Truck-unmanned aerial vehicle cooperative path optimization method for heterogeneity inspection task and program product

Abstract

The invention discloses a truck-unmanned aerial vehicle cooperative path optimization method and program product for a heterogeneity inspection task, and the method comprises the following steps: (1) setting a target function of a truck-unmanned aerial vehicle cooperative path optimization model as the minimum total cost, (2) adding routing constraints, heterogeneity constraints of different types of inspection tasks on equipment, unmanned aerial vehicle energy consumption constraints and time constraints to the truck-unmanned aerial vehicle cooperative path optimization model; and (3) solving the truck-unmanned aerial vehicle cooperative path optimization model to obtain an optimized decision variable so as to obtain an optimal path and an optimal unmanned aerial vehicle-truck configuration scheme for a heterogeneity inspection task. According to the invention, heterogeneity of inspection tasks is considered, and the planned path scheme is higher in inspection efficiency.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation and inspection technology, and in particular to a truck-UAV collaborative path optimization method and program product for heterogeneous inspection tasks. Background Art

[0002] With advances in drone technology, truck-drone collaborative systems are being applied to various inspection tasks, including urban traffic inspections, environmental data collection, and forest fire patrols. In these systems, trucks can perform ground-based tasks that require human intervention while also serving as mobile platforms, carrying, launching, and recovering drones and providing battery replacements. Drones can leverage their flight capabilities to reach target areas, collect high-resolution data, and perform inspections in hazardous environments. By combining the strengths of trucks and drones, these systems enable efficient inspections across a wider geographic area, reducing labor costs while improving safety and efficiency.

[0003] In practical applications, inspection tasks are heterogeneous due to differences in inspection content, environment, and other characteristics. These tasks require drones or trucks equipped with corresponding functional equipment. For example, detecting fire risks may require a drone equipped with infrared sensors, while facility inspections may require high-resolution cameras or lidar. Therefore, when planning a truck-drone collaborative inspection system, it is necessary to address task adaptability and the allocation of multiple drones to trucks, jointly optimizing fleet configuration and task routes to reduce overall costs and improve overall efficiency.

[0004] Despite the wide range of heterogeneous tasks in reality, most existing drone inspection research focuses on a unified task setup, failing to fully consider the diverse needs of different types of tasks and failing to meet the heterogeneous demands of these tasks. Furthermore, existing research often uses drones and trucks as a fixed pairing for route planning and task allocation, resulting in low inspection efficiency. Summary of the Invention

[0005] In response to the problems existing in the prior art, the purpose of the present invention is to provide a truck-UAV collaborative path optimization method and program product for heterogeneous inspection tasks with higher inspection efficiency.

[0006] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions: A truck-UAV collaborative path optimization method for heterogeneous inspection tasks includes the following steps: (1) The objective function of the truck-UAV collaborative path optimization model is set as: , Where, represents the total cost, They represent the truck startup cost and the unit time driving cost respectively. 、 They represent the startup cost and the unit time driving cost of the UAV respectively. 、 are all truck route variables, respectively in truck From warehouse to task node Driving, from the task node arrive The value is 1 when driving, otherwise it is 0. Configure variables for drone-truck, in drone The value is 1 if it is assigned to truck k, otherwise it is 0. 、 Represents truck and drone slave nodes respectively arrive driving time, is the drone route variable. Itinerary For slave task nodes i arrive The value is 1 when driving, otherwise it is 0. is the set of all task nodes except warehouse and terminal. Represents the set of all task nodes except the end point, Represents the set of all task nodes except the starting point, represents a collection of drones, represents the set of trucks, represents the set of drone itineraries, 、 、 、 is the decision variable; (2) Add routing constraints, heterogeneity constraints on equipment for different types of inspection tasks, and UAV energy consumption and time constraints to the truck-UAV collaborative path optimization model; (3) Solve the truck-UAV collaborative path optimization model to obtain the optimized decision variables, thereby obtaining the optimal route and optimal UAV-truck configuration solution for heterogeneous inspection tasks.

[0007] A computer program product comprises a computer program / instruction, wherein the computer program / instruction implements the above method when executed by a processor.

[0008] Compared with the prior art, the present invention has the following beneficial effects: 1. To address the problem of trucks and drones collaborating to perform heterogeneous inspection tasks, a mixed integer programming model was successfully constructed that accurately reflects the complexity of the tasks. This model comprehensively considers multiple constraints, including the heterogeneous equipment requirements for different types of inspection tasks, the battery life of drones, the truck and drone fleet configuration, and task duration. By treating the relationship between drones and trucks as an optimizable parameter rather than a fixed pairing, it effectively optimizes resource allocation and task routing in complex real-world environments, enabling the entire task to be completed with a smaller number of drones and trucks. This improves the flexibility and efficiency of inspection tasks and significantly reduces overall costs. 2. The present invention also proposes an adaptive large neighborhood search algorithm to solve model parameters. The algorithm can flexibly respond to task requirement scenarios of different scales and types, quickly provide high-quality solutions, and ensure efficient solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the process flow of the truck-UAV collaborative path optimization method for heterogeneous inspection tasks provided by the present invention; Figure 2 Schematic diagram of an architecture applicable to the method of the present invention; Figure 3 This is a schematic diagram of the process of solving the truck-UAV collaborative path optimization model of the present invention; Figure 4 This is a visualization diagram of the numerical experimental results of the present invention. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0011] Example 1

[0012] This embodiment provides a truck-UAV collaborative path optimization method for heterogeneous inspection tasks to solve the UAV-truck collaborative inspection problem, such as Figure 2 As shown in Figure 2, the drone-truck collaborative inspection problem is specifically defined as follows: a) Each truck must carry at least one drone, and there is a maximum number of drones a truck can carry; b) There are many different types of drones, capable of performing different types of missions; c) Both trucks and drones can inspect mission nodes, but they must meet the inspection equipment requirements of the node; d) Trucks not only carry out ground missions but can also transport drones and serve as mobile take-off and landing platforms for drones, providing launch, recovery, and battery recharge. e) If the battery level allows, each drone can perform multiple missions after a single departure; f) If the drone arrives at the rendezvous point before the truck, it can land there and wait for the truck to complete the recovery operation; g) All convoys depart from the warehouse and return to the warehouse within the specified time window.

[0013] The assumptions of the problems addressed by the present invention are as follows: a) Trucks and drones are not allowed to visit nodes repeatedly; b) Each node must and can only be visited once; c) Once the drone is returned to the truck, the battery will be replaced with a fully charged battery.

[0014] Regarding the above inspection questions and assumptions, Figure 1 As shown, the method of this embodiment includes the following steps: , Where, represents the total cost, They represent the truck startup cost and the unit time driving cost respectively. 、 They represent the startup cost and the unit time driving cost of the UAV respectively. 、 are truck route variables, respectively in truck From warehouse to task node Driving, from the task node arrive The value is 1 when driving, otherwise it is 0. Configure variables for drone-truck, in drone The value is 1 when it is assigned to truck k, otherwise it is 0. 、 Represents truck and drone slave nodes respectively arrive driving time, is the drone route variable. Itinerary For slave task nodes i arrive The value is 1 when driving, otherwise it is 0. is the set of all task nodes except warehouse and terminal. Represents the set of all task nodes except the end point, Represents the set of all task nodes except the starting point, represents a collection of drones, represents the set of trucks, represents the set of drone itineraries, 、 、 、 is the decision variable.

[0015] (2) Add routing constraints, heterogeneity constraints on equipment for different types of inspection tasks, and UAV energy consumption constraints and time constraints to the truck-UAV collaborative path optimization model.

[0016] Routing constraints include: , , , , , , , , , , , , , , , , Where, is the truck route variable, Configure variables for truck-tasks. By truck The value is 1 when accessed, otherwise it is 0. 、 Represents task nodes respectively ,j in the truck Position in the route, express The number of task nodes, Represents the set of all task nodes, Indicates the drone take-off point variable. In trip f from 1 when taking off, 0 otherwise. Indicates the drone take-off point variable. In the trip f+1 from 1 when taking off, 0 otherwise. Indicates the drone recovery point variable. In the trip f The value is 1 when it is recycled, otherwise it is 0. Indicates the drone recovery point variable. In the trip f The value is 1 when it is recycled, otherwise it is 0. Are all UAV trip variables, respectively as task nodes 、j in drones The value is 1 when it is accessed in the trip f, otherwise it is 0. represents the drone route variable, Indicates the maximum number of drones a truck can carry. Configure variables for truck-tasks. By truck The value is 1 when accessed, otherwise 0.

[0017] Constraints 1 through 5 above guarantee the feasibility of the truck's route by balancing traffic, eliminating subloops, and ensuring that each node is visited exactly once. Similarly, constraints 6 through 13 guarantee the feasibility of the drone's itinerary. Constraint 14 ensures that each task is executed only once; constraint 15 ensures that each edge traversed by the drone is associated with at least one assigned task; and constraint 16 enforces that the drone's itineraries are consecutive positive integers.

[0018] The heterogeneous constraints imposed by different types of inspection tasks on equipment include: , , Where, Represents the node-truck inspection variable, when the task node Can be transported by truck The value is 1 when the inspection is in progress, otherwise it is 0. Indicates node-UAV inspection variable, when the task node Can be operated by drone d The value is 1 during inspection and 0 otherwise. This constraint ensures that each task node is assigned to a truck or drone with corresponding execution capabilities.

[0019] The energy consumption constraints of the UAV include: , , , , , Where, 、 Respectively represent drones At the task node , the remaining power at time j, Indicates the drone battery capacity, Represents a task node Inspection time.

[0020] Of the constraints above, the first and second constraints ensure that each drone trip begins with a fully charged battery. The third and fourth constraints track the drone's battery level during the trip. The fifth constraint ensures that the drone has enough battery to complete the trip.

[0021] The time constraints include: , , , , , , , , , , , , , , , Where, 、 Represents trucks From warehouse, task node Time to leave, Respectively represent the start time and end time of the warehouse time window, is the truck route variable, Represents trucks Arrival at the mission node time, Represents a task node Inspection time, Respectively represent drones Arrival at the mission node time, Indicates the time to replace the drone battery. Truck Time to reach the destination, Indicates drone From the task node Time to leave, Respectively represent drones From the task node Time to leave.

[0022] Of the constraints above, the first and second constraints specify the departure times of all fleets. Constraints three through four track the arrival and departure times of trucks and drones at each visited node. Constraints 12 and 13 determine the start time of each new drone trip. Constraint 14 ensures that drones are recovered before taking off again. Constraint 15 forces all trucks to return to the depot within a specified time window.

[0023] (3) Solve the truck-UAV collaborative path optimization model to obtain the optimized decision variables, thereby obtaining the optimal route and optimal UAV-truck configuration solution for heterogeneous inspection tasks.

[0024] like Figure 3 As shown, this step uses the adaptive large neighborhood algorithm to solve the model, specifically including: (3-1) Based on the preset initial truck-drone configuration plan, the initial mission execution route of the truck and drone is constructed using the nearest neighbor insertion method. After the route is constructed, all idle drones are removed and returned to the warehouse.

[0025] Phase 1: Based on the nearest neighbor insertion strategy and considering the time window constraint, the truck’s route for executing the task is constructed; Phase 2: For each uninserted drone mission point, the nearest truck node is found. If a truck at that node has a drone available, that truck node becomes the launch node, and the drone node is inserted immediately after it. The next truck node that meets the battery capacity constraint is selected as the return node. If the nearest truck node cannot be inserted, the next closest truck node is considered, and so on.

[0026] After all nodes have been visited, drone operations may affect the truck's waiting time at each pickup node, thus affecting the truck's return time to the warehouse. Consequently, some initial solutions may violate the warehouse's time window constraints. In these cases, infeasible initial solutions are allowed and penalized by including the time window violation as a penalty term in the objective function.

[0027] Set the number of loops, Iteration=0.

[0028] (3-2) Use the roulette wheel strategy to select the route and apply the destruction operator and repair operator to generate a new route, and introduce or retract the drone.

[0029] The destruction and repair operators perturb the current solution 9 (current route) to generate a new solution (a new route). This invention proposes seven destruction operators and nine repair operators. The destruction operator is used to remove a portion of nodes from the current route, thereby creating an incomplete route. This allows for the subsequent repair process to explore new neighborhoods and potentially find a better solution. The repair operator fills in the gaps created by the destruction operator, thereby constructing a new, complete route. The detailed application of these operators is as follows: The 7 types of destruction operators are as follows: a) Random removal: Randomly remove nodes from the current solution, where is a predefined integer, usually greater than 1.

[0030] b) Cluster removal: randomly select a node as the focal node, and then remove the node and its nearest nodes.

[0031] c) Recent Client Removal: Randomly remove a node from a path and remove the nearest task node in the path.

[0032] d) Path Removal: Randomly select a truck path and remove all truck and drone nodes associated with it.

[0033] e) Worst cost removal: remove the node that can save the maximum cost after deleting the node in the current solution.

[0034] f) Randomly remove-drone: A drone is randomly selected, all nodes it visits are removed, and the drone is unloaded from its own truck.

[0035] g) Worst Cost Removal-UAV: Select a drone with the highest travel cost, remove all nodes it visits, and unload the drone from its truck.

[0036] The 9 repair operators are as follows: a) Random Insertion - Truck: Randomly select an insertion location that satisfies the warehouse time window constraint and insert the truck node. If no suitable insertion location is found, a new truck route is created.

[0037] b) Closest Insert - Truck: Attempt to insert an unvisited truck node into the existing route, after the closest truck node. If this insertion does not meet the time window constraint, the next closest node is considered, and so on. If no suitable location exists, a new truck route is created.

[0038] c) Greedy Insertion - Truck: Compare the cost increase when inserting the truck node into all feasible locations (including creating new routes) and choose the insertion location with the smallest cost increase.

[0039] d) New Truck Route Construction: Connect all unvisited truck nodes into a new route in the same way as in step 1 of the initialization phase. This operation is only performed when there are idle trucks.

[0040] e) Random Insertion-UAV: Randomly select an unvisited UAV node with an insertion strategy, and choose from the following two ways: (1) create a new UAV itinerary; (2) insert it into a feasible position of an existing UAV itinerary.

[0041] f) Nearest Insert-UAV: Similar to step 2 of the initialization phase, a new UAV trip is created for the unvisited UAV node, taking off from the nearest truck node, or it is inserted into the nearest existing UAV trip.

[0042] g) Greedy Insertion-UAV: Select the insertion location that minimizes the cost increase, which can be inserting the node into the existing route or creating a new UAV itinerary.

[0043] h) Activate New Drones - Randomly: For each type of unvisited drone node, a new drone is activated and assigned to the truck closest to that type of unvisited node. The new drone is then used to serve the unvisited drone node by randomly selecting a feasible route (either a new trip or inserting it into an existing trip). Unreachable nodes are handled by existing drones using the same strategy as for random insertion of drones.

[0044] i) Activate New Drone - Nearest: A new drone is activated for each type of unvisited drone node and assigned to the truck closest to that type of unvisited node. The new drone is then used to service the unvisited drone node by creating a new trip departing from the nearest truck node or inserting the node into the nearest existing drone trip. Unreachable nodes are handled by existing drones using the same strategy as for the nearest inserted drone.

[0045] These operations, through alternating destruction and repair, can effectively optimize the scheduling and path planning of trucks and drones, and improve the performance and efficiency of the overall system.

[0046] In this invention, the destruction operator and repair operator are usually adaptively weighted according to their performance and are selected using a roulette wheel method to ensure that the algorithm can continuously and effectively explore the solution space and find high-quality solutions. The specific method of updating the operator weight is as follows: , in, Represents the weights before and after the operator x is updated, and the parameters Indicates the score update weight coefficient, with a value range of 0-1. represents the number of times the operator x appears in the iteration process, It represents the score of each operator in the iterative process. Specifically, when a new optimal solution is obtained, the score is 10; when a solution that is not optimal but better than the current solution is obtained, the score is 5; when a solution that is worse than the current solution but is selected based on the simulated annealing mechanism is obtained, the score is 1.

[0047] Each destruction operator and repair operation has a selection weight , in each iteration, the probability of the operator being selected is determined according to the following formula : , X represents the number of operators.

[0048] (3-3) Taking the total cost as the target value, the simulated annealing acceptance criterion is used to determine whether the newly generated route is accepted and update the local optimal solution.

[0049] Compare the cost of the new solution (route) S' with the total cost of the optimal solution. If the total cost of the new solution S' is smaller, then update the optimal solution and the current solution to the new solution S'; if the total cost of the new solution S' is greater than the cost of the optimal solution but less than the cost of the current solution S, then update the current solution to the new solution S'; if the cost of the new solution S' is greater than the cost of the current solution S, then determine whether to retain the new solution S' according to the following formula.

[0050] , Where T represents the simulation temperature; (3-4) Determine whether the iteration termination condition is met. If so, output the local optimal solution as the optimal route and truck-drone configuration plan. Otherwise, Iteration = Iteration + 1, and return to step (3-2).

[0051] (4) According to the spatial distribution characteristics of different tasks and the impact of drone power consumption on the total cost, the optimal route and optimal drone-truck configuration plan for different mission scenarios are adjusted.

[0052] The specific steps are as follows: (4-1) Task space distribution modeling is performed to construct two typical task space layouts, including (1) linear distribution: task points are distributed in strips, which is suitable for scenarios such as river bank inspection and transmission line inspection; (2) cluster distribution: task points are concentrated in local areas, which is suitable for scenarios such as wind turbine monitoring.

[0053] (4-2) Adjust parameters for sensitivity analysis, set multiple sets of UAV battery limit parameters, simulate system performance under different endurance conditions, and analyze their impact on path selection and total system cost; set different ratios of truck-performed tasks and UAV-performed tasks, and compare the system cost and fleet configuration under different task distributions.

[0054] (4-3) Make decision recommendations for specific scenarios. For example, for tasks with clustered distribution, it is recommended to deploy more drones on each truck to reduce the length of the truck path. For tasks with linear distribution, it is recommended to use drones with longer endurance and appropriately increase the number of truck points to improve coverage.

[0055] The following numerical experiments are conducted on the examples of the present invention to verify the feasibility of the model and algorithm, as follows: Due to the complexity of this problem, there are currently no readily available standard examples for direct use. To verify the effectiveness and feasibility of the proposed method, we created test cases based on example generation methods from existing literature. These test cases simulated real-world mission scenarios, allowing for comprehensive testing and verification of the proposed method for combined fleet and route optimization.

[0056] The present invention uses 18 examples for experimental verification, and the number of nodes in the scenario gradually increases from 8 to 32. When solving each example, the results of the algorithm proposed in this invention (ALNS) are compared with the results of the commercial solver Gurobi, as shown in Table 1. The visualization diagram of the example solution results is shown in Figure 4 . For each instance, the ALNS algorithm is executed 10 times with different random seeds. As shown in the third and sixth columns of Table 1, the computation time of Gurobi increases rapidly with the size of the problem (with a maximum limit of 48 hours), while the ALNS algorithm of the present invention is always able to solve the problem in a short time. In addition, the vast majority of the target value gaps reported in the seventh column are zero, indicating that the ALNS algorithm successfully found the global optimal solution in many instances. In addition, the gap between the average target value and the best target value obtained by ALNS is always kept below 3%, demonstrating the robustness and effectiveness of the algorithm in generating high-quality, near-optimal solutions.

[0057] Table 1 Solution results of the example Instance Encoding Gurobi optimal solution Gurobi solution time (s) ALNS optimal solution ALNS average solution ALNS solution time (s) The gap between the ALNS optimal solution and the Gurobi optimal solution (%) The difference between the ALNS average solution and the Gurobi optimal solution (%) 8-2-1-2A 156 0.07 156 156 0.03 0.00 0.00 8-2-1-2B 154 0.06 154 154 0.04 0.00 0.00 10-2-1-2A 156 0.26 156 156 0.17 0.00 0.00 10-2-1-2B 174 0.27 174 174 0.19 0.00 0.00 12-2-2-4A 178 32.86 178 178.8 1.54 0.00 0.04 12-2-2-4B 192 17.9 192 192.4 1.1 0.00 0.04 14-2-2-4A 204 12.46 204 204.4 2.28 0.00 0.02 14-2-2-4B 232 20.68 232 233.6 3.74 0.00 0.69 16-2-2-4A 210 178.04 210 210.8 1.81 0.00 0.38 16-2-2-4B 274 207.06 274 274.6 2.74 0.00 0.22 18-2-2-4A 254 2431.97 254 254.6 9.05 0.00 0.24 18-2-2-4B 292 430.82 296 297.2 10.76 1.37 1.78 20-2-2-4A 256 874.25 256 257.4 17.45 0.00 0.55 20-2-2-4B 278 1075.33 278 279.0 24.91 0.00 0.36 24-2-2-6A 382 3118.12 382 386.4 28.73 0.00 1.15 24-2-2-6B 258 7912.33 258 258.6 30.95 0.00 0.23 32-2-2-8A 598 / 598 610.9 61.31 0.00 2.16 32-2-2-8B 554 / 554 569.5 67.25 0.00 2.80 From the above, it can be seen that in order to solve the problem of trucks and drones collaborating to perform heterogeneous inspection tasks, the present invention has successfully constructed a mixed integer programming model that accurately reflects the complexity of the task. This model comprehensively considers the heterogeneous requirements of equipment for different types of inspection tasks, the battery life of drones, the fleet combination formed by trucks and drones, and the time window of the task, among other constraints. It can effectively optimize resource allocation and task routes in complex actual environments and has practical application value. In addition, the present invention proposes an adaptive large neighborhood search algorithm to form a solution framework for truck-drone collaborative path planning. This framework can flexibly respond to mission requirement scenarios of different scales and types, quickly provide high-quality solutions, ensure the flexible deployment of heterogeneous drones, and use a smaller number of drones and trucks to complete all tasks, greatly improving the operational flexibility of the system and reducing system costs, thereby providing an efficient solution for the security inspection industry.

[0058] Example 2 Embodiments of the present invention also provide a computer program product, such as an app on a mobile phone or tablet, an installation program on a computer, etc., which includes a computer program / instructions that, when executed by a processor, implement the method described in Example 1. The code for the computer-executable program for performing the operations of the present invention can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0059] It should be understood that the above embodiments and descriptions only describe the principles, main features and advantages of the present invention. Without departing from the spirit and scope of the present invention, the present invention may be subject to various changes and improvements, and these changes and improvements all fall within the scope of protection of the present invention.

Claims

1. A truck-UAV collaborative path optimization method for heterogeneous inspection tasks, characterized by: The steps include: (1) The objective function of the truck-UAV collaborative path optimization model is set as: ， Where, represents the total cost, They represent the truck startup cost and the unit time driving cost respectively. 、 They represent the startup cost and the unit time driving cost of the UAV respectively. 、 are truck route variables, respectively in truck From warehouse to task node Driving, from the task node arrive The value is 1 when driving, otherwise it is 0. Configure variables for drone-truck, in drone The value is 1 when it is assigned to truck k, otherwise it is 0. 、 Represents truck and drone slave nodes respectively arrive driving time, is the drone route variable. Itinerary For slave task nodes i arrive The value is 1 when driving, otherwise it is 0. is the set of all task nodes except warehouse and terminal. Represents the set of all task nodes except the end point, Represents the set of all task nodes except the starting point, represents a collection of drones, represents the set of trucks, represents the set of drone itineraries, 、 、 、 is the decision variable; (2) Add routing constraints, heterogeneity constraints on equipment for different types of inspection tasks, and UAV energy consumption and time constraints to the truck-UAV collaborative path optimization model; (3) Solve the truck-UAV collaborative path optimization model to obtain the optimized decision variables, thereby obtaining the optimal route and optimal UAV-truck configuration solution for heterogeneous inspection tasks.

2. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: The routing constraints include: ， ， ， ， ， Where, is the truck route variable, Configure variables for truck-tasks. By truck The value is 1 when accessed, otherwise it is 0. 、 Represents task nodes respectively ,j in the truck Position in the route, express The number of task nodes, Represents the set of all task nodes, Indicates the drone take-off point variable. In trip f from 1 when taking off, 0 otherwise. Indicates the drone recovery point variable. In the trip f The value is 1 when it is recycled, otherwise it is 0.

3. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: The routing constraints also include: , , , , , , , , , , , Where, Are all UAV trip variables, respectively as task nodes 、j in drones The value is 1 when it is accessed in the trip f, otherwise it is 0. 、 All represent the variables of the drone’s take-off point. 、 Represents the drone recovery point variable, represents the drone route variable, Configure variables for truck-task, Represents the set of all task nodes, Indicates the maximum number of drones a truck can carry.

4. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: The heterogeneous constraints imposed by different types of inspection tasks on equipment include: , , Where, Configure variables for truck-task, Represents the node-truck inspection variable, when the task node Can be transported by truck The value is 1 when the inspection is in progress, otherwise it is 0. Indicates node-UAV inspection variable, when the task node Can be operated by drone d The value is 1 when the inspection is in progress, otherwise it is 0. is the drone’s itinerary variable.

5. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: The energy consumption constraints of the UAV include: , , , , , Where, 、 Respectively represent drones At the task node , the remaining power at time j, Indicates the drone battery capacity, Represents the drone take-off point variable, Represents the drone recovery point variable, Represents a task node Inspection time, is the drone’s itinerary variable.

6. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: The time constraints include: , , , , , , , , , , , Where, 、 Represents trucks From warehouse, task node Time to leave, Respectively represent the start time and end time of the warehouse time window, is the truck route variable, Represents trucks Arrival at the mission node Time, Represents a task node Inspection time, Respectively represent drones Arrival at the mission node time, Indicates the time to replace the drone battery. Represents the drone take-off point variable, Configure variables for truck-task, Truck Time to reach the destination, Indicates drone From the task node Time to leave, is the drone’s itinerary variable.

7. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: The time constraints also include: , , , , Where, Indicates the end time of the warehouse time window. Truck Arrival at the mission node Time, Represents a task node Inspection time, Indicates drone Arrival at the mission node time, Indicates the time to replace the drone battery. 、 All represent the variables of the drone’s take-off point. Configure variables for truck-task, Indicates drone Time to reach the destination, Respectively represent drones From the task node Time to leave, Represents the drone recovery point variable.

8. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: Step (3) specifically includes: (3-1) Based on the preset initial truck-drone configuration plan, the initial mission execution route of the truck and drone is constructed using the nearest neighbor insertion method. After the route is constructed, all idle drones are removed and returned to the warehouse; (3-2) Using a roulette wheel strategy to select and apply destruction operators and repair operators to generate a new route, and introduce or retract drones; the destruction operator is used to remove some nodes from the current route, thereby creating an incomplete route, and the repair operator is used to fill the gaps created by the destruction operator, thereby constructing a new complete route; (3-3) Taking the total cost as the target value, use the simulated annealing acceptance criterion to determine whether the newly generated route is accepted and update the local optimal solution; (3-4) Determine whether the iteration termination condition is met. If so, output the local optimal solution as the optimal route and truck-UAV configuration plan. Otherwise, return to step (3-2).

9. The truck-UAV collaborative path optimization method for heterogeneous inspection tasks according to claim 1 is characterized in that: After step (3), the following steps are also included: (4) According to the spatial distribution characteristics of different tasks and the impact of drone power consumption on the total cost, the optimal route and optimal drone-truck configuration plan for different mission scenarios are adjusted.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images