Vehicle-machine cooperative path planning method considering patrol timeliness

Abstract

The application provides a vehicle-machine cooperative path planning method considering patrol timeliness, and relates to the technical fields of electric power inspection and intelligent path optimization. The application takes maximizing total patrol benefit as a target, preferentially accesses high-value task points within limited time, and significantly improves overall patrol benefit. Through integrated modeling of vehicle path, stopping point selection, unmanned aerial vehicle (UAV) take-off and landing, and flight path, the vehicle-machine cooperative scheduling capability is strengthened. The UAV takes off and lands from the vehicle stopping point, and continuously accesses multiple task points in a single flight, improving the flexibility of task execution. Meanwhile, the real constraints such as UAV endurance, total time upper limit, vehicle-machine time synchronization, and battery replacement cooperation are comprehensively considered, so that the planning scheme is more suitable for the actual patrol scene, and can effectively solve the technical problems of vehicle-machine cooperative scheduling within limited time and maximizing the access efficiency of differentiated value task points.

Description

Technical Field

[0001] This invention relates to the field of power line inspection and intelligent path optimization technology, specifically to a vehicle-machine collaborative path planning method that takes into account inspection timeliness. Background Technology

[0002] In the operation and maintenance of power transmission lines, rapid inspection and fault diagnosis are crucial for ensuring power grid safety. Compared with traditional manual inspections, drones, with their advantages of mobility, flexibility, and wide coverage, have become an important means of emergency inspections. To further improve operational efficiency, the vehicle-machine collaborative mode (drones mounted on vehicles) has emerged. Vehicles extend the drone's operating radius and provide transportation and energy refueling support, thereby improving overall inspection capabilities.

[0003] In related technologies, research on vehicle-drone collaborative path planning is relatively mature. Early research mainly focused on scenarios such as logistics and delivery, optimizing task allocation and scheduling (with the goal of minimizing time or cost). Subsequent research expanded to scenarios such as disaster relief and regional monitoring, and introduced factors such as multi-drone collaboration and complex environmental constraints. In recent years, some studies have begun to focus on optimization problems under limited time, introducing task reward weights to prioritize access to high-value objectives.

[0004] However, the relevant technologies have at least the following shortcomings in emergency inspections of power transmission lines: on the one hand, the lack of effective coordination between drone mission scheduling and vehicle movement leads to wasted time due to battery swapping and resupply and path waiting; on the other hand, the algorithms do not adequately consider the differences in mission value, making it difficult to prioritize high-value targets under strict time constraints, ultimately affecting the overall inspection efficiency. Summary of the Invention

[0005] (a) Technical problems to be solved To address the shortcomings of related technologies, this invention provides a vehicle-machine collaborative path planning method that considers patrol timeliness, solving the technical problem of how to collaboratively optimize vehicle and drone scheduling within a limited patrol time to maximize the access efficiency of task points with differentiated value.

[0006] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: A vehicle-machine cooperative path planning method considering patrol timeliness includes: Obtain the coordinates of patrol task points and their corresponding benefits, vehicle parking point coordinates, number of drones, maximum single-trip flight time of drones, and total patrol time limit; among them, the benefit is the value measure of task point information, and its value is positively correlated with the patrol priority of the task point, and is determined by at least one of the following: task point importance, urgency, and risk level. Based on the coordinates of the patrol task points and vehicle parking points, the flight time and path required for the UAV mission are calculated. A mixed-integer linear programming model is established with the objective of maximizing the total patrol revenue, where the total patrol revenue is the sum of the revenues corresponding to each task point visited. The model constraints include: Vehicle path constraints: The vehicle departs from and returns from the base, and the path satisfies flow balance and no sub-loops. The access to the docking point must match the take-off and landing requirements of the drone. Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution cannot exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all the actual docking points visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. Time synchronization constraints: The vehicle arrives at the docking point earlier than the departure time; the drone lands later than the takeoff time and matches the vehicle's dwell time in the same sortie; the vehicle leaves the docking point later than the drone recovery and battery swapping time; and the completion time of each task of the vehicle and the drone does not exceed the upper limit of the total patrol time. The solution model generates vehicle paths, UAV flight paths, and take-off and landing strategies.

[0007] Preferably, the model is solved using the Benders decomposition method, including iteratively performing the following steps until convergence: Main problem: Construct a decision using vehicle route variables, drone take-off and landing variables, payload variables, and route order variables to determine the vehicle stop sequence and drone take-off and landing strategy, and set auxiliary variables to represent the upper bound of revenue; Sub-problem: Based on the solution to the main problem, optimize the flight path of the UAV and the time arrangement of the vehicle and the UAV, verify the feasibility of the path and calculate the actual patrol benefits.

[0008] Preferably, the main problem and the sub-problems are interactively iterated through a cutting plane: When the subproblem is infeasible, a feasibility cut is generated and added to the main problem to eliminate infeasible solutions; When the estimated return of the main problem exceeds the actual inspection return of the sub-problems, an optimal cut is generated and added to the main problem to correct the return estimate.

[0009] Preferably, a variable preprocessing step is performed before solving the main problem: Pre-determine infeasible take-off and landing point combinations for the drone within its maximum single flight time, and eliminate the corresponding drone take-off and landing variables.

[0010] Preferably, the drone supports both cyclic sortie mode and forward sortie mode; The cyclic sortie mode refers to the drone taking off and landing from the same docking point; The forward sortie mode refers to the UAV taking off from the current docking point and landing at a subsequent docking point in the vehicle's forward direction; and when the forward sortie mode is adopted, the vehicle-machine cooperative constraint includes that the UAV landing point is located after the takeoff point in the vehicle access sequence.

[0011] Preferably, one or more of the following valid inequalities are added to the main problem: (i) Vehicles are only permitted to access docking points where there is a demand for drone take-off and landing; (ii) The sum of the vehicle's total driving time, the total battery swapping time of the UAV, and the waiting time in the cycle mode shall not exceed the upper limit of the total patrol time; (iii) The sum of the time a single drone spends moving with the vehicle and its independent flight time shall not exceed the upper limit of the total patrol time; (iv) Eliminate constraints on the symmetry of homogeneous UAV construction.

[0012] Preferably, before solving the model, a greedy strategy is used to generate an initial feasible solution, including: A comprehensive score is calculated based on the task point revenue and stop point accessibility around the stop point, and high-scoring stop points are gradually added to the vehicle path using the most time-saving insertion method. Candidate tasks are generated from high to low based on the task point benefits. When the endurance constraint, time synchronization constraint, and total inspection time constraint are satisfied, the corresponding candidate task is added to the initial solution to form an initial feasible solution.

[0013] A vehicle-machine cooperative path planning system that considers patrol timeliness includes: The basic data acquisition module is used to acquire the coordinates of patrol task points and their corresponding benefits, the coordinates of vehicle parking points, the number of drones, the maximum single flight time of drones, and the upper limit of total patrol time. Among them, the benefit is the value measure of the task point information, and its value is positively correlated with the patrol priority of the task point, and is determined by at least one of the following: the importance of the task point, the urgency, and the risk level. The model building module is used to calculate the flight time and path required for the UAV mission based on the coordinates of the patrol task points and the vehicle docking points. It establishes a mixed-integer linear programming model with the objective of maximizing the total patrol revenue, which is the sum of the revenues corresponding to each task point visited. Model constraints include: Vehicle path constraints: The vehicle departs from and returns from the base, and the path satisfies flow balance and no sub-loops. The access to the docking point must match the take-off and landing requirements of the drone. Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution cannot exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all the actual docking points visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. Time synchronization constraints: The vehicle arrives at the docking point earlier than the departure time; the drone lands later than the takeoff time and matches the vehicle's dwell time in the same sortie; the vehicle leaves the docking point later than the drone recovery and battery swapping time; and the completion time of each task of the vehicle and the drone does not exceed the upper limit of the total patrol time. The strategy solving module solves the model to generate vehicle paths, UAV flight paths, and take-off and landing strategies.

[0014] A storage medium storing a computer program, wherein the computer program causes a computer to execute the vehicle-machine cooperative path planning method as described above, taking into account inspection timeliness.

[0015] An electronic device, the electronic device comprising: Processor and memory; The memory stores program instructions; The processor is used to run the program instructions to execute the vehicle-machine cooperative path planning method that takes into account the inspection timeliness as described above.

[0016] (III) Beneficial Effects This invention provides a vehicle-machine cooperative path planning method that considers inspection timeliness. Compared with related technologies, it has the following advantages: This invention aims to maximize overall patrol benefits by prioritizing access to high-value task points within a limited time, significantly improving overall patrol efficiency. It enhances vehicle-machine collaborative scheduling capabilities through integrated modeling of vehicle routes, stop point selection, and UAV takeoff and landing / flight paths. It clarifies that UAVs can take off and land from vehicle stops and can access multiple task points consecutively in a single flight, improving mission execution flexibility. Furthermore, it considers real-world constraints such as UAV endurance, total time limits, vehicle-machine time synchronization, and battery swapping coordination, making the planning scheme more aligned with actual patrol scenarios. This effectively addresses the technical challenges of vehicle-machine collaborative scheduling within a limited time and maximizing the efficiency of accessing differentiated value task points. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A block diagram illustrating a vehicle-machine cooperative path planning method considering patrol timeliness, provided in an embodiment of the present invention; Figure 2 A flowchart of a vehicle-machine cooperative path planning method considering patrol timeliness is provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0019] Component labeling explanation: 100 - electronic device, 101 - memory, 102 - processor, 103 - display. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] This invention addresses the application needs of vehicles carrying drones to perform power transmission facility inspection tasks. It integrates and optimizes vehicle routes, drone task allocation, flight paths, and time arrangements by taking into account factors such as inspection time constraints, differences in task point benefits, vehicle parking location selection, and drone flight and recovery coordination. It is applicable to business scenarios such as emergency inspections, fault diagnosis, and emergency repair decision support in power systems.

[0022] This invention aims to address the shortcomings of existing emergency transmission line inspection technologies, such as insufficient consideration of inspection time constraints, inadequate characterization of task value differences, and lack of flexibility in drone flight modes, in collaborative path planning between vehicles and vehicle-mounted drones. It proposes a vehicle-drone collaborative path planning method that considers inspection timeliness. By integrating and optimizing vehicle routes, drone task allocation, flight paths, take-off and landing strategies, and timing, this method enables vehicles carrying multiple drones to perform emergency inspection tasks more efficiently within a given inspection timeframe. This improves the coverage of high-value inspection targets and overall inspection benefits, thereby enhancing the timeliness, coordination, and practicality of emergency transmission line inspection operations.

[0023] In particular, the term "inspection timeliness" introduced in the embodiments of the present invention is explained separately: The patrol timeliness is used to characterize the urgency of the patrol mission in terms of time. This includes both the overall patrol mission completion time being limited to the specified or expected total time range (total patrol time ceiling), and the endurance limitations of a single UAV flight (maximum endurance of a single UAV flight), as well as the time coordination requirements between the vehicle and the UAV during takeoff, landing, recovery, and battery swapping. To better understand the above technical solutions, a detailed explanation will be provided below with reference to the accompanying drawings and specific implementation methods.

[0024] Example 1: like Figure 1 As shown, this embodiment of the invention provides a vehicle-machine cooperative path planning method that considers inspection timeliness, including: S1. Obtain the coordinates of patrol task points and corresponding benefits, vehicle parking point coordinates, number of drones, maximum single-trip flight time of drones, and total patrol time limit; wherein, the benefit is a value measure of task point information, and its value is positively correlated with the patrol priority of the task point, and is determined by at least one of the following: task point importance, urgency, and risk level. S2. Based on the coordinates of the patrol task points and the vehicle parking points, calculate the flight time and path required for the UAV mission. Establish a mixed-integer linear programming model with the objective of maximizing the total patrol revenue. The total patrol revenue is the sum of the revenues corresponding to each task point visited. The model constraints include: Vehicle path constraints: The vehicle departs from and returns from the base, and the path satisfies flow balance and no sub-loops. The access to the docking point must match the take-off and landing requirements of the drone. Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution cannot exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all the actual docking points visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. In addition, time synchronization constraints: the vehicle arrives at the docking point earlier than the departure time; in the same sortie, the drone lands later than the takeoff time and matches the vehicle's dwell time; the vehicle leaves the docking point later than the drone recovery and battery swapping time; and the completion time of each task of the vehicle and the machine does not exceed the upper limit of the total patrol time. S3. Solve the model to generate vehicle paths, UAV flight paths, and take-off and landing strategies.

[0025] The embodiments of this invention aim to maximize the total benefits of patrols, prioritizing the coverage of high-value task points within a limited time to improve overall efficiency; by integrating vehicle routes, UAV take-off and landing, and flight paths into a unified plan, vehicle-machine collaboration is enhanced; considering factors such as range, time synchronization, and battery swapping constraints, the solution is more in line with practical applications and efficiently solves the problems of vehicle-machine collaborative scheduling and task access efficiency.

[0026] First, it should be clarified that the benefit of a task point is a measure of the value of the information at that task point. Its value is positively correlated with the patrol priority of the task point; that is, the higher the benefit value, the higher the patrol priority of the corresponding task point, and the more frequently it will be patrolled. Furthermore, the value is determined by at least one of the following: the importance, urgency, and risk level of the task point. Essentially, this benefit is the value of the information obtained after completing the patrol task; that is, by conducting patrol operations at the task point, the state information of the target object is obtained, thereby providing guidance for subsequent decision-making. It should be understood that the determination of the benefit can be flexibly made based on the actual needs of the patrol scenario, taking into account factors such as the importance, urgency, and risk level of the task point, and does not need to be limited to a fixed calculation method.

[0027] For example, in emergency inspections of power facilities, information obtained through timely inspections of facilities and equipment with higher risk of disaster and higher probability of failure is more valuable for fault location and repair decisions, resulting in higher returns. Path planning models can prioritize inspections of such task points to maximize overall inspection information gains and improve the targeting and effectiveness of inspection operations. More specifically, in emergency inspection scenarios of transmission lines, within a given total inspection time, the vehicle route, vehicle stop selection, UAV take-off and landing recovery strategy, UAV task allocation, UAV flight path, and vehicle-UAV time scheduling are collaboratively optimized to maximize the total benefits of the inspection task while satisfying UAV endurance constraints and vehicle-UAV synchronization constraints. The overall technical solution is summarized below: This invention provides a model for a scenario where a vehicle carries multiple drones to perform emergency inspections of power transmission lines. The system consists of a work base, several vehicle docking points, several inspection task points, one vehicle, and multiple drones. Each inspection task point has a different weight, representing its importance or potential fault risk level during the emergency inspection. The vehicle departs from the base, visits some vehicle docking points, and then returns to the base. The drones are released from the vehicle at the base or a docking point, inspect the task points, return to the vehicle's location or a subsequent docking point ahead of the vehicle, and are recovered and have their batteries swapped after rendezvousing with the vehicle.

[0028] Unlike the path planning model in related technologies that requires access to all task points, this invention allows the system to selectively access task points within a limited time, thereby prioritizing coverage of high-value inspection targets and achieving revenue-oriented emergency inspection planning.

[0029] Specifically, embodiments of the present invention propose the following vehicle-machine collaborative operation mechanism: (1) Vehicle parking spot setting mechanism Locations where vehicles can dock and support drone takeoff and recovery are independently modeled as vehicle docking points. Vehicles do not directly serve patrol mission points, but instead provide takeoff, landing, waiting, and battery swapping support for drones by accessing some docking points. By introducing path planning at the docking point layer, a hierarchical collaborative relationship is formed between vehicle path decision-making and drone mission execution.

[0030] (2) Dual-mode flight mechanism of UAV The drone in this embodiment of the invention supports the following two types of flight modes.

[0031] ① Cyclic sortie mode refers to the drone taking off and landing from the same docking point.

[0032] Specifically: The drone takes off from a certain docking point, visits one or more mission points, and then returns to the original docking point to land. The vehicle waits at the docking point for the drone to complete its mission and be retrieved.

[0033] ② Forward sortie mode refers to the UAV taking off from the current docking point and landing at a subsequent docking point in the direction the vehicle is traveling.

[0034] Specifically: The drone takes off from a certain docking point, visits one or more mission points, and then lands at a subsequent docking point in the direction the vehicle is traveling. The vehicle continues along the planned path and meets up with the drone at that subsequent docking point.

[0035] By introducing the two types of flight modes mentioned above at the same time, the embodiments of the present invention break through the limitation of the relatively simple single flight mode of UAVs in related technologies, enabling UAVs to flexibly arrange take-off and landing relationships according to the vehicle's forward movement.

[0036] (3) Continuous access mechanism for unmanned aerial vehicles This allows drones to visit multiple patrol points consecutively in a single flight, instead of just a single point. This mechanism can increase the effective coverage of a single launch, reduce the coordination losses caused by frequent takeoffs and landings, and improve patrol benefits within a limited timeframe, provided endurance allows.

[0037] (4) Battery swapping coordination mechanism The battery replacement process after the drone meets the vehicle is included in the time consumption calculation. After each mission, the drone undergoes a battery swap and restores its flight range upon meeting the vehicle, thus making the model more closely resemble the actual emergency patrol operation process.

[0038] See Figure 2 , Figure 2The overall process of a vehicle-machine cooperative path planning method that takes into account the timeliness of patrol is disclosed: First, basic data and parameters are input, then a vehicle-machine cooperative path optimization model is established, and the Benders decomposition method is used for iterative solution, and finally the path planning results of vehicles and drones are output.

[0039] Next, we will combine Figure 2 The plan provides a detailed explanation of each step.

[0040] It should be noted in advance that step a corresponds to step S1 above, step b corresponds to step S2 above, and steps c to r correspond to step S3 above.

[0041] Step a: Input basic data and parameters to obtain basic data such as the coordinates of patrol task points and corresponding benefits, vehicle parking point coordinates, number of drones, maximum single-trip flight time of drones, and maximum total patrol time.

[0042] Step b: Establish an optimization model and construct a mixed-integer linear programming model with the objective of maximizing the total inspection revenue.

[0043] The optimization objective here is to maximize the patrol benefits. Let the set of task points be... Each task point The corresponding return is If the task point If a drone visits the site, the visit decision is recorded as 1; otherwise, it is recorded as 0. The objective function can then be expressed as: Among them, decision variables Indicates task point Whether it is accessed by drones.

[0044] Furthermore, the mixed-integer programming model is established based on the following core constraints: a) Vehicle path constraints: The vehicle departs from the base and returns, and the path satisfies flow balance and no sub-loop. The access to the stop point must match the take-off and landing requirements of the drone. b) Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution shall not exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. c) Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all docking points actually visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. d) Time synchronization constraints: The vehicle arrives at the dock earlier than it departs; the drone lands later than it takes off and matches the vehicle's dwell time in the same sortie; the vehicle leaves the dock later than the drone is recovered and its battery is swapped; and the completion time of each task of the vehicle and the drone does not exceed the upper limit of the total patrol time.

[0045] Understandably, in the actual solution process, in order to improve the model solution efficiency and ensure the feasibility of the solution, several auxiliary constraints (such as vehicle-UAV time coordination constraints, symmetry elimination constraints, etc.) can be further introduced.

[0046] Specifically, in some embodiments, the following combination of constraints may be selected: (1) Vehicle route constraints The following constraints are set for the vehicle route: ① The vehicle departs from the base and eventually returns to the base.

[0047] ② The vehicle path satisfies the flow balance relationship, that is, after a vehicle arrives at a certain stop, it must leave from that stop.

[0048] ③Each stop can be visited at most once.

[0049] ④ Eliminate sub-loops by using sequence variables to ensure that vehicle paths are continuous and connected.

[0050] ⑤ The docking points visited by the vehicle must cover all planned take-off and landing points for the drone. (2) Unmanned mission constraints can be further subdivided into UAV path constraints and UAV endurance constraints, among which: (2-1) UAV path constraints. Here, the following constraints are set for the UAV path.

[0051] ① The drone only takes off or lands at the actual docking point visited by the vehicle.

[0052] ②Each mission point can be visited by a single drone at most once.

[0053] ③ The flight path of the UAV between mission points satisfies the flow balance relationship.

[0054] ④ Each drone may perform at most one sortie at the same docking point.

[0055] ⑤ Eliminate sub-loops in the UAV flight path by using sequential variables to ensure the flight path is continuous and effective.

[0056] (2-2) Unmanned Aerial Vehicle (UAV) Endurance Constraints: Here, we assume that the maximum endurance of a single UAV flight is E, and the sum of the total flight time and mission service time of the UAV in a certain flight is less than or equal to E.

[0057] It is understood that this constraint ensures that the inspection scheme generated by the embodiments of the present invention meets the actual operational capability requirements of the UAV.

[0058] (3) Vehicle-machine coordination constraints Here, coupling constraints are used to ensure that the cooperative relationship between the vehicle and the drone is established.

[0059] ① The take-off and landing points of the drone must be located in the set of nodes actually visited by the vehicle.

[0060] ② When a drone performs a flight mission, its landing point must be located at or after the takeoff point in the vehicle access sequence. Specifically, when using the forward sortie mode, the drone's landing point is limited to being after the takeoff point in the vehicle access sequence.

[0061] ③ The drone can only move between nodes with the vehicle when it is mounted.

[0062] ④ Each drone must travel with the vehicle from the base and eventually return to the base.

[0063] (4) Time synchronization constraints Here, a time coordination mechanism between vehicles and drones is further constructed.

[0064] ① Set the initial departure time of the vehicle to zero.

[0065] ② Calculate the arrival and departure times of vehicles at each stop based on the vehicle route.

[0066] ③ If a drone lands at a certain stop, the drone's landing time is later than its takeoff time and matches the vehicle's dwell time (i.e., the landing / takeoff time of the same drone falls within the vehicle's dwell time at that stop), and the vehicle's departure time is later than the time the vehicle arrives at the stop and later than the time the drone completes its mission and battery swap.

[0067] ④ The completion time of each task by the vehicle and the drone does not exceed the upper limit of the total patrol time, achieving coordinated optimization of waiting, take-off and landing and battery swapping time.

[0068] Step c: Establish a Benders decomposition framework to perform Benders decomposition on the model, obtaining the main problem and subproblems.

[0069] As the number of task points, docking points, and drones increases, the variable size and combinatorial complexity of the above model rise rapidly, making direct overall solution difficult. Therefore, this embodiment of the invention employs the Benders decomposition algorithm for iterative solution until convergence.

[0070] It should be noted that the Benders decomposition algorithm is an efficient decomposition method suitable for mixed integer programming with coupled variables. It makes decisions on vehicle paths and UAV take-off and landing strategies through the main problem, verifies the feasibility of UAV flight paths and time coordination through sub-problems, and iterates and optimizes through cutting plane feedback.

[0071] Step d: Preprocess the variables in the main problem and delete obviously infeasible takeoff and landing decision variables.

[0072] To further improve the solution efficiency, this embodiment of the invention also proposes one of the enhancement strategies—variable preprocessing: pre-determine the infeasible take-off and landing point combinations of the UAV within the maximum single flight time, and remove the corresponding UAV take-off and landing variables.

[0073] Specifically, before solving the main problem, it is pre-determined whether certain combinations of takeoff and landing points constitute feasible flight missions within the drone's range. If, for a given set of takeoff and landing points, the drone cannot meet the range requirements even by visiting only a single mission point, the corresponding variable is fixed to zero to reduce the number of variables.

[0074] Step e: Add effective inequalities to the main problem to compress the search space and improve the solution efficiency.

[0075] To further improve the solution efficiency, this embodiment of the invention also proposes one enhancement strategy—adding various valid inequalities to the main problem: (i) Necessity constraint: Vehicles are only allowed to access docking points where there is a demand for drone take-off and landing; (ii) Necessity constraint: The sum of the vehicle's cumulative driving time, the total battery swapping time of the UAV, and the waiting time in the cycle mode shall not exceed the upper limit of the total patrol time; (iii) Time constraints for a single UAV mission: The sum of the time a single UAV spends moving with the vehicle and its independent flight time shall not exceed the upper limit of the total patrol time; (iv) Symmetry elimination constraint: construct symmetry elimination constraint for homogeneous UAVs.

[0076] Step f: Generate an initial feasible solution using a greedy strategy and use it as the initial upper bound of the algorithm.

[0077] To further improve the solution efficiency, this embodiment of the invention also proposes one of the enhancement strategies—before solving the model, a greedy strategy is used to generate an initial feasible solution: First, a comprehensive score is calculated based on the mission point revenue and accessibility of the docking point. High-scoring docking points are then gradually added to the vehicle path using the most time-efficient insertion method. Among them, docking point accessibility refers to a comprehensive measure of the number of mission points that can be covered around the docking point, the round-trip flight distance of the drone, and the flight time.

[0078] Secondly, candidate tasks are generated in descending order of task point benefits. When the endurance constraint, time synchronization constraint, and total inspection time constraint are satisfied, the corresponding candidate tasks are added to the initial solution to form an initial feasible solution.

[0079] Step g: Initialize the iterative solution parameters, including global upper and lower bounds, the iteration counter, and the current optimal solution information. The upper bound is the current optimal profit estimate, and the lower bound is the actual optimal patrol profit obtained so far.

[0080] Step h: Solve the main problem to obtain the vehicle path, UAV take-off and landing strategy, and the objective value of the main problem.

[0081] Step i: Substitute the vehicle path and UAV take-off and landing strategy determined by the main problem into the subproblem as fixed parameters.

[0082] Step j: Solve the subproblem to determine the specific flight path of the UAV and the time arrangement between the vehicle and the UAV.

[0083] Step k: Determine if the subproblem is feasible.

[0084] Step 1: If the subproblem is not feasible, construct a feasible cut and add it to the main problem.

[0085] Step m: If the subproblem is feasible, calculate the actual patrol benefit of the current plan.

[0086] Step n: Construct an optimal cut based on the solution results of the subproblems and add it to the main problem.

[0087] Associated with steps h-n, the model is solved using the Benders decomposition method, specifically by iteratively performing the following steps until convergence: Main problem: Construct a decision using vehicle route variables, drone take-off and landing variables, payload variables, and route order variables to determine the vehicle stop sequence and drone take-off and landing strategy, and set auxiliary variables to represent the upper bound of revenue; Sub-problem: Based on the solution to the main problem, optimize the flight path of the UAV and the time arrangement of the vehicle and the UAV, verify the feasibility of the path and calculate the actual patrol benefits.

[0088] Furthermore, the main problem and the subproblems interact and iterate through a cutting plane: When the subproblem is infeasible, a feasibility cut is generated and added to the main problem to eliminate infeasible solutions; when the estimated benefit of the main problem exceeds the actual inspection benefit of the subproblem, an optimal cut is generated and added to the main problem to correct the benefit estimate.

[0089] Specifically: The main problem is responsible for high-level collaborative decision-making, determining the vehicle stop visit sequence and the UAV take-off, landing, and payload strategies, providing a decision-making framework for refined UAV planning. The sub-problems, based on fixed vehicle paths and take-off / landing strategies, further optimize the specific UAV flight paths, visit sequences, and vehicle-UAV time coordination to obtain the true optimal patrol benefits under the current scheme.

[0090] If a subproblem is infeasible, it indicates that the current vehicle path or take-off / landing strategy does not meet time or coordination constraints. Invalid solutions are eliminated through feasibility cuts. If a subproblem is feasible but its benefits are overestimated, the benefit boundary is tightened through optimality cuts. After multiple iterations and convergence, the optimal solution or a high-quality feasible solution is finally obtained.

[0091] It is understandable that, through the above iterations, the embodiments of the present invention can obtain the optimal solution or a high-quality solution to the problem in the process of continuously tightening the solution space.

[0092] Step o: Based on the current objective value of the main problem and the actual benefits of the subproblems, update the global upper bound, global lower bound, and the current optimal solution.

[0093] Step p: Determine whether the difference between the global upper and lower bounds meets the preset convergence termination condition.

[0094] Step q: If the termination condition is not met, return to step h to continue iteratively solving the problem.

[0095] Step r: Output the path planning results of vehicles and drones (i.e., the patrol plan) and the corresponding maximum patrol benefits.

[0096] Thus far, this embodiment of the invention has fully described the entire process of the vehicle-machine cooperative path planning method that takes into account the timeliness of inspections.

[0097] Example 2: This invention provides a vehicle-machine cooperative path planning system that considers patrol timeliness, comprising: The basic data acquisition module is used to acquire the coordinates of patrol task points and their corresponding benefits, the coordinates of vehicle parking points, the number of drones, the maximum single flight time of drones, and the upper limit of total patrol time. Among them, the benefit is the value measure of the task point information, and its value is positively correlated with the patrol priority of the task point, and is determined by at least one of the following: the importance of the task point, the urgency, and the risk level. The model building module is used to calculate the flight time and path required for the UAV mission based on the coordinates of the patrol task points and the vehicle docking points. It establishes a mixed-integer linear programming model with the objective of maximizing the total patrol revenue, which is the sum of the revenues corresponding to each task point visited. Model constraints include: Vehicle path constraints: The vehicle departs from and returns from the base, and the path satisfies flow balance and no sub-loops. The access to the docking point must match the take-off and landing requirements of the drone. Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution cannot exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all the actual docking points visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. Time synchronization constraints: The vehicle arrives at the docking point earlier than the departure time; the drone lands later than the takeoff time and matches the vehicle's dwell time in the same sortie; the vehicle leaves the docking point later than the drone recovery and battery swapping time; and the completion time of each task of the vehicle and the drone does not exceed the upper limit of the total patrol time. The strategy solving module solves the model to generate vehicle paths, UAV flight paths, and take-off and landing strategies.

[0098] The embodiments of this invention aim to maximize the total benefits of patrols, prioritizing the coverage of high-value task points within a limited time to improve overall efficiency; by integrating vehicle routes, UAV take-off and landing, and flight paths into a unified plan, vehicle-machine collaboration is enhanced; considering factors such as range, time synchronization, and battery swapping constraints, the solution is more in line with practical applications and efficiently solves the problems of vehicle-machine collaborative scheduling and task access efficiency.

[0099] In an alternative implementation, the model is solved using the Benders decomposition method, which includes iteratively performing the following steps until convergence: Main problem: Construct a decision using vehicle route variables, drone take-off and landing variables, payload variables, and route order variables to determine the vehicle stop sequence and drone take-off and landing strategy, and set auxiliary variables to represent the upper bound of revenue; Sub-problem: Based on the solution to the main problem, optimize the flight path of the UAV and the time arrangement of the vehicle and the UAV, verify the feasibility of the path and calculate the actual patrol benefits.

[0100] In an optional implementation, the main problem and the subproblems interact and iterate through a cutting plane: When the subproblem is infeasible, a feasibility cut is generated and added to the main problem to eliminate infeasible solutions; When the estimated return of the main problem exceeds the actual inspection return of the sub-problems, an optimal cut is generated and added to the main problem to correct the return estimate.

[0101] In an optional implementation, a variable preprocessing step is performed before solving the main problem: Pre-determine infeasible take-off and landing point combinations for the drone within its maximum single flight time, and eliminate the corresponding drone take-off and landing variables.

[0102] In one optional implementation, the drone supports both cyclic sortie mode and forward sortie mode; The cyclic sortie mode refers to the drone taking off and landing from the same docking point; The forward sortie mode refers to the UAV taking off from the current docking point and landing at a subsequent docking point in the vehicle's forward direction; and when the forward sortie mode is adopted, the vehicle-machine cooperative constraint includes that the UAV landing point is located after the takeoff point in the vehicle access sequence.

[0103] In an alternative implementation, one or more of the following valid inequalities are added to the main problem: (i) Vehicles are only permitted to access docking points where there is a demand for drone take-off and landing; (ii) The sum of the vehicle's total driving time, the total battery swapping time of the UAV, and the waiting time in the cycle mode shall not exceed the upper limit of the total patrol time; (iii) The sum of the time a single drone spends moving with the vehicle and its independent flight time shall not exceed the upper limit of the total patrol time; (iv) Eliminate constraints on the symmetry of homogeneous UAV construction.

[0104] In an optional implementation, before solving the model, an initial feasible solution is generated using a greedy strategy, including: A comprehensive score is calculated based on the task point revenue and stop point accessibility around the stop point, and high-scoring stop points are gradually added to the vehicle path using the most time-saving insertion method. Candidate tasks are generated from high to low based on the task point benefits. When the endurance constraint, time synchronization constraint, and total inspection time constraint are satisfied, the corresponding candidate task is added to the initial solution to form an initial feasible solution.

[0105] Example 3: This invention provides a storage medium storing a computer program, wherein the computer program causes a computer to execute a vehicle-machine cooperative path planning method considering inspection timeliness as provided in any embodiment of this invention.

[0106] In embodiments of the present invention, any combination of one or more storage media may be used. The storage medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM, ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0107] Example 4: This invention provides an electronic device. Figure 3 The diagram shown is a structural schematic of the electronic device 100 provided in an embodiment of the present invention. In some embodiments, the electronic device may be a mobile phone, tablet computer, wearable device, in-vehicle device, augmented reality (AR) / virtual reality (VR) device, laptop computer, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), or other terminal device. Furthermore, the vehicle-machine cooperative path planning method considering inspection timeliness provided in this embodiment of the present invention can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. This embodiment of the present invention does not limit the specific application scenarios of the vehicle-machine cooperative path planning method considering inspection timeliness.

[0108] like Figure 3 As shown, the electronic device 100 provided in this embodiment of the invention includes a memory 101 and a processor 102.

[0109] The memory 101 is used to store computer programs; preferably, the memory 101 includes various media that can store program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0110] Specifically, memory 101 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. Electronic device 100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 101 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0111] The processor 102 is connected to the memory 101 and is used to execute the computer program stored in the memory 101 so that the electronic device 100 executes the vehicle-machine cooperative path planning method that takes into account the inspection timeliness provided in any embodiment of the present invention.

[0112] In an optional implementation, the processor 102 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, evaluation index gate or transistor logic devices, or evaluation index hardware components.

[0113] In an optional embodiment, the electronic device 100 of this invention may further include a display 103. The display 103 is communicatively connected to the memory 101 and the processor 102, and is used to display the relevant GUI interactive interface of the vehicle-machine cooperative path planning method that takes into account the inspection timeliness.

[0114] It is understood that the vehicle-machine cooperative path planning system, storage medium and electronic device considering inspection timeliness provided in the embodiments of the present invention correspond to the vehicle-machine cooperative path planning method considering inspection timeliness provided in the embodiments of the present invention. The explanation, examples and beneficial effects of the relevant contents can be referred to the corresponding parts of the method, and will not be repeated here.

[0115] In summary, compared with related technologies, it has the following beneficial effects: 1. Improve patrol efficiency: The embodiments of the present invention aim to maximize the total patrol benefits, and can prioritize accessing task points with higher weight within a limited patrol time, thereby improving the overall efficiency of emergency patrols.

[0116] 2. Enhanced Collaborative Capabilities: This embodiment of the invention integrates vehicle path, docking point selection, UAV take-off and landing recovery, and flight path planning, thereby improving the collaborative operation capabilities between vehicles and vehicle-mounted UAVs.

[0117] 3. Improve mission execution flexibility: This embodiment of the invention supports two flight modes for UAVs: cyclical sorties and forward sorties, and allows UAVs to continuously visit multiple mission points in a single flight, thereby improving the flexibility of patrol mission execution.

[0118] 4. Enhance practical application value: The embodiments of the present invention comprehensively consider the total inspection time constraint, the drone's endurance constraint, the time synchronization relationship between the vehicle and the drone, and the battery swapping process, so that the planning results are closer to the real application scenario of emergency inspection of power transmission lines.

[0119] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0120] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle-machine cooperative path planning method considering patrol timeliness, characterized in that, include: Obtain the coordinates of patrol task points and their corresponding benefits, vehicle parking point coordinates, number of drones, maximum single-trip flight time of drones, and total patrol time limit; among them, the benefit is the value measure of task point information, and its value is positively correlated with the patrol priority of the task point, and is determined by at least one of the following: task point importance, urgency, and risk level. Based on the coordinates of the patrol task points and vehicle parking points, the flight time and path required for the UAV mission are calculated. A mixed-integer linear programming model is established with the objective of maximizing the total patrol revenue, where the total patrol revenue is the sum of the revenues corresponding to each task point visited. The model constraints include: Vehicle path constraints: The vehicle departs from and returns from the base, and the path satisfies flow balance and no sub-loops. The access to the docking point must match the take-off and landing requirements of the drone. Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution cannot exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all the actual docking points visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. Time synchronization constraints: The vehicle arrives at the docking point earlier than the departure time; the drone lands later than the takeoff time and matches the vehicle's dwell time in the same sortie; the vehicle leaves the docking point later than the drone recovery and battery swapping time; and the completion time of each task of the vehicle and the drone does not exceed the upper limit of the total patrol time. The solution model generates vehicle paths, UAV flight paths, and take-off and landing strategies.

2. The vehicle-machine cooperative path planning method as described in claim 1, characterized in that, The model is solved using the Benders decomposition method, which involves iteratively performing the following steps until convergence: Main problem: Construct a decision using vehicle route variables, drone take-off and landing variables, payload variables, and route order variables to determine the vehicle stop sequence and drone take-off and landing strategy, and set auxiliary variables to represent the upper bound of revenue; Sub-problem: Based on the solution to the main problem, optimize the flight path of the UAV and the time arrangement of the vehicle and the UAV, verify the feasibility of the path and calculate the actual patrol benefits.

3. The vehicle-machine cooperative path planning method as described in claim 2, characterized in that, The main problem and the sub-problems interact and iterate through a cutting plane: When the subproblem is infeasible, a feasibility cut is generated and added to the main problem to eliminate infeasible solutions; When the estimated return of the main problem exceeds the actual inspection return of the sub-problems, an optimal cut is generated and added to the main problem to correct the return estimate.

4. The vehicle-machine cooperative path planning method as described in claim 2, characterized in that, Before solving the main problem, perform variable preprocessing steps: Pre-determine infeasible take-off and landing point combinations for the drone within its maximum single flight time, and eliminate the corresponding drone take-off and landing variables.

5. The vehicle-machine cooperative path planning method as described in claim 2, characterized in that, The drone supports both cyclic sortie mode and forward sortie mode; The cyclic sortie mode refers to the drone taking off and landing from the same docking point; The forward sortie mode refers to the UAV taking off from the current docking point and landing at a subsequent docking point in the vehicle's forward direction; and when the forward sortie mode is adopted, the vehicle-machine cooperative constraint includes that the UAV landing point is located after the takeoff point in the vehicle access sequence.

6. The vehicle-machine cooperative path planning method as described in claim 5, characterized in that, Add one or more of the following valid inequalities to the main problem: (i) Vehicles are only permitted to access docking points where there is a demand for drone take-off and landing; (ii) The sum of the vehicle's total driving time, the total battery swapping time of the UAV, and the waiting time in the cycle mode shall not exceed the upper limit of the total patrol time; (iii) The sum of the time a single drone spends moving with the vehicle and its independent flight time shall not exceed the upper limit of the total patrol time; (iv) Eliminate constraints on the symmetry of homogeneous UAV construction.

7. The vehicle-machine cooperative path planning method as described in claim 1, characterized in that, Before solving the model, a greedy strategy is used to generate an initial feasible solution, including: A comprehensive score is calculated based on the task point revenue and stop point accessibility around the stop point, and high-scoring stop points are gradually added to the vehicle path using the most time-saving insertion method. Candidate tasks are generated from high to low based on the task point benefits. When the endurance constraint, time synchronization constraint, and total inspection time constraint are satisfied, the corresponding candidate task is added to the initial solution to form an initial feasible solution.

8. A vehicle-machine cooperative path planning system that considers patrol timeliness, characterized in that, include: The basic data acquisition module is used to acquire the coordinates of patrol task points and their corresponding benefits, the coordinates of vehicle parking points, the number of drones, the maximum single flight time of drones, and the upper limit of total patrol time. Among them, the benefit is the value measure of the task point information, and its value is positively correlated with the patrol priority of the task point, and is determined by at least one of the following: the importance of the task point, the urgency, and the risk level. The model building module is used to calculate the flight time and path required for the UAV mission based on the coordinates of the patrol task points and the vehicle docking points. It establishes a mixed-integer linear programming model with the objective of maximizing the total patrol revenue, which is the sum of the revenues corresponding to each task point visited. Model constraints include: Vehicle path constraints: The vehicle departs from and returns from the base, and the path satisfies flow balance and no sub-loops. The access to the docking point must match the take-off and landing requirements of the drone. Drone mission constraints: Drones can only take off and land from docking points accessed by vehicles. The sum of the time for a single flight and the time for mission execution cannot exceed the maximum endurance. Each mission point can be accessed by a single drone at most once. Drones can support continuous access to multiple mission points in a single flight. Vehicle-machine collaboration constraints: The take-off and landing points of the drones are all the actual docking points visited by the vehicles. The drones depart from the base with the vehicles and eventually return to the base. Time synchronization constraints: The vehicle arrives at the docking point earlier than the departure time; the drone lands later than the takeoff time and matches the vehicle's dwell time in the same sortie; the vehicle leaves the docking point later than the drone recovery and battery swapping time; and the completion time of each task of the vehicle and the drone does not exceed the upper limit of the total patrol time. The strategy solving module solves the model to generate vehicle paths, UAV flight paths, and take-off and landing strategies.

9. A storage medium, characterized in that, It stores a computer program, wherein the computer program causes the computer to execute the vehicle-machine cooperative path planning method considering patrol timeliness as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes: Processor and memory; The memory stores program instructions; The processor is configured to run the program instructions to execute the vehicle-machine cooperative path planning method considering inspection timeliness as described in any one of claims 1 to 7.

Images