Unmanned aerial vehicle recovery path self-adaptive planning method and system based on air-ground cooperation

Abstract

The invention provides an unmanned aerial vehicle recovery path self-adaptive planning method and system based on air-ground cooperation, and relates to the technical field of robot motion planning, and the method comprises the steps: constructing a three-dimensional grid map of a task environment, and obtaining the positions of an unmanned aerial vehicle and an unmanned vehicle, and the maximum flight distance of the unmanned aerial vehicle; based on the positions of the unmanned aerial vehicle and the unmanned vehicle and the maximum flight distance of the unmanned aerial vehicle, determining responsibility distribution of the unmanned aerial vehicle and the unmanned vehicle in the recovery task, and obtaining an optimal unmanned aerial vehicle recovery scheme; selecting a corresponding path planning mode according to the optimal unmanned aerial vehicle recovery scheme, and determining a starting point and an ending point of path planning and dimensions of a search space based on the positions of the unmanned aerial vehicle and the unmanned aerial vehicle; according to the selected path planning mode, executing a path planning algorithm to generate a final recovery path; through the air-ground collaborative decision and cross-dimension bidirectional joint path planning algorithm, safe and efficient recovery of the unmanned aerial vehicle under the electric quantity constraint is realized, and the task success rate and the system collaborative efficiency are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of robot motion planning technology, specifically to an adaptive planning method and system for UAV recovery paths based on air-ground cooperation. Background Technology

[0002] Drones, with their wide field of vision and high maneuverability, have gained favor among numerous researchers and institutions. However, their limited endurance makes them unsuitable for long-range, high-payload tasks, severely restricting their application scope. Air-ground collaborative systems, by organically integrating the advantages of drones with the long endurance and heavy payload capacity of unmanned vehicles (UAVs), can accomplish complex tasks exceeding the capabilities of individual drones / vehicles, demonstrating strong application potential in a wide range of scenarios such as wilderness search and rescue, express delivery, and environmental monitoring. During mission execution, the UAV, while acting as the individual mission executor, also serves as a mission support platform for the air-ground collaborative system, providing a charging platform for the drones. This effectively expands the mission coverage and comprehensively enhances the overall mission resilience of the system. This requires multiple interactions and coordination between the drone and the UAV, with drone recovery being a crucial link in ensuring successful mission execution.

[0003] In practical applications, drones and unmanned vehicles (UAVs) typically undertake different sub-tasks in air-ground collaborative mission scenarios, such as executing tasks in different areas, of different types, or at different stages, in order to fully leverage the advantages of drone-UAV collaboration, decompose complex tasks, and improve the overall execution efficiency and quality of the mission. Therefore, when a drone's battery is low, due to distance and environmental limitations, it may be difficult for the drone to land on the UAV before its battery runs out. How to achieve safe and efficient recovery under battery constraints is a highly challenging problem in the mission execution process of air-ground collaborative systems.

[0004] Most existing drone recovery methods are based on a single platform perspective, planning the path and trajectory of the drone or unmanned vehicle independently, lacking air-ground collaborative decision-making. This results in insufficient collaboration between drones and unmanned vehicles, leading to suboptimal recovery paths in terms of coordination, safety, and energy efficiency. Furthermore, existing drone recovery methods typically focus on the performance of the landing platform's visual recognition or landing control, neglecting to consider the drone's battery constraints. This makes it difficult to guarantee the success rate of recovery missions when the drone's battery is low, and may even lead to serious accidents such as crashes due to battery depletion. Summary of the Invention

[0005] To address the aforementioned issues, this invention proposes an adaptive planning method and system for UAV recovery paths based on air-ground collaboration. Through air-ground collaborative decision-making and a cross-dimensional bidirectional joint path planning algorithm, it achieves safe and efficient UAV recovery under power constraints, significantly improving mission success rate and system collaboration efficiency.

[0006] According to some embodiments, the present invention adopts the following technical solution: An adaptive planning method for UAV recovery paths based on air-ground cooperation includes: Construct a 3D grid map of the mission environment to obtain the positions of drones and unmanned vehicles, as well as the maximum flight distance of drones; Based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, the responsibility allocation of the drone and the unmanned vehicle in the recovery task is determined, and the optimal drone recovery plan is obtained. Based on the optimal drone recovery scheme, the corresponding path planning mode is selected, and the starting point, ending point, and search space dimensions of the path planning are determined based on the locations of the drone and the unmanned vehicle. Based on the selected path planning mode, the path planning algorithm is executed to generate the final recycling path; In the aforementioned responsibility allocation scheme, when the drone and the unmanned vehicle each assume part of the recovery responsibility, a cross-dimensional bidirectional joint path planning algorithm is used to generate safe travel paths for the drone and the unmanned vehicle under path distance constraints.

[0007] According to some embodiments, the present invention adopts the following technical solution: An adaptive planning system for drone recovery paths based on air-ground cooperation includes: The location acquisition module is configured to: construct a 3D grid map of the mission environment, acquire the location of the drone and unmanned vehicle, and the maximum flight distance of the drone; The responsibility allocation module is configured to determine the responsibility allocation between the drone and the unmanned vehicle in the recovery task based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, so as to obtain the optimal drone recovery plan. The mode selection module is configured to: select the corresponding path planning mode based on the best drone recovery scheme, and determine the starting point, ending point and search space dimensions of the path planning based on the positions of the drone and the unmanned vehicle; The path planning module is configured to execute a path planning algorithm based on the selected path planning mode to generate the final recycling path. In the aforementioned responsibility allocation scheme, when the drone and the unmanned vehicle each assume part of the recovery responsibility, a cross-dimensional bidirectional joint path planning algorithm is used to generate safe travel paths for the drone and the unmanned vehicle under path distance constraints.

[0008] According to some embodiments, the present invention adopts the following technical solution: A computer program product includes a computer program that, when executed by a processor, implements the aforementioned adaptive planning method for UAV recovery paths based on air-ground cooperation.

[0009] According to some embodiments, the present invention adopts the following technical solution: A non-transitory computer-readable storage medium is provided for storing computer instructions, which, when executed by a processor, implement the aforementioned adaptive planning method for UAV recovery paths based on air-ground cooperation.

[0010] According to some embodiments, the present invention adopts the following technical solution: An electronic device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the adaptive planning method for UAV recovery path based on air-ground cooperation.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention constructs a dynamic decision-making mechanism for drone recovery tasks based on the location of the drone and the unmanned vehicle, as well as the drone's battery level (maximum flight range). This mechanism enables adaptive allocation of responsibilities between the drone and the unmanned vehicle during the recovery process. It fully leverages the overall efficiency of the air-ground collaborative system, significantly improving the intelligence level of collaborative operations and the reliability of task execution, effectively ensuring the safe and efficient recovery of drones under battery constraints.

[0012] This invention proposes three drone recovery schemes: Ego, SemiAid, and FullAid. These schemes enable safe drone recovery while strictly adhering to remaining battery power constraints, minimizing the impact of the recovery process on the original mission of the unmanned vehicle (UAV). Specifically, the maximum flight distance of the drone is considered in both the drone recovery decision-making mechanism and the path planning algorithm. This assesses the drone's ability to complete the safe recovery task independently, allowing for the addition of UAV assistance only when necessary. Furthermore, the drone's flight distance is maximized under limited battery power constraints to minimize the degree to which the UAV deviates from its original mission area, ensuring that the UAV can quickly return to its original mission area after the recovery task is completed.

[0013] This invention proposes a cross-dimensional bidirectional joint path planning algorithm that can simultaneously maintain two search processes: a three-dimensional forward search and a two-dimensional backward search. This efficiently generates safe travel paths for both the drone and the unmanned vehicle (UAV) to meet drone recovery mission requirements. By introducing a guiding term for searching the current node on the other side into the heuristic function, both search processes can be encouraged to expand broadly and rapidly towards each other. When a node expands to a safe boundary, the search conditions are immediately tightened, and a set of candidate rendezvous points is constructed. When selecting the optimal rendezvous point, while ensuring the drone's flight distance meets the remaining battery power constraint, a waiting cost assessment is added to balance the execution time of the forward and backward paths, preventing one side from waiting for an extended period. Attached Figure Description

[0014] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0015] Figure 1 The flowchart is shown in Example 1, illustrating the adaptive planning method for UAV recovery paths based on air-ground cooperation. Figure 2 The image shows the simulation results of UAV recovery under the Ego recovery scheme in Example 1. (a) is the front view of the simulation results, (b) is the top view of the simulation results, and the blue line is the UAV's travel path. Figure 3 The image shows the simulation results of UAV recovery under the SemiAid recovery scheme in Example 1. (a) is the front view of the simulation results, (b) is the top view of the simulation results, the blue line is the UAV's travel path, and the red line is the unmanned vehicle's travel path. Figure 4 The image shows the simulation results of UAV recovery under the FullAid recovery scheme in Example 1. (a) is the front view of the simulation results, (b) is the top view of the simulation results, the blue line is the UAV's travel path, and the red line is the unmanned vehicle's travel path. Detailed Implementation

[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0017] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0018] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0019] Example 1 One embodiment of the present invention provides an adaptive planning method for UAV recovery paths based on air-ground cooperation, comprising: Step 1: Construct a 3D grid map of the mission environment to obtain the positions of the drone and unmanned vehicle, as well as the maximum flight distance of the drone; Step 2: Based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, determine the allocation of responsibilities between the drone and the unmanned vehicle in the recovery mission, and obtain the optimal drone recovery plan; Step 3: Based on the optimal drone recovery plan, select the corresponding path planning mode, and determine the starting point, ending point, and search space dimensions of the path planning based on the locations of the drone and unmanned vehicle; Step 4: Based on the selected path planning mode, execute the path planning algorithm to generate the final recycling path; In the aforementioned responsibility allocation scheme, when the drone and the unmanned vehicle each assume part of the recovery responsibility, a cross-dimensional bidirectional joint path planning algorithm is used to generate safe travel paths for the drone and the unmanned vehicle under path distance constraints.

[0020] The responsibility allocation here clarifies the responsibilities of the drone and the unmanned vehicle (UAV) during the recovery process, based on the actual state of the system (the positions of the drone and UAV, and the maximum flight distance of the drone). Responsibility allocation is crucial for achieving successful air-ground collaborative recovery and forms the basis for drone recovery schemes. The responsibilities of the drone and the UAV differ in the three recovery schemes, and the path planning algorithms employed also differ: In the Ego recovery scheme, the UAV only provides a landing platform, and the recovery responsibility is entirely assigned to the drone; only path planning is needed for the drone (the UAV performs its original task, and its path planning is not within the scope of this invention), using a unidirectional path planning algorithm; in the SemiAid recovery scheme, the recovery responsibility is shared between the drone and the UAV, requiring simultaneous path planning for both, using a cross-dimensional bidirectional joint path planning algorithm; in the FullAid recovery scheme, the recovery responsibility is primarily assigned to the UAV, with the drone only assisting the UAV in landing after its arrival; only path planning is needed for the UAV, using a unidirectional path planning algorithm. As one embodiment, the UAV recovery path adaptive planning method based on air-ground cooperation of the present invention achieves safe and efficient recovery of UAVs under power constraints through air-ground cooperative decision-making and cross-dimensional bidirectional joint path planning algorithm, which significantly improves the mission success rate and system cooperation efficiency. The specific implementation process is described below.

[0021] S1 Initialization: Construct a 3D grid map of the mission environment, obtain the positions of the drone and unmanned vehicle, and the maximum flight distance of the drone; Furthermore, the location of the drones and unmanned vehicles is provided by the positioning system, and the maximum flight distance of the drones can reflect the remaining battery power, which is used to make calculations.

[0022] Specifically, the grid in this embodiment Figure 3 The resolution of each dimension is [missing information]. The origin of the coordinate system is The actual location information of the drone can be obtained through an optical motion capture positioning system. Real-time location information of unmanned vehicles The maximum flight distance of the drone is .

[0023] S2 Drone Recovery Solution Decision: Based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, determine the allocation of responsibilities between the drone and the unmanned vehicle in the recovery task, and obtain the optimal drone recovery solution; The available drone recovery solutions include three options: Ego, SemiAid, and FullAid, as follows: (1) In the Ego recovery scheme, the drone assumes the recovery responsibility on its own: the drone navigates to the unmanned vehicle landing platform and lands on its own, and the unmanned vehicle's mission is not affected in any way during the entire recovery process; (2) In the SemiAid recovery plan, the drone and the unmanned vehicle shall each assume part of the recovery responsibility: the unmanned vehicle shall suspend its current task and move towards the drone. Under the guidance of the best rendezvous point, the drone shall land on the unmanned vehicle landing platform to complete the recovery task. Then the unmanned vehicle shall return to its original task area to continue its task. (3) In the FullAid recovery scheme, the unmanned vehicle assumes the main responsibility for recovery: the drone turns on the power saving mode or lands temporarily and waits for the unmanned vehicle to pick it up. The unmanned vehicle then suspends its current task and goes to the location of the drone to assist the drone in completing the landing.

[0024] Specifically, the best drone recovery solution Choose according to the following formula:

[0025] in, Both are positive numbers, representing the user-defined security threshold and distance coefficient, respectively. This indicates the distance between the drone and the unmanned vehicle.

[0026] In the FullAid recovery scenario, if the drone's battery is severely depleted, the drone will shut down the power of non-essential hardware (such as lights and thermal imagers) in power-saving mode. The drone will hover at the minimum power required for flight, awaiting pickup by the unmanned vehicle. Since the drone's battery continues to be consumed in power-saving mode, to further ensure drone safety and increase the likelihood of successful recovery, the drone can also be landed directly in a nearby select landing area (to avoid crashing due to depleted battery). After the unmanned vehicle arrives, the drone can take off again and land on the unmanned vehicle's landing platform, or it can be transferred to the unmanned vehicle's landing platform by the clamping device on the unmanned vehicle. Whether to choose power-saving mode hovering or temporary landing can be selected based on the actual situation of the drone.

[0027] The primary responsibility for recovery here is not the same as solely undertaking the recovery responsibility. In the FullAid recovery scheme, the distance between the drone and the unmanned vehicle is shortened by the unmanned vehicle, and the recovery responsibility is mainly borne by the unmanned vehicle. After the unmanned vehicle arrives near the location of the drone, the drone needs to cooperate with the unmanned vehicle to complete the landing. That is, during the landing phase, the drone needs to assume a certain recovery responsibility. In contrast, in the Ego recovery scheme, the entire recovery process does not require the cooperation of the unmanned vehicle. The unmanned vehicle only provides a landing platform, and its original mission is not affected in any way. Therefore, it is said that the drone independently undertakes the recovery responsibility.

[0028] S3 Path Planning Mode Decision: Based on the optimal drone recovery plan, select the corresponding path planning mode, and determine the starting point, ending point, and search space dimensions based on the locations of the drone and unmanned vehicle; Furthermore, the available path planning modes include two types: one-way and two-way, as follows: (1) In the unidirectional path planning mode, the path planning algorithm has both two-dimensional and three-dimensional spatial path planning capabilities, has a definite starting point and ending point, maintains only one search process, and will eventually generate a path; (2) In the bidirectional path planning mode, the path planning algorithm has two definite starting points and maintains two search processes in different dimensions and directions: forward search and backward search. The two search processes meet at the best meeting point determined in the search process, and finally generate two paths: the three-dimensional flight path of the UAV and the two-dimensional travel path of the unmanned vehicle.

[0029] Furthermore, different recycling schemes correspond to different path planning patterns, and the starting point, ending point, and search space dimensions of the planning algorithm also differ, as detailed below: The Ego recovery scheme corresponds to a one-way path planning mode, where the starting point of the planning algorithm is the drone's position. The destination is the location of the driverless car. Search space dimension ; The SemiAid recovery scheme corresponds to a bidirectional path planning mode, where the forward search starting point of the planning algorithm is the drone's position. Search space dimension The backward search starts from the location of the autonomous vehicle. Search space dimension The forward and backward searches reach the same endpoint, which is the optimal meeting point selected during the search process by comprehensively considering factors such as the drone's flight distance, search efficiency, and the impact of the unmanned vehicle's original mission. The FullAid recovery scheme corresponds to a one-way path planning mode, where the starting point of the planning algorithm is the location of the autonomous vehicle. The endpoint is the projected position of the drone on the plane where the unmanned vehicle is located. Search space dimension .

[0030] S4 Path Planning: Based on the selected path planning mode, execute the path planning algorithm to generate the final recovery path. If the generated path meets the requirements of the drone recovery mission, the process ends; otherwise, execute S2. If the recycling scheme determined in step S2 is Ego or FullAid, then the one-way path planning mode is adopted in S3. The specific steps of the corresponding one-way path planning algorithm are as follows: SS401 initializes the open list, closed list, and initial node; Specifically, the rasterized coordinates of the start and end points are: , ,in, The floor function is used for rounding down; open lists are used for rounding down. The closed list is The initial node coordinates are Its actual cost The heuristic cost is:

[0031] in, They represent The smallest, medium, and largest absolute values ​​among all elements.

[0032] The overall cost of the initial node is:

[0033] in, These are the weighting coefficients.

[0034] Initial node Insert open list middle.

[0035] SS402, based on spatial dimension, constructs the corresponding node increment vector; Specifically, the node increment vector represents the coordinate increment of a node in each direction and the cost incurred. In a two-dimensional search, nodes can only expand in eight directions (axial and 2D diagonals), so the node increment vector in two-dimensional space is... ,in, The node increment is represented by the coordinate increment. and actual cost increment It consists of two parts. .

[0036] During a 3D space search, nodes can expand in 26 directions (axial, 2D diagonal, and 3D diagonal), so the node increment vector in 3D space is... ,in, The node increment is represented by the coordinate increment. and actual cost increment It consists of two parts. .

[0037] SS403, based on the start and end positions, constructs an initial ellipse expansion constraint to limit the expansion range of nodes in the horizontal direction; Specifically, the ellipse extension constraint It is obtained by rotating and scaling the unit circle, and can be expressed by the formula:

[0038] in, Let be a point inside a circle with center at the origin and radius 1. For rotation matrix, For scaling matrices, Ellipse The length of the major semi-axis, Ellipse The length of the short semi-axis, Ellipse The center.

[0039] Initial ellipse expansion constraint The center is set as the midpoint of the two-dimensional projection line segment connecting the start and end points, and the scaling matrix is ​​set according to the length of this line segment. Specifically, the initial ellipse expansion constraint... center The length of the major semi-axis The length of the minor half-axis , Starting point coordinates, The endpoints are respectively The coordinate values.

[0040] During the search, the size of the ellipse is dynamically adjusted based on the search status. The introduction of ellipse extension constraints restricts the search to the vicinity of the line segment connecting the start and end points, avoiding a large number of meaningless searches.

[0041] SS404, if open list If not empty, proceed to step SS405; otherwise, proceed to step SS406. SS405, Extract Open List The node with the lowest overall cost is designated as the current node. If its coordinates match the destination coordinates, a safe path is obtained through node backtracking, and the algorithm terminates. Otherwise, the current node is used as the parent node, and new nodes to be expanded are constructed based on the node increment vector. The actual cost, heuristic cost, and overall cost of the effective nodes to be expanded are calculated, and they are inserted into the open list. Execute step SS404; Specifically, the current node coordinates are ,Right now The node with the lowest overall cost is selected from the open list. Insert into a closed list after extraction and in Delete it.

[0042] If the current node coordinates coordinates of the endpoint If inconsistent, then the current node Overlay node increment Construct a new node to be expanded, with coordinates as follows: The actual cost is From the constructed nodes to be expanded, select those that simultaneously satisfy the elliptic expansion constraint and the safety constraint (nodes are within the safe region, i.e., the obstacle-free region) and are not located in the area specified in the original text. The node in the list is treated as a valid node to be expanded, and after updating its parent node and cost, or calculating its cost, it is inserted into the open list. .

[0043] Specifically, if the valid node to be expanded is already... If the current node is selected, its actual cost and total cost are updated, and its parent node is set to the current node; otherwise, its heuristic cost is calculated.

[0044] in, They represent The smallest, medium, and largest values ​​among the absolute values ​​of each element. This is the angle formed by the new node with the start and end points. This function considers axial, 2D diagonal, and 3D diagonal movement costs, providing estimates closer to the actual path costs, which helps guide the search to approach the target point more quickly; it also introduces a path curvature penalty term. This encourages the algorithm to reduce unnecessary turns and improve path quality. Calculate the comprehensive cost of the effective nodes to be expanded:

[0045] SS406: If the current search boundary is already the maximum search boundary, the search fails and the algorithm ends; otherwise, appropriately increase the size of the ellipse to expand the search range and execute step SS404.

[0046] Specifically, the center of the ellipse remains unchanged, and the size of the ellipse is adjusted using a scaling matrix, that is, both the major and minor semi-axis are simultaneously expanded to [a larger size]. times, ,in This is the scaling adjustment factor.

[0047] If the recycling scheme determined in step S2 is SemiAid, then the bidirectional path planning mode is adopted in S3. The corresponding cross-dimensional bidirectional joint path planning algorithm has the following specific steps: SD401 initializes the open list, closed list, and initial node for the forward and backward searches; Specifically, the rasterized coordinates of the starting points for the forward and backward searches are respectively... , ,in This is the floor operation. The open lists for the forward search and backward search are respectively... , The closed lists are respectively , The initial node coordinates are respectively , The actual costs are respectively , The heuristic costs are as follows:

[0048]

[0049] in, They represent The minimum, medium, and maximum absolute values ​​of each element. They represent The combined costs for the minimum, medium, and maximum absolute values ​​of each element are as follows:

[0050]

[0051] in, These are the weighting coefficients.

[0052] Will insert ,Will insert .

[0053] SD402 simultaneously constructs both three-dimensional spatial node increment vectors and two-dimensional spatial node increment vectors; Specifically, the node increment vector in the forward search three-dimensional space. Increment of each node Including coordinate increments and actual cost increment Two parts, .

[0054] Backward search of node increment vectors in 2D space Increment of each node Including coordinate increments and actual cost increment Two parts, .

[0055] SD403, based on the forward search start point and the backward search start point, constructs an initial ellipse expansion constraint to limit the expansion range of nodes in the horizontal direction; Specifically, the ellipse extension constraint It is obtained by rotating and scaling the unit circle, expressed by the formula: , in, Let be a point inside a circle with center at the origin and radius 1. For rotation matrix, For scaling matrices, Ellipse The length of the major semi-axis, Ellipse The length of the short semi-axis, Ellipse The center.

[0056] Initial ellipse expansion constraint The center is set as the midpoint of the two-dimensional projection line segment connecting the start and end points, and the scaling matrix is ​​set according to the length of this line segment. Specifically, the initial ellipse expansion constraint... center The length of the major semi-axis The length of the minor half-axis , Each represents the starting point of the forward search. coordinates, These are the starting points of the backward search. The coordinate values.

[0057] During the search process, the size of the ellipse is dynamically adjusted based on the search status. The introduction of ellipse extension constraints restricts the search to the vicinity of the line segment connecting the start and end points, avoiding a large number of meaningless searches. In particular, in this bidirectional path planning, both the forward and backward search processes are confined within the elliptical region, greatly increasing the probability of the two search processes meeting.

[0058] SD404: If the forward search has ended, proceed to step SD407; otherwise, extract the node with the minimum overall cost from the forward open list as the current node, and construct a set of forward candidate rendezvous points based on the maximum flight distance of the UAV. Specifically, the coordinates of the current node in the forward search are: That is, forward open list The node with the lowest overall cost has an actual cost of The node from Remove and insert into the forward closed list and in Delete. If Then add the current node to the forward candidate rendezvous point set. .

[0059] SD405: If the coordinates of the current node are consistent with the coordinates of the starting point of the backward search, the forward search process ends; otherwise, a new node to be expanded is constructed based on the current node and the incremental vector of the nodes in the three-dimensional space. The actual cost, heuristic cost and comprehensive cost of the effective node to be expanded are calculated and inserted into the open list. Specifically, the coordinates of the current node Coordinates of the starting point of the backward search If there is a discrepancy, a new node to be expanded is constructed by overlaying the current node with the incremental nodes in the three-dimensional space, and its coordinates are... The actual cost is From the constructed nodes to be expanded, select those that simultaneously satisfy the elliptical expansion constraint, the safety constraint (the node is within the safe region, i.e., the obstacle-free region), and the flight distance constraint, and are not located in the area specified in the original text. The node in the list is treated as a valid node to be expanded, and after updating its parent node and cost, or calculating its cost, it is inserted into the forward open list. .

[0060] Specifically, if the valid node to be expanded is already... If the current node is selected, its actual cost and total cost are updated, and its parent node is set to the current node; otherwise, its heuristic cost is calculated. ,

[0061] in, They represent The minimum, medium, and maximum absolute values ​​of each element. Let this be the angle formed by the new node and the starting points of both the forward and backward searches. Calculate the comprehensive cost of the effective nodes to be expanded:

[0062] Determine the forward search boundary based on the maximum flight distance of the UAV. and relative search boundaries , The flight distance constraint is determined by the actual cost of the new node. If the node is not found, it is discarded. To improve the speed of finding the optimal meeting point, after the size of the forward candidate meeting point set reaches a custom threshold, new nodes close to the starting point are filtered out, restricting new nodes to the neighborhood before the forward search boundary. .

[0063] SD406: If the forward open list is empty, increase the size of the ellipse appropriately within the maximum search range. If the current search range has reached the boundary of the maximum search range, end the forward search process. The ellipse size adjustment is the same as in step SS406, and will not be repeated here.

[0064] SD407: If the backward search has ended but the forward search has not ended, proceed to step SD410; if both the backward search and the forward search have ended, proceed to step SD411; otherwise, extract the node with the minimum comprehensive cost from the backward open list as the current node and construct a set of backward candidate meeting points. Specifically, the coordinates of the current node in the backward search are: Backward open list The node with the lowest overall cost has an actual cost of ,like Then add the current node to the set of backward candidate rendezvous points. .

[0065] SD408: If the coordinates of the current node are consistent with the two-dimensional projection coordinates of the starting point of the forward search, then the forward search process ends; otherwise, a new node to be expanded is constructed based on the current node and the incremental vector of the node in the two-dimensional space. The actual cost, heuristic cost and comprehensive cost of the effective node to be expanded are calculated and inserted into the open list. Specifically, if the current node coordinates Two-dimensional projection coordinates of the forward search starting point If they are inconsistent, a new node to be expanded is constructed by superimposing the current node with the incremental nodes in the two-dimensional space, and its coordinates are... The actual cost is From the constructed nodes to be expanded, select those that simultaneously satisfy the elliptic expansion constraint and the safety constraint (nodes are within the safe region, i.e., the obstacle-free region) and are not located in the area specified in the original text. The node in the list is treated as a valid node to be expanded, and after updating its parent node and cost, or calculating its cost, it is inserted into the back open list. .

[0066] Specifically, if the valid node to be expanded is already... If the current node is selected, its actual cost and total cost are updated, and its parent node is set to the current node; otherwise, its heuristic cost is calculated.

[0067]

[0068] in, They represent The minimum, medium, and maximum absolute values ​​of each element. Let this be the angle formed by the new node and the starting points of both the forward and backward searches. Calculate the comprehensive cost of the effective nodes to be expanded:

[0069] The relative search boundary for the backward search is determined based on the maximum flight distance of the UAV. , To fully utilize the drone's remaining battery power, minimize the impact on the vehicle's original mission, and simultaneously improve the speed of finding the optimal rendezvous point, after the size of the backward candidate rendezvous point set reaches a custom threshold, new nodes close to the forward and backward search starting points are filtered out, restricting new nodes to the neighborhood of the drone's maximum flight distance. . SD409: If the backward open list is empty, the size of the ellipse is increased appropriately within the maximum search range. If the current ellipse has reached the boundary of the maximum search range, the backward search process ends. The ellipse size adjustment is the same as in step SS406, and will not be repeated here. SD410: Based on the states of the forward and backward searches and the size of the candidate meeting point set, attempt to calculate the intersection of the forward candidate meeting point set and the backward candidate meeting point set to find the optimal meeting point. If the optimal meeting point is found, proceed to step SD411; otherwise, proceed to step SD404. Specifically, the actual cost of forward candidate meeting points exist Internal value selection, backward candidate meeting point heuristic cost Traditional Chinese heuristic cost exist The inner value is taken, where In the early stages of planning, nodes located far from the safety boundary allow for a wider search. As nodes expand to the safety boundary, a boundary control mechanism is triggered, tightening the search conditions and constructing a set of forward / backward candidate rendezvous points to improve the speed of finding effective rendezvous points. The expansion range of forward search nodes is determined by the actual cost. The decision extends as far as... This ensures that the forward search does not exceed a preset safe distance, thus strictly limiting the drone's flight path to its range. The expansion range of the backward search nodes is determined by the backward search heuristic cost. Traditional Chinese heuristic cost The decision extends as far as... To reduce unnecessary expansion.

[0070] Furthermore, when the sizes of both the forward and backward candidate meeting point sets reach the threshold, or when the search on one side terminates and the size of the candidate meeting point set on the other side reaches the threshold, the candidate meeting point set is calculated. The combined cost of each node Recalculate using the following formula:

[0071] in, and These represent the actual cost obtained during the forward search and the actual cost obtained during the backward search of the current node, respectively. and These represent the expected speeds of the drone and the unmanned vehicle, respectively. Indicates the waiting cost weight. This represents a waiting time penalty, used to balance the execution time of the forward and backward paths, preventing one side from waiting for an extended period. If the candidate rendezvous point set... If not empty, set the candidate rendezvous points. Comprehensive cost The smallest node is selected as the optimal meeting point.

[0072] If the optimal rendezvous point is not found, switch to the FullAid recovery scheme, enable the one-way path planning algorithm, calculate the safe travel path of the unmanned vehicle, and the algorithm ends; otherwise, obtain the safe travel path of the drone and the unmanned vehicle through backtracking of the forward search node and the backward search node, and the algorithm ends.

[0073] Specifically, if the above steps fail to find the optimal rendezvous point, the FullAid retrieval scheme is switched to, and steps SS401-SS406 are executed to obtain the safe travel path for the autonomous vehicle. Otherwise, based on the optimal rendezvous point, [the following steps are performed] at... and The process involves node backtracking to obtain the safe travel paths of drones and unmanned vehicles.

[0074] The heuristic cost functions designed in steps SD405 and SD408 respectively differ from those in traditional heuristic cost functions. and Based on this, a guiding term for the current node in the reverse search was added. and This encourages forward and backward searches to meet in the middle region, increasing the probability and speed of the two searches meeting.

[0075] Figures 2-4 Simulation results for three drone recovery schemes are presented. Figure 2 The image shows the simulation results of drone retrieval under the Ego retrieval scheme, where the blue line represents the drone's travel path. As can be seen, the drone moves along the generated path and can land directly on the unmanned vehicle to complete the retrieval task. During this process, the original task of the unmanned vehicle is not affected. Figure 3 The simulation results of drone recovery under the SemiAid recovery scheme are shown. The blue line represents the drone's path and the red line represents the unmanned vehicle's path. It can be seen that the drone and the unmanned vehicle move towards each other along their respective paths. The assistance of the unmanned vehicle effectively shortens the drone's path length, making it possible to safely recover drones with limited remaining power. Figure 4 The simulation results for drone retrieval under the FullAid retrieval scheme are shown. The blue line represents the drone's path, and the red line represents the vehicle's path. It can be seen that the vehicle leaves its original mission point to fully assist the drone in retrieval. Before the vehicle arrives, the drone can switch to power-saving mode or temporarily land in place. When the vehicle approaches, the drone lands on it to complete the retrieval task.

[0076] The main contents of the method proposed in this embodiment are as follows: (1) Construct a decision-making mechanism for drone recycling schemes. Based on the remaining power of the drone, determine the responsibility allocation between the drone and the unmanned vehicle in the recycling task. Through effective collaboration between the drone and the unmanned vehicle, ensure that the drone completes the recycling task before its power is exhausted. (2) A cross-dimensional bidirectional joint path planning algorithm is proposed. Based on the graph search algorithm, it maintains two search processes in different dimensions and directions at the same time, so as to realize the rapid generation of safe travel paths for UAVs and unmanned vehicles under the power constraints of UAVs. (3) An ellipse extension constraint is proposed for unidirectional and bidirectional path planning algorithms to improve the path planning speed. At the same time, the combined search process on the opposite side is guided to accelerate the convergence of the two search processes in bidirectional path planning. (4) A two-way path execution time balancing mechanism is proposed. By introducing a waiting time penalty term into the comprehensive cost of candidate meeting points, the path execution time of UAVs and unmanned vehicles is balanced, so as to avoid one party waiting for a long time while satisfying the remaining power constraints of UAVs.

[0077] Example 2 One embodiment of the present invention provides an adaptive planning system for UAV recovery paths based on air-ground cooperation, comprising: The location acquisition module is configured to: construct a 3D grid map of the mission environment, acquire the location of the drone and unmanned vehicle, and the maximum flight distance of the drone; The responsibility allocation module is configured to determine the responsibility allocation between the drone and the unmanned vehicle in the recovery task based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, so as to obtain the optimal drone recovery plan. The mode selection module is configured to: select the corresponding path planning mode based on the best drone recovery scheme, and determine the starting point, ending point and search space dimensions of the path planning based on the positions of the drone and the unmanned vehicle; The path planning module is configured to execute a path planning algorithm based on the selected path planning mode to generate the final recycling path. In the aforementioned responsibility allocation scheme, when the drone and the unmanned vehicle each assume part of the recovery responsibility, a cross-dimensional bidirectional joint path planning algorithm is used to generate safe travel paths for the drone and the unmanned vehicle under path distance constraints. Example 3 One embodiment of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned adaptive planning method for UAV recovery path based on air-ground cooperation.

[0078] Example 4 In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided for storing computer instructions. When the computer instructions are executed by a processor, the adaptive planning method for UAV recovery path based on air-ground cooperation is implemented.

[0079] Example 5 One embodiment of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the aforementioned adaptive planning method for UAV recovery path based on air-ground cooperation.

[0080] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] 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.

[0082] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. An adaptive planning method for UAV recovery paths based on air-ground cooperation, characterized in that, include: Construct a 3D grid map of the mission environment to obtain the positions of drones and unmanned vehicles, as well as the maximum flight distance of drones; Based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, the responsibility allocation of the drone and the unmanned vehicle in the recovery task is determined, and the optimal drone recovery plan is obtained. Based on the optimal drone recovery scheme, the corresponding path planning mode is selected, and the starting point, ending point, and search space dimensions of the path planning are determined based on the locations of the drone and the unmanned vehicle. Based on the selected path planning mode, the path planning algorithm is executed to generate the final recycling path; In the aforementioned responsibility allocation scheme, when the drone and the unmanned vehicle each assume part of the recovery responsibility, a cross-dimensional bidirectional joint path planning algorithm is used to generate safe travel paths for the drone and the unmanned vehicle under path distance constraints.

2. The adaptive planning method for UAV recovery path based on air-ground cooperation as described in claim 1, characterized in that, The maximum flight distance of the drone is calculated based on the drone's remaining battery power.

3. The adaptive planning method for UAV recovery path based on air-ground cooperation as described in claim 1, characterized in that, The process of determining the allocation of responsibilities between drones and unmanned vehicles in the recovery task to obtain the optimal drone recovery plan involves selecting the best plan from three drone recovery options. Specifically: Ego recovery solution: The drone assumes the responsibility of recovery independently. The drone navigates to the unmanned vehicle landing platform and lands autonomously. The unmanned vehicle's mission is not affected in any way during the entire recovery process. SemiAid recovery solution: Drones and unmanned vehicles each assume part of the recovery responsibility. The unmanned vehicle suspends its current task and moves towards the drone. Guided by the optimal rendezvous point, the drone lands on the unmanned vehicle's landing platform to complete the recovery task. The unmanned vehicle then returns to its original task area to continue its task. FullAid recovery solution: The unmanned vehicle assumes the main responsibility for recovery, while the drone enters power-saving mode or temporarily lands and waits for the unmanned vehicle to pick it up. The unmanned vehicle then suspends its current task and goes to the drone's location to assist it in landing.

4. The adaptive planning method for UAV recovery path based on air-ground cooperation as described in claim 3, characterized in that, The selection of the optimal solution from the three drone recovery schemes can be expressed by the following formula: in, Both are positive numbers, representing the user-defined security threshold and distance coefficient, respectively. Indicates the distance between the drone and the unmanned vehicle. This represents the maximum flight distance of the drone.

5. The adaptive planning method for UAV recovery path based on air-ground cooperation as described in claim 3, characterized in that, The selection of the appropriate path planning mode, and the determination of the starting point, ending point, and search space dimensions based on the positions of the UAV and the unmanned vehicle, involves choosing between unidirectional and bidirectional path planning modes, and determining the starting point, ending point, and search space dimensions according to the selected mode. Specifically: The Ego recovery scheme adopts a one-way path planning mode, with the starting point being the drone's location and the ending point being the unmanned vehicle's location, and the search space being three-dimensional; SemiAid's recovery solution uses a two-way path planning mode. The forward search starts at the location of the drone and searches in three dimensions, while the backward search starts at the location of the unmanned vehicle and searches in two dimensions. The endpoint is the optimal meeting point determined by multiple factors during the search process. The FullAid recovery scheme selects a one-way path planning mode, with the starting point being the location of the unmanned vehicle and the ending point being the projection position of the drone on the plane where the unmanned vehicle is located, and the search space is two-dimensional.

6. The adaptive planning method for UAV recovery path based on air-ground cooperation as described in claim 1, characterized in that, The path planning algorithm also includes a unidirectional path planning algorithm used when the UAV assumes the responsibility of recovery alone and the unmanned vehicle assumes the main responsibility of recovery.

7. An adaptive planning system for UAV recovery paths based on air-ground cooperation, characterized in that, include: The location acquisition module is configured to: construct a 3D grid map of the mission environment, acquire the location of the drone and unmanned vehicle, and the maximum flight distance of the drone; The responsibility allocation module is configured to determine the responsibility allocation between the drone and the unmanned vehicle in the recovery task based on the location of the drone and the unmanned vehicle and the maximum flight distance of the drone, so as to obtain the optimal drone recovery plan. The mode selection module is configured to: select the corresponding path planning mode based on the best drone recovery scheme, and determine the starting point, ending point and search space dimensions of the path planning based on the positions of the drone and the unmanned vehicle; The path planning module is configured to execute a path planning algorithm based on the selected path planning mode to generate the final recycling path. In the aforementioned responsibility allocation scheme, when the drone and the unmanned vehicle each assume part of the recovery responsibility, a cross-dimensional bidirectional joint path planning algorithm is used to generate safe travel paths for the drone and the unmanned vehicle under path distance constraints.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the adaptive planning method for UAV recovery path based on air-ground cooperation as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the adaptive planning method for UAV recovery path based on air-ground cooperation as described in any one of claims 1-6.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the adaptive planning method for UAV recovery path based on air-ground cooperation as described in any one of claims 1-6.

Images