A method, storage medium, and device for air-ground cooperative trajectory planning based on genetic algorithms and sliding window optimization.

Abstract

This invention discloses an air-ground cooperative trajectory planning method, storage medium, and device based on genetic algorithms and sliding window optimization. Addressing the scenario of cooperative trajectory planning between tethered UAVs and unmanned vehicles, this invention tackles constraints such as speed mismatch between UAVs and unmanned vehicles, spatial coupling between UAVs and unmanned vehicles due to limited tether cable length and deployment / retrieval speed, and ground collision avoidance for unmanned vehicles. Focusing on objectives such as shortest trajectory, shortest task time, and optimal trajectory, it uses a genetic algorithm to achieve trajectory planning tasks with multiple constraints and optimization objectives under an air-ground cooperative operation system. Furthermore, a sliding window optimization method is employed to adjust and adaptively optimize the real-time trajectory, resolving the problem of trajectory planning conflicts between tethered UAVs and unmanned vehicles during outdoor power system inspections.

Description

Technical Field

[0001] This invention relates to an air-ground cooperative trajectory planning method, storage medium, and device based on genetic algorithms and sliding window optimization, for use in the field of tethered drones and unmanned vehicles cooperating in outdoor inspections of power systems, and particularly to the process of air-ground cooperative trajectory planning. Background Technology

[0002] Tethered drones, as a new type of drone technology, connect to ground power and data transmission systems via tethered cables, enabling extended aerial stays and operations. Compared to traditional stand-alone drones, tethered drones not only offer longer flight endurance but also provide enhanced reliability and data transmission capabilities through their connection to ground systems. A typical tethered drone system mainly consists of three parts: the drone platform, the tethered cable, and the ground integrated platform. The ground integrated platform includes a power system and an automatic cable deployment and retrieval device, providing power and communication links for the tethered drone and ensuring the cable unfolds and retracts in an orderly manner during drone ascent and descent, avoiding tangling.

[0003] In the field of power line inspection, tethered drones can hover at high altitudes such as power lines and substations for extended periods, monitor equipment operation in real time, and quickly transmit high-definition images to help staff identify potential fault points. They are particularly suitable for power line inspection scenarios that require uninterrupted lighting, monitoring, or data collection, including nighttime maintenance lighting, high-altitude operation safety monitoring, refined autonomous inspection, and emergency and special inspections.

[0004] Unmanned vehicle (UAV) power line inspection is a crucial and mature component of smart grids and digital transformation. It refers to the advanced technology of using ground-based mobile robots (often called UAVs or ground robots) to autonomously or remotely inspect, collect data, and monitor the status of power facilities. For outdoor power line inspection scenarios, UAVs can perfectly complement tethered drones. The UAV acts as a ground platform for the tethered drone, and both UAVs possess autonomous operating capabilities. Around the task scenario, they collaborate on decision-making and planning, achieving data sharing and collaborative operations, thus constructing an integrated "air + ground" intelligent inspection system. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an air-ground cooperative trajectory planning method, computer equipment, and storage medium based on genetic algorithms and sliding window optimization.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] First, a power line inspection air-ground cooperative trajectory planning method based on genetic algorithm and sliding window optimization is presented. The method includes:

[0008] Step 1) Construct a multi-constraint, multi-objective optimization model for collaborative trajectory planning of tethered UAVs and unmanned vehicles, and define gene-encoded variables, which include the coordinates and speed of the three-dimensional trajectory points of the tethered UAV, the two-dimensional plane trajectory coordinates of the unmanned vehicle, and the cable length information of the tethered cable winch.

[0009] Step 2) Set the constraints of the multi-constraint multi-objective optimization model, including the trajectory constraints and speed constraints of the tethered UAV, the collision constraints, speed constraints, and motion rotation angle constraints of the unmanned vehicle, as well as the winch cable length constraints and cable deployment / retraction speed constraints.

[0010] Step 3) Set the multi-objective optimization function of the multi-constraint multi-objective optimization model, including the shortest time for the coupled track chain, the minimum energy consumption of the tethered UAV and the unmanned vehicle, the optimal trajectory smoothness, the minimum collision risk of the unmanned vehicle, the minimum number of winch cable releases and take-ups, and the minimum average cable length. The weight coefficient change method is used to normalize the multi-objectives and construct the individual fitness function.

[0011] Step 4) Solve the multi-constraint multi-objective optimization model using an improved genetic algorithm, including: generating an initial population based on constraints, calculating individual fitness, performing selection operations using tournament selection, performing crossover operations using an adaptive multi-point crossover method, performing mutation operations using a Gaussian mutation method based on constraints, and performing sliding window optimization on individual gene encoding after each generation of evolution, finally outputting a cooperative trajectory that satisfies all constraints and has the best fitness.

[0012] Optionally, the gene-encoding variables in step 1) A layered coupling structure is used to encode the tethered UAV track. Unmanned vehicle track coding Coding with winch cable length Encapsulated as a unified node, and the position of the tethered drone on the predetermined trackline. As a public benchmark.

[0013] Optionally, in step 2), the collision constraint of the unmanned vehicle adopts a gridded electronic map, which merges obstacles and safety radii into no-entry grids, and counts the number of no-entry grids crossed by the unmanned vehicle trajectory in real time during the gene decoding stage.

[0014] Optionally, the adaptive multi-point crossover method described in step 4) selects the maximum number of crossover points in the early stages of evolution. To increase diversity, a value of ≥8 is used, and then the value is reduced to a linear decreasing value in the later stages. ≤4.

[0015] Optionally, the Gaussian mutation described in step 4) is in , , The mutation operation is performed in a hierarchical and progressive manner.

[0016] Optionally, step 5 is also included, in which the environment and trajectory deviation are monitored in real time during actual execution, and sliding window optimization is used to replan and dynamically adjust the local trajectory to ensure the real-time feasibility, safety and optimization of the collaborative flight path of the tethered UAV and the unmanned vehicle.

[0017] Optionally, the multi-objective optimization function described in step 3) adopts a dynamic weighting strategy after normalization: in the offline evolution stage, the degree of skewness of the optimization objective is calculated according to a preset fixed weight vector; in the online sliding window stage, the weights are adjusted online according to the real-time deviation and the remaining cable length margin, so that the weights of energy consumption and safety increase as the real-time deviation increases.

[0018] Optionally, the sliding window optimization described in step 5) specifically involves: monitoring actual deviations and environmental changes, extracting unexecuted track segments by node number, first calculating the local path of the unmanned vehicle using the A* algorithm, and then verifying whether the winch speed and cable length exceed the limits; if they exceed the limits, reducing the speed of the unmanned vehicle and replanning; otherwise, writing the corrected segment back to the gene chain and superimposing the deviation correction amount before outputting control commands, and then incrementing the node number and repeating the process until the task is completed.

[0019] Secondly, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the above-described method.

[0020] Finally, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method.

[0021] The beneficial effects of this invention are as follows: This invention addresses the collaborative trajectory planning scenario of tethered UAVs and unmanned vehicles. It addresses constraints such as speed mismatch between UAVs and unmanned vehicles, spatial coupling between UAVs and unmanned vehicles caused by the length and deployment / retrieval speed of the tether cable, and ground collision avoidance for unmanned vehicles. Focusing on objectives such as shortest trajectory, shortest time, and optimal trajectory, it uses a genetic algorithm to achieve trajectory planning tasks with multiple constraints and optimization objectives under an air-ground collaborative operation system. Furthermore, it employs a sliding window optimization method to adjust and adaptively optimize the real-time trajectory, thus solving the problem of collaborative trajectory planning for tethered UAVs and unmanned vehicles during outdoor inspections of power systems. Attached Figure Description

[0022] Figure 1 This is a schematic diagram illustrating the collaborative operation of a tethered drone and an unmanned vehicle.

[0023] Figure 2 Flowchart of a multi-constraint, multi-objective genetic algorithm;

[0024] Figure 3 Optimize the flowchart for real-time sliding windows. Detailed Implementation

[0025] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0026] like Figure 1 As shown, the tethered UAV (T-UAV) A001 needs to navigate along a planned trajectory, connected to the unmanned vehicle (UGV) A002 via a tether cable A003 to obtain power supply and communication data. The UGV A002 follows the tethered UAV A001, while avoiding ground obstacles to ensure its own safety. Since the position between the UGV A002 and the tethered UAV A001 is constrained by the cable length, the UGV A002 needs to search for the optimal navigation path within a limited space. Alternatively, the UGV A002 can also gain more room to maneuver by adjusting the cable length with the tethered UAV A001. Generally, the winch cable length needs to be maintained within the optimal range based on the spatial relationship between the UGV A002 and the tethered UAV A001. A cable that is too short will restrict the maneuverability of the tethered UAV A001, while an excessively long cable will increase the navigation resistance and the risk of entanglement. The radius R1 represents the radius of the circular range within which the UGV A002 can move under the current cable length constraint.

[0027] In this embodiment, the global cooperative trajectory planning of the tethered UAV and the unmanned vehicle can be regarded as a multi-constraint, multi-objective optimization problem, defined as follows: This represents two highly coupled flight path chains for the tethered UAV and the unmanned vehicle. Path points on each path chain are coupled to a point on the other's path chain. The distance between the coupled path points is anchored to the cable length information of the tethered winch under the same node. To accurately represent this coupled path chain, this embodiment defines node encoding variables. as follows:

[0028]

[0029] use This indicates that the tethered UAV's 3D track numbered as The coordinates and speed of the waypoints. The coordinates of the autonomous vehicle's two-dimensional ground trajectory are represented by the coordinates of the trajectory. Coupling means that the tethered drone and the unmanned vehicle must move to this position simultaneously. The length of the mooring winch represents the length of the cable. , Coupling. Then the node encoding variable... This can be further described as:

[0030]

[0031] An individual's genetic code must directly contain or influence all key variables within the entire system; it is the sole instruction guiding the individual's behavior. Gene node encoding of individual populations, and track encoding of tethered drones. middle, It does not represent the position of the tethered drone in a spatial coordinate system, but rather the position of the tethered drone on a predetermined path. and Then it represents the first The lateral and longitudinal offsets of the tethered drone relative to the predetermined trajectory line at each node, after adopting the above gene coding method, only need to be limited. and The range of values ​​can satisfy the trajectory constraints of tethered drones. And continuous The set value provides a baseline for subsequent crossover processes in the population, which is beneficial for gene splicing and optimization. A person possessing... The gene chain of an individual with a gene coding node can be represented as follows:

[0032]

[0033] To solve The Each node, using express The segment, hereinafter referred to as .

[0034] The optimization problem revolves around three constraints: tethered drones, unmanned vehicles, and winches. The following seven constraints can be extracted:

[0035] (1) Trajectory constraints of tethered UAVs Tethered drones must fly along a predetermined trajectory, with a certain degree of deviation allowed in both lateral and longitudinal directions. The tethered drone's trajectory is coded. middle, This indicates the position of the tethered drone on the predetermined flight path. and Then it represents the first The lateral and longitudinal offsets of the tethered drone relative to the predetermined trajectory line at each node are limited. and The range of values ​​can be used to constrain the trajectory of tethered drones. , Used to store the flight path of the unmanned vehicle and The range of values ​​for is required. .

[0036] (2) Speed ​​constraints of tethered UAVs The maximum flight speed and maximum acceleration / deceleration capability of the tethered drone must be selected within a limited set range. express The flight speed of the tethered drone at that location, express The acceleration of tethered drones, Indicates the maximum permissible flight speed of the tethered drone. This indicates the maximum permissible acceleration and speed constraint for tethered drones. Used to save the current solution middle and Quantity required .

[0037] (3) Collision constraints for unmanned vehicles The unmanned vehicle's trajectory should not collide with any obstacles and must remain outside the safe distance of all ground obstacles. The boundary of the no-entry zone for ground obstacles includes the obstacle itself and the safe radius. This embodiment uses a grid method to process electronic charts and obstacle targets. Used to save solutions Unmanned vehicle flight path The number of obstacle grids traversed is required. .

[0038] (4) Unmanned vehicle speed constraints The maximum speed and maximum acceleration / deceleration capability of the unmanned vehicle must be selected within a limited set range; define and constrain the speed of the tethered drone. Similarly, requirements .

[0039] (5) Unmanned vehicle motion turning angle constraint When searching for a path, autonomous vehicles must consider the maximum turning angle constraint, making sharp turns impossible. The selection of the next point's location must be based on the previous point's location and heading, overlaid with the search viewpoint, within the reachable range. express and The turning angles of the two segments of the unmanned vehicle's flight path. This indicates the maximum permissible threshold for the turning angle of the autonomous vehicle's trajectory. Used for saving The number of nodes and the trajectory turning angle constraints. .

[0040] (6) Winch cable length constraint The winch cable length must accommodate the distance between the tethered drone and the unmanned vehicle, and there is a maximum length limit; Represents a node The winch cable is long. This indicates the maximum usable cable length for the winch. Using a parabolic fitting method, the minimum cable length required for stable navigation of the tethered UAV is determined based on the three-dimensional spatial relationship between the tethered UAV and the unmanned vehicle. , Used to store and Quantity required .

[0041] (7) Winch cable release and take-up speed constraints There is a maximum speed limit for cable winding and unwinding when adjusting cable length using a winch. Representing fragments The average speed of the inner winch in winding and unwinding the cable. This indicates the maximum speed of the winch. Used to store Quantity required .

[0042] To achieve optimal air-ground cooperative trajectory planning for tethered drones and unmanned vehicles, and to optimize the problem... The following eight optimization objectives are set: including minimizing the time for coupling the path chain. Tethered drones have the lowest energy consumption Smoothness of tethered drone trajectory Minimize the risk of collisions during autonomous vehicle navigation Autonomous vehicles consume the least energy Smoothness of autonomous vehicle trajectory The winch cable length is minimized and the number of times it is wound up and down is minimized. The winch has the smallest average cable length. After normalization, the eight optimization objectives are used to obtain the final target values ​​using the weighting coefficient transformation method. The mathematical description is as follows:

[0043]

[0044] In the above formula These represent the weight values ​​for the eight optimization objectives, indicating... The degree to which this optimization objective is emphasized.

[0045] Therefore, the global trajectory planning problem for tethered UAVs and unmanned vehicles can be described as: outputting a trajectory that satisfies the constraints. And optimize the overall objective value The minimum coupled flight path chain, i.e., the shortest possible travel time, the smoothest possible trajectory for the tethered UAV and unmanned vehicle, the lowest possible energy depletion, and the fewest possible winch operations while maintaining a reasonable cable length. The mathematical quantification of these eight optimization objectives is as follows:

[0046] (1) Target with the shortest coupling track chain time : Representing fragments The flight time for an internally tethered drone is as follows:

[0047]

[0048] (2) Tethered drones have the lowest energy consumption In the objective optimization function In this study, the energy consumption of tethered drones is one of the eight optimization objectives included in the horizontal comparison. The calculation is performed using weighted coefficients, and it is not necessary to determine the specific energy consumption value. Therefore, some parameters can be simplified. The energy consumption required for the tethered drone to maintain its balance can be ignored, and only the energy consumption due to the drone's speed can be considered. The energy consumption objective function can then be approximately expressed as:

[0049]

[0050] The drag of a tethered drone can generally be expressed as:

[0051]

[0052] in Indicates air density; Indicates the speed of the tethered drone; This indicates the drag coefficient of a tethered unmanned aerial vehicle (UAV). Representing the frontal cross-sectional area (the projected area perpendicular to the direction of motion), we can obtain:

[0053]

[0054] (3) Smoothness of tethered UAV trajectory All trajectory turns within the tethered drone's trajectory segment The mean is defined as follows:

[0055]

[0056] (4) Minimize the risk of collision during unmanned vehicle navigation Definition method and collision constraints of autonomous vehicles Consistency is a double guarantee for ensuring the safety of unmanned vehicle navigation trajectories.

[0057]

[0058] (5) Minimize energy consumption of unmanned vehicles Definition and Minimum Energy Consumption Target for Tethered Unmanned Aerial Vehicles Similarly, as follows:

[0059]

[0060] (6) Smoothness of unmanned vehicle trajectory Definition and smoothness of tethered drone trajectory Similarly, the definition is as follows:

[0061]

[0062] (7) Minimize the number of times the winch cable is wound and released. This optimization goal can avoid frequent cable length adjustments; Representing fragments The average speed of the inner winch in winding and unwinding the cable. Used to store The quantity is defined as follows:

[0063]

[0064] (8) Minimum target for average cable length of winch The winch cable length should be used as needed; an excessively long cable will increase the drag on the tethered drone and the risk of entanglement. Represents a node The winch cable is long. The definition is as follows:

[0065]

[0066] In summary, the calculation methods for each optimization objective are as follows:

[0067]

[0068] Therefore, the problem of air-ground cooperative trajectory planning for tethered drones and unmanned vehicles can be expressed as:

[0069]

[0070] Regarding optimization issues Based on the corresponding constraints and optimization objectives, this embodiment, building upon the genetic algorithm, employs an improved population initialization strategy and a heuristic evolutionary method. Furthermore, it incorporates a sliding window method to optimize local trajectories during the actual execution phase of the coupled trajectory, thereby realizing a power line inspection air-ground cooperative trajectory planning method based on genetic algorithms and sliding window optimization. Experiments have demonstrated that this algorithm can meet the global cooperative trajectory planning requirements of tethered UAVs and unmanned vehicles, and possesses advantages such as multi-objective adaptive optimization, fast convergence speed, and higher trajectory search success rate.

[0071] (1) Gene coding design:

[0072]

[0073] (2) Individual fitness design:

[0074] The individual fitness function is selected based on the sum of the objective weights. , The smaller the value, the higher the individual's environmental adaptability.

[0075] (3) A multi-constraint, multi-objective genetic algorithm for air-ground cooperative trajectory planning in power line inspection, see Figure 2 :

[0076] Step 001: Initialize the parameters of the power line inspection air-ground collaborative system;

[0077] Step 002: Based on constraints Generate an initial population;

[0078] Step 003: Based on Function for calculating the fitness of individuals within a population;

[0079] Step 004: Selection: Select superior individuals based on their fitness.

[0080] Step 005: Crossover: Superior individuals within the population crossover to generate offspring;

[0081] Step 006: Mutation: Mutating the gene coding within offspring individuals with a certain probability;

[0082] Step 007: Individual optimization: Optimize each offspring gene one by one based on the sliding window optimization operator;

[0083] Step 008: Generate a new generation of population based on individual selection strategies;

[0084] Step 009: Check if the number of evolution iterations has reached the set value. If not, return to step 003 and continue a new round of evolution. If yes, output the optimal individual based on the current state and end the algorithm process.

[0085] In a preferred example: The difficulty of population initialization lies in the complex and diverse constraints and optimization objectives. This embodiment is based on an innovative gene encoding method, combined with an iterative search method, to gradually complete the population initialization process. All individuals in the initial population have high fitness while satisfying all constraints.

[0086] The population initialization process is as follows:

[0087] Step 201: Initialize system parameters, tethered UAV search starting point coordinates, and node sequence number. Number of individuals in the target population ;

[0088] Step 202: ++, random sampling The probability of winning a lottery value is determined based on a normal distribution, and a random selection algorithm is used to select the winning value.

[0089] Step 203: Select the horizontal movement based on a greedy algorithm and longitudinal movement Priority is given to the location of the endpoint of the trajectory of unmanned vehicles and tethered drones, and the probability of winning is allocated accordingly. Then, the winning value is determined according to the random selection algorithm.

[0090] Step 204: Determine the motion time from the average velocity between the two nodes of the tethered drone. ;

[0091] Step 205: Randomly sample the winch speed based on a normal distribution , ;

[0092] Step 206: Fit the parabola according to the constraint relationship Calculate the maximum reachable radius of the autonomous vehicle (lock up );

[0093] Step 207: Determine the maximum achievable speed of the autonomous vehicle based on its maximum acceleration and deceleration capabilities. and minimum achievable speed Calculate the average velocity and the radius of motion (circles) respectively. and circle );

[0094] Step 208: Select Overlapping areas, obstacle removal areas and their safety radii, generate a set of areas selectable by the unmanned vehicle;

[0095] Step 209: Based on a greedy algorithm, prioritize selecting coordinates close to the tethered drone. If the coordinates are unreachable, then use... The algorithm is connected, and the number of coordinate points of the tethered UAV is expanded according to the number of reversal nodes to obtain... and ;

[0096] Step 210: Iterate through and check whether each individual meets the mandatory constraints; discard those that do not.

[0097] Step 211: (The population has not reached the specified number of individuals) Return to step 202;

[0098] Step 212: Population initialization complete.

[0099] Furthermore, in step 203, the longitudinal and lateral displacements are selected based on a greedy algorithm. and vertical lateral movement The logic is as follows: Define candidate positions. The distance to the driverless car is The distance to the destination of the tethered drone is Then design intermediate quantities as follows:

[0100]

[0101] represent The percentage on the predetermined trajectory defines the candidate location. The probability function for selection is as follows:

[0102]

[0103] Furthermore, in step 206, to calculate the maximum radius of motion of the unmanned vehicle under the current cable length constraint, a parabolic fitting method is used to approximate the cable length attitude at the maximum radius of motion. It is assumed that the height of the tethered drone relative to the unmanned vehicle is... The horizontal distance is Then the minimum winch cable length Satisfy the following formula:

[0104]

[0105] Based on the above formula, the maximum radius of motion of the unmanned vehicle under the current cable length can be calculated in reverse.

[0106] In a preferred example, after the selection, crossover, and mutation stages of the conventional genetic algorithm, an individual optimization stage is added. A heuristic evolutionary approach is adopted to artificially optimize the gene encoding within some individuals, thereby improving the fitness of the individuals, inspiring the evolution of the population, and accelerating the convergence process.

[0107] further:

[0108] (1) The selection process adopts the Tournament Selection method, and the selection is based on the fitness of each individual. The main idea is to select the best individuals from a group of individuals through multiple rounds of comparison, which will serve as the basis for the next round of evolution. The advantage of the competitive selection method is that it is relatively stable when dealing with high-dimensional problems, is not prone to getting trapped in local optima, and can effectively avoid premature convergence in the selection process, thereby improving the algorithm's global search capability and increasing the diversity of the population.

[0109] (2) An adaptive multi-point crossover method is used for the crossover process, and the number of crossover points is set. (usually set to) In the early stages of population evolution, the number of crossover points is selected. To improve population diversity, the number of crossover points was selected in the later stage. This accelerates the convergence of individuals within the population.

[0110] (3) The Gaussian mutation method based on constraints was selected for the mutation stage. Since the constraints are diverse and complex, blind mutations can lead to new individuals that do not meet the constraints. Therefore, the mutation stage must consider the limitations of the constraints; otherwise, it is an invalid mutation. To maintain the stability of the population, an individual screening rate was set. Individuals are randomly selected for mutation, and the selected individuals are evaluated based on their gene mutation rate. It determines whether each gene encodes a mutation or not. This limits the maximum range of gene mutations, generally taking the value of the mutation target. This avoids excessively large values ​​that could lead to random walks of mutation numbers. (Gene encoding) The internal variables are coupled and constrained with each other, therefore they are divided according to the subsystem object. , , The mutation operation is performed in three parts, using a hierarchical and progressive approach. Furthermore, to ensure the mutation operation is carried out controllably under constraints, each gene-coding mutation is preceded by a check against the constraints and a mutation value constraint coefficient. Calculate the range of mutations that satisfy the constraints, then use Gaussian mutation to select mutation values. After mutation is completed, perform a constraint check and retain only the mutated individuals that meet the constraints.

[0111] (4) The individual optimization stage aims at local optimization. It relies on the sliding window optimization operator to traverse the gene sequence and optimize the local genome coding, which can accelerate population evolution and individual convergence. The optimization process is similar to that of the mutation stage. , , The optimization is carried out in batches in three parts, including the optimization of the tethered drone trajectory, the optimization of the tethered drone speed, and the optimization of the winch cable length. After the local optimization, it is checked whether it meets the constraints. If it does not meet the constraints, it is discarded.

[0112] In a preferred example, the optimized operator design is as follows:

[0113] (1) Trajectory optimization operator for tethered UAVs:

[0114] Tethered UAV trajectory optimization can improve the smoothness of the tethered UAV's flight path, enabling outliers deviating from the trajectory to undergo adaptive approach processing based on a sliding window operator. Matrix operators The object being processed is The trajectory optimization operator for tethered drones is defined as follows:

[0115]

[0116]

[0117]

[0118] (2) Tethered UAV speed optimization operator:

[0119] The tethered drone speed optimization operator is matrix The object being processed is Operation method and tethered drone trajectory optimization operator similar.

[0120]

[0121]

[0122] (3) Winch cable length optimization operator:

[0123] Winch cable length optimization operator Design and tethered drone speed optimization operator Similarly, it can be expressed as follows:

[0124]

[0125]

[0126] Individuals before and after optimization are retained in the current population. The next generation of individuals is selected through a tournament. Due to the characteristics of the tournament selection, both types of individuals theoretically have the possibility of entering the next generation of the population. This retention mechanism can accelerate the convergence of individuals in the population to a certain extent, but it also preserves a certain degree of diversity evolutionary potential.

[0127] The foregoing section detailed a multi-constraint, multi-objective genetic algorithm for air-ground collaborative trajectory planning in power line inspection. This algorithm can search for the optimal collaborative operation trajectory under multiple constraints and objectives. However, in actual power line inspection air-ground collaborative operations, environmental fluctuations and changes occur, and tethered drones and unmanned vehicles cannot accurately execute predetermined trajectories, leading to accumulated trajectory deviations. Therefore, the following real-time sliding window planning module is designed (see...). Figure 3 The current local paths of tethered drones and unmanned vehicles are replanned to ensure that constraints and collision avoidance requirements are met.

[0128] In a preferred example, the real-time sliding window planning module performs the following steps:

[0129] Step 301: Obtain the optimal individual gene encoding for the multi-constraint, multi-objective genetic algorithm;

[0130] Step 302: Obtain the gene codes for the lengths of tethered drones, unmanned vessels, and winch cables based on GCN (gene coding sequence number initially set to 0);

[0131] Step 303: The trajectory safety monitoring module monitors environmental changes and subsequent trajectories to be executed in real time, and determines whether local correction is needed. If no local correction is needed, it will directly jump to step 310 for execution; if local correction is needed, it will execute step 304.

[0132] Step 304: Extract the local trajectory segments that need to be replanned;

[0133] Step 305: Time taken for a local segment calculate;

[0134] Step 306: Replan the local trajectory of the unmanned vessel using the A* algorithm;

[0135] Step 307: Winch accessibility assessment. Check whether the requirements for winch speed and cable length in the replanned trajectory exceed the maximum winch speed and maximum cable length. If they exceed, the winch is unreachable, proceed to step 308. If they do not exceed, the winch is reachable, and proceed to step 309.

[0136] Step 308: Based on the speed adjustment module, reduce the tethered UAV's travel speed and restart local planning, then jump to step 305;

[0137] Step 309: Update the locally adjusted new gene codes into the optimal individual to generate a new current optimal individual.

[0138] Step 310: The gene coding sequence extractor obtains the gene coding of tethered UAVs, unmanned ships, and winch cable lengths based on GCN (gene coding sequence number) and delivers it to the deviation correction module;

[0139] Step 311: The offset correction module performs deviations based on the current position and speed of the tethered UAV, unmanned vehicle, and winch, calculates the correction amount, and adds the gene code obtained in step 310 to generate the final gene code control amount to be executed.

[0140] Step 312: The tethered UAV trajectory tracking module, the unmanned vehicle trajectory tracking module, and the winch cable length following control module execute the gene-coded control quantity;

[0141] Step 313: GCN (gene coding number)++, jump to step 302 and repeat.

[0142] This application also provides a computer-readable storage medium storing a computer program that can be used to execute the steps of the above-described power line inspection air-ground cooperative trajectory planning method.

[0143] This application also provides a computer device. At the hardware level, this computer device includes a processor, an internal bus, a network interface, memory, and non-volatile memory, and may also include other hardware required for various operations. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the steps of the aforementioned power line inspection air-ground cooperative trajectory planning method.

[0144] Those skilled in the art will understand that embodiments of the present invention can be provided as methods or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This invention is described with reference to flowchart illustrations and / or block diagrams of methods and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] It should be noted that the above specific embodiments enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the patent of the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An air-ground cooperative path planning method based on genetic algorithm and sliding window optimization, characterized in that: The method comprises the following steps: Step 1) constructing a multi-constraint multi-objective optimization model for the cooperative path planning of the tethered unmanned aerial vehicle and the unmanned vehicle, defining gene coding variables, the gene coding variables including three-dimensional path point coordinates and speed values of the tethered unmanned aerial vehicle, two-dimensional plane trajectory coordinates of the unmanned vehicle, and cable length information of the tethering winch; Step 2) setting constraint conditions of the multi-constraint multi-objective optimization model, including path constraints of the tethered unmanned aerial vehicle, speed constraints, collision constraints of the unmanned vehicle, speed constraints, motion rotation angle constraints, and winch cable length constraints and cable length speed constraints; Step 3) setting multi-objective optimization functions of the multi-constraint multi-objective optimization model, including the shortest time for coupling path links, the minimum energy consumption of the tethered unmanned aerial vehicle and the unmanned vehicle, the optimal trajectory smoothness, the minimum collision risk of the unmanned vehicle, the minimum number of winch cable length winding and unwinding, and the minimum average cable length, and the multi-objective is normalized by using a weight coefficient variation method, and an individual fitness function is constructed; Step 4) solving the multi-constraint multi-objective optimization model by using an improved genetic algorithm, including generating an initial population based on the constraint conditions, calculating individual fitness, selecting by using a tournament selection method, performing cross operation by using an adaptive multi-point cross method, performing mutation operation by using a Gaussian mutation method based on the constraint conditions, and performing sliding window optimization on individual gene coding after each generation evolution, and finally outputting a cooperative path meeting all constraint conditions and having optimal fitness.

2. The method of claim 1, wherein: Gene encoding variable in step 1 Encoding tethered UAV flight path using hierarchical coupling structure Encoding unmanned vehicle flight path Encoding winch cable length Packaged as a unified node, and the position of the tethered UAV on the predetermined flight path line As a common reference.

3. The method of claim 1, wherein: In step 2), the collision constraint of the unmanned vehicle adopts a rasterized electronic map, and obstacles and safety radii are combined into forbidden grids, and the number of forbidden grids crossed by the unmanned vehicle trajectory is counted in real time in the gene decoding stage.

4. The method of claim 1, wherein: The adaptive multi-point crossover method in step 4) selects the maximum number of crossover points in the early stage of evolution ≥ 8 to increase diversity, and decreases to the minimum number of crossover points in the later stage according to the linear decreasing strategy ≤ 4.

5. The method of claim 2, wherein: The Gaussian variation in step 4) is performed in 、 、 The mutation operation is performed in a hierarchical progressive manner.

6. The method of any one of claims 1 to 5, characterized in that: Step 5) is further included, in actual execution, real-time monitoring of environmental and trajectory deviations, and re-planning and dynamic adjustment of local trajectories by using sliding window optimization, to ensure real-time feasibility, safety and optimality of the cooperative path of the tethered unmanned aerial vehicle and the unmanned vehicle.

7. The method of claim 6, wherein: The multi-objective optimization function in step 3) adopts a dynamic weight strategy after normalization: a preset fixed weight vector is used to calculate the degree of optimization target bias in the offline evolution stage; and in the online sliding window stage, the weight is adjusted online according to real-time deviation and remaining cable length margin, so that the energy consumption and safety weight increase with the increase of real-time deviation.

8. The method of claim 6, wherein: The sliding window optimization in step 5) is specifically: monitoring actual deviations and environmental changes, rolling and intercepting unexecuted path segments according to node numbers, calculating a local path of the unmanned vehicle by using the A-star algorithm first, and then verifying whether the winch speed and cable length are out of limits; if out of limits, the unmanned vehicle speed is reduced for re-planning, otherwise the modified segment is written back to the gene chain and output control instructions after adding a deviation correction amount, and then the node number is incremented, and the cycle is executed until the task is completed.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1-8.

10. A computer device, comprising: The computer program is stored in the memory and can be run on the processor, and the processor implements the method in any one of claims 1-8 when executing the program.

Images