therefore, all embodiments of the above-mentioned multi-UAV cooperative flight planning method for logistics are applicable to the electronic device and storage medium, and can achieve the same or similar beneficial effects.

[0095] The terminal device provided by the embodiments of the present invention can display proper nouns and / or fixed phrases for users to select, thereby reducing user input time and improving user experience.

[0096] This terminal device exists in various forms, including but not limited to: (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and are primarily designed to provide voice and data communication. These terminals include smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones.

[0097] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, possessing computing and processing capabilities, and generally also have mobile internet access features. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0098] (3) Portable entertainment devices: These devices can display and play multimedia content. This category includes audio and video players (such as iPods), handheld game consoles, e-book readers, as well as smart toys and portable car navigation devices.

[0099] (4) Other electronic devices with data interaction functions.

[0100] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0101] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.

[0102] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0103] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects, all of which are collectively referred to herein as "modules" or "systems." Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The computer program may be stored / distributed in a suitable medium, provided with or as part of other hardware, or may take other distribution forms, such as via the Internet or other wired or wireless telecommunications systems.

[0104] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A multi-UAV cooperative flight planning method for logistics, characterized in that, The method includes: Initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information; the basic information includes: each task and its corresponding spatial location and time constraints, the identifier of each UAV and its corresponding UAV status information; Based on the task information set and the UAV status information set, an association between tasks and UAVs is established, and the association that satisfies the task constraints and UAV capability limitations is used to allocate tasks to UAVs, resulting in task allocation results for each UAV. Based on the task allocation results, path optimization is performed individually for each UAV, and a desired flight speed is set for each segment of the optimized path to obtain a path-speed candidate scheme for each UAV. Using the path-velocity candidate schemes of each UAV, the spatiotemporal occupancy relationship of each UAV within a specific time range is constructed and flight conflict detection is performed; If no flight conflict exists, determine whether the path-velocity candidate scheme meets the output conditions. If it does, output the planning result.

2. The method according to claim 1, characterized in that, After constructing the spatiotemporal occupancy relationship of each UAV within a specific time range and performing flight conflict detection using the path-velocity candidate scheme for each UAV, the process also includes: When a flight conflict exists, the flight status information of the relevant UAVs is adjusted, and then the path-velocity candidate scheme is updated. The updated path-velocity candidate scheme is then subjected to continued flight conflict detection and adjustment until no flight conflict is detected. The step of determining whether the path-speed candidate scheme meets the output condition, and if so, outputting the planning result, includes: Determine whether the updated path-speed candidate scheme meets the output conditions. If it does, output the planning result.

3. The method according to claim 2, characterized in that, The UAV status information includes takeoff time, arrival time at the mission's spatial location, flight speed for each segment, and flight path. When a flight conflict exists, the flight status information of the relevant UAVs is adjusted, including: When a flight conflict exists, the takeoff time or arrival time of the relevant UAVs is adjusted; or the flight speed of the relevant UAVs is redistributed for a certain period of time before or after the conflict segment; or the conflict flight path of the relevant UAVs is modified.

4. The method according to claim 1, characterized in that, Based on the task information set and the UAV status information set, an association is established between tasks and UAVs, and the associations that satisfy task constraints and UAV capability limitations are used to allocate tasks to UAVs, resulting in task allocation results for each UAV; including: Based on the task information set and the UAV status information set, a task allocation objective function for each UAV is constructed using the task allocation cost; Under the conditions of satisfying the task constraints and UAV capability limitations, the objective function for task allocation is solved to obtain the task allocation decision variables for each UAV; The task allocation decision variables for each UAV are combined to obtain the task allocation result for the corresponding UAV.

5. The method according to claim 1, characterized in that, The step of optimizing the path for each drone individually based on the task allocation result includes: Based on the task allocation results, and under the premise of satisfying the UAV's starting position constraints, the order in which the UAV visits the spatial positions of the corresponding tasks is obtained, and the flight path of the UAV is determined. The flight path is optimized with the goal of minimizing the single-machine path cost.

6. The method according to claim 1, characterized in that, The process of setting a desired flight speed for each segment of the optimized path to obtain path-speed candidate schemes for each UAV includes: A fixed flight speed is set for each segment of the optimized path, or a specific flight speed is allocated to each segment of the optimized path according to the segment length ratio, or a regularized flight speed is set for each segment of the optimized path according to the mission time requirements, to obtain the path-speed candidate scheme for each UAV.

7. The method according to claim 1, characterized in that, The process of constructing the spatiotemporal occupancy relationship of each UAV within a specific time range and performing flight conflict detection using the path-velocity candidate scheme of each UAV includes: Using the path length and segment speed in the path-speed candidate scheme, the flight time of the UAV on each segment is calculated, and the time-series trajectory of the UAV within the time constraint is obtained, thus obtaining the area occupied by the UAV in the spatiotemporal domain. Perform traversal flight conflict detection on the occupied areas of all drones.

8. The method according to claim 7, characterized in that, The process of traversing and detecting flight conflicts across the occupied areas of all drones includes: The occupied areas of all UAVs can be detected discretely based on time steps; or the occupied areas of all UAVs can be detected event-driven based on the arrival time of the spatial location of the critical mission; or the occupied areas of all UAVs can be detected continuously based on flight segment intervals.

9. The method according to claim 1, characterized in that, The output conditions include: There are no drone pairs that violate flight safety distance constraints or reach the preset maximum number of iterations.

10. A multi-UAV cooperative flight planning system for logistics, characterized in that, The system includes: The information initialization module is used to initialize the basic information required for multi-UAV cooperative flight planning, and obtain the set of task information to be executed and the set of UAV status information; the basic information includes: each task and its corresponding spatial location and time constraints, the identifier of each UAV and its corresponding UAV status information; The task allocation module is used to establish the association between tasks and drones based on the task information set and the drone status information set, and to allocate tasks to drones based on the association that satisfies the task constraints and drone capability limitations, so as to obtain the task allocation result for each drone. The path-speed joint optimization module is used to optimize the path of each UAV individually based on the task allocation result, and set the expected flight speed for each segment of the optimized path to obtain the path-speed candidate scheme for each UAV. The spatiotemporal conflict detection and resolution module is used to construct the spatiotemporal occupancy relationship of each UAV within a specific time range and perform flight conflict detection and resolution by utilizing the path-velocity candidate scheme of each UAV. The output module is used to determine whether the path-speed candidate scheme meets the output conditions when there is no flight conflict. If it does, the planning result is output.

Images