Power inspection drone autopilot deployment and scheduling method, system, equipment and medium

Abstract

The present invention relates to the field of drone scheduling technology, and provides a method, system, device, and medium for deploying and scheduling power inspection drone autopilots. The method comprises the following steps: a power inspection dispatch center issues power inspection tasks; each drone autopilot calculates an estimated task execution cost based on a task execution cost evaluation function according to the power inspection task, and sends the estimated task execution cost to the power inspection dispatch center. The power inspection dispatch center compares the estimated task execution costs of all power inspection tasks and, based on the principle of minimizing task execution costs, allocates the power inspection task to a target drone autopilot, so that the drone autopilot plans a path in real time and executes the inspection task according to the power inspection task. The present invention can reasonably allocate inspection tasks based on factors such as drone autopilot status, weather changes, and geographical environment, and can adaptively optimize scheduling for emergencies. This method can not only effectively improve drone autopilot resource utilization, task execution flexibility, and inspection efficiency, but also reduce inspection costs.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) dispatching, and in particular to a method, system, equipment and medium for dispatching an autopilot of an electric power inspection UAV. Background Art

[0002] With the rapid development of drone technology, drones have been widely used in power inspections, gradually replacing manual inspections. However, existing drone deployment and scheduling methods often use static scheduling strategies, which are unable to dynamically adjust inspection tasks based on factors such as drone status, weather changes, and geographical environment. This not only leads to low drone inspection efficiency, but also fails to achieve real-time scheduling and task optimization for emergencies, resulting in underutilized drone resources. This can easily lead to problems such as low battery levels and overlapping tasks during inspections, making it impossible to achieve optimal resource allocation and maximize inspection results, while also resulting in excessively high inspection costs. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for deploying and scheduling autopilots of power inspection UAVs. Through an inspection task allocation mechanism that comprehensively considers the loss cost, risk cost, time cost and task priority when the UAV performs the inspection task to evaluate the task execution cost, combined with an inspection path obstacle avoidance mechanism designed based on an improved A* algorithm, it can not only ensure the reasonable allocation of inspection tasks, but also realize real-time dynamic scheduling optimization for emergency situations, which can not only effectively improve the resource utilization rate of the UAV autopilot, the flexibility of task execution and the inspection efficiency, but also reduce the inspection cost.

[0004] In order to achieve the above objectives, a method, system, device and medium for deploying and scheduling an autopilot for power inspection drones are provided.

[0005] In a first aspect, an embodiment of the present invention provides a method for deploying and scheduling a power inspection UAV autopilot, which is applied to a power inspection dispatch center to deploy and schedule a plurality of UAV autopilots. The method includes the following steps:

[0006] In response to the power inspection task issued by the power inspection dispatch center, each UAV autopilot calculates the corresponding task execution estimated cost based on the power inspection task and a task execution cost evaluation function, and sends the task execution estimated cost to the power inspection dispatch center; the task execution cost evaluation function is obtained based on the loss cost, risk cost, time cost and task priority of the task execution;

[0007] Based on the principle of minimizing task execution costs, the power inspection dispatch center allocates the power inspection task to a target UAV autopilot according to the comparison results of all task execution estimated costs corresponding to the power inspection task; the target UAV autopilot is the UAV autopilot corresponding to the minimum task execution estimated cost;

[0008] In response to receiving the power inspection task, the target UAV autopilot plans a path in real time to perform the power inspection task.

[0009] Furthermore, the loss cost includes electricity cost and equipment depreciation cost; the steps of obtaining the loss cost include:

[0010] Obtaining the flight power of the UAV autopilot based on the accumulated values of the hovering power, climbing power, and power to overcome air resistance of the UAV autopilot, and obtaining the electricity cost based on the flight power of the UAV autopilot, the total inspection flight time of the UAV autopilot, and the unit electricity price;

[0011] The task execution life consumption is obtained based on the task complexity score coefficient, the UAV autopilot task load, the UAV autopilot task flight altitude, and the total inspection flight time of the UAV autopilot. The equipment depreciation cost is obtained based on the task execution life consumption, the UAV autopilot design life, and the UAV autopilot purchase cost. The equipment depreciation cost is expressed as:

[0012]

[0013]

[0014] Where, represents the depreciation cost of equipment; represents the purchase cost of the drone autopilot; Indicates the design life of the UAV autopilot; Indicates the task execution life consumption; represents the task complexity rating coefficient; Indicates the UAV autopilot mission load, Indicates the average flight altitude of the UAV autopilot mission; Indicates the total duration of the drone's autopilot inspection flight; and They represent correction coefficients respectively;

[0015] The loss cost is obtained according to the accumulated value of the electricity cost and the equipment depreciation cost.

[0016] Furthermore, the risk cost includes bad weather risk, altitude risk, and signal obstruction risk; and the steps of obtaining the risk cost include:

[0017] Acquire real-time weather data for mission execution, and perform UAV autopilot failure prediction based on the real-time weather data for mission execution and a pre-built failure probability prediction model to obtain the severe weather risk;

[0018] Obtaining geographic data of the mission execution area, and obtaining the altitude risk based on the geographic data of the mission execution area and the maximum allowable flight altitude of the UAV autopilot;

[0019] Communication signal coverage data of the mission execution area is obtained, and loss of connection risk prediction is performed based on the communication signal coverage data of the mission execution area and a pre-built loss of connection probability prediction model to obtain the signal blocking risk.

[0020] Furthermore, the time cost includes the total flight time of the UAV autopilot inspection and the total time of the UAV autopilot inspection to replenish power; the steps for obtaining the time cost include:

[0021] Obtaining an optimal inspection path based on a path planning algorithm, and obtaining the total inspection flight duration of the UAV autopilot based on the optimal inspection path and the flight speed of the UAV autopilot; the flight speed of the UAV autopilot is obtained by correcting the maximum flight speed of the UAV autopilot based on weather conditions and load status;

[0022] The amount of power required for task execution is obtained based on the total duration of the UAV autopilot inspection flight, the maximum battery capacity of the UAV autopilot, and the unit flight energy consumption of the UAV autopilot. The total duration of the UAV autopilot inspection power replenishment is obtained based on the amount of power required for task execution and the average charging power of the charging station.

[0023] The time cost is obtained according to the accumulated value of the total flight time of the UAV autopilot inspection and the total time of the UAV autopilot inspection to replenish power.

[0024] Furthermore, the target UAV autopilot plans a path in real time to perform the power inspection task, including the following steps:

[0025] When the target UAV autopilot detects a path obstacle, an obstacle avoidance path is generated based on the improved A* algorithm according to the obstacle information of the path obstacle, and the task execution cost after obstacle avoidance is evaluated based on the obstacle avoidance path; the obstacle information includes obstacle type, obstacle position and obstacle speed; the cost function of the improved A* algorithm includes actual cost, heuristic estimated cost and obstacle risk cost; the obstacle risk cost is expressed as:

[0026]

[0027] in, Indicates the current path node The corresponding obstacle risk cost; Indicates the current path node Minimum distance to obstacles; Indicates the current path node The corresponding obstacle speed; and Indicates the distance influence weight and speed influence weight;

[0028] According to the task execution cost after obstacle avoidance, the obstacle information is sent to the power inspection and dispatching center, so that the power inspection and dispatching center decides whether the target UAV autopilot should avoid the obstacle and continue to perform the task based on the obstacle information; the obstacle information includes the current position information of the UAV autopilot, the task destination position and the task execution cost after obstacle avoidance.

[0029] Furthermore, the step of the power inspection and dispatching center deciding whether the target UAV autopilot should avoid the obstacle and continue to perform the mission according to the obstacle information includes:

[0030] The power inspection and dispatching center issues a new inspection task based on the obstacle information, and compares the estimated execution cost of the new inspection task fed back by the drone autopilot with the post-obstacle avoidance task execution cost in the obstacle information;

[0031] When the task execution cost after the obstacle avoidance is the minimum, notifying the target UAV autopilot to continue executing the power inspection task based on the obstacle avoidance path;

[0032] When the task execution cost after obstacle avoidance is not the minimum value, the new inspection task is assigned to the UAV autopilot corresponding to the minimum value, and the target UAV autopilot is notified to exit the inspection task.

[0033] Furthermore, the method further comprises:

[0034] When the power inspection task is completed, the target UAV autopilot generates the actual cost of the task execution of the power inspection task, and optimizes and adjusts the weight coefficient of each cost in the task execution cost evaluation function based on the deviation between the actual cost of each item in the actual cost of the task execution and the estimated cost of the corresponding item in the estimated cost of the task execution.

[0035] In a second aspect, an embodiment of the present invention provides a system for deploying and dispatching a power inspection UAV autopilot, the system comprising a power inspection dispatch center and a plurality of UAV autopilots;

[0036] The power inspection dispatch center is used to issue power inspection tasks, receive task execution estimated costs fed back by various UAV autopilots, and, based on the comparison results of all task execution estimated costs corresponding to the power inspection tasks, assign the power inspection tasks to target UAV autopilots based on the principle of minimizing task execution costs; the target UAV autopilot is the UAV autopilot corresponding to the minimum task execution estimated cost;

[0037] The UAV autopilot is used to calculate the corresponding task execution estimated cost based on the task execution cost evaluation function according to the power inspection task issued by the power inspection dispatching center, and send the task execution estimated cost to the power inspection dispatching center; the task execution cost evaluation function is obtained based on the loss cost, risk cost, time cost and task priority of the task execution; it is also used to plan the path in real time according to the power inspection task assigned by the power inspection dispatching center to execute the power inspection task.

[0038] In a third aspect, an embodiment of the present invention further provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0039] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0040] The present invention provides a method, system, computer device, and storage medium for deploying and scheduling power inspection drone autopilots. The method enables a power inspection dispatch center to issue power inspection tasks. Each drone autopilot, based on the power inspection task, calculates an estimated task execution cost based on a task execution cost evaluation function and sends the calculated estimated task execution cost to the power inspection dispatch center. The power inspection dispatch center then compares the estimated task execution costs of all tasks corresponding to the power inspection task and, based on the principle of minimizing task execution costs, assigns the power inspection task to a target drone autopilot. The target drone autopilot then plans a real-time path to execute the power inspection task based on the received power inspection task. Compared to existing technologies, this method for deploying and scheduling power inspection drone autopilots can rationally allocate inspection tasks based on factors such as drone status, weather changes, and the geographical environment. It can also adaptively optimize scheduling for emergencies, effectively improving drone autopilot resource utilization, task execution flexibility, and inspection efficiency while also reducing inspection costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 1 is a flow chart of a method for deploying and scheduling an autopilot for electric power inspection UAVs according to an embodiment of the present invention;

[0042] Figure 2 This is another flowchart of the method for deploying and scheduling an autopilot for electric power inspection UAVs according to an embodiment of the present invention;

[0043] Figure 3 This is a structural diagram of a deployment and scheduling system for an electric power inspection UAV autopilot according to an embodiment of the present invention;

[0044] Figure 4 1 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and beneficial effects of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the embodiments described below are part of the embodiments of the present invention and are only used to illustrate the present invention, but are not used to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] The method for deploying and scheduling autopilots for power inspection drones provided by this invention can be understood as a technical solution that addresses the current situation where existing methods for deploying and scheduling autopilots for power inspection drones struggle to optimally allocate drone resources and maximize inspection mission effectiveness. This solution rationally allocates inspection missions based on factors such as drone status, weather changes, and the geographical environment, while also dynamically adjusting scheduling strategies in real time to address emergencies. The following examples will provide a detailed explanation of the method for deploying and scheduling autopilots for power inspection drones provided by this invention.

[0047] In one embodiment, Figure 1 As shown, a method for deploying and scheduling power inspection drone autopilots is provided, which is applied to the deployment and scheduling of several drone autopilots by the power inspection dispatching center. The power inspection dispatching center maintains communication with all drone autopilots. The power inspection dispatching center is responsible for issuing inspection tasks according to actual power inspection needs. The drone autopilots that can participate in the inspection tasks provide an estimated cost of task execution to bid for the inspection tasks. Each drone autopilot generates an estimated cost of task execution by estimating the loss cost, risk cost, time cost and task priority during the execution of the inspection task to participate in the inspection task bidding. After receiving the inspection task confirmed by the power inspection dispatching center, the route is planned in real time to execute the corresponding inspection task. The specific method for deploying and scheduling power inspection drone autopilots includes the following steps:

[0048] S11. In response to the power inspection task released by the power inspection dispatching center, each UAV autopilot calculates the corresponding task execution estimated cost based on the task execution cost evaluation function according to the power inspection task, and sends the task execution estimated cost to the power inspection dispatching center.

[0049] In actual applications, the power inspection dispatch center generates corresponding power inspection tasks based on power inspection needs and publishes them to a bidding task pool shared by all drone autopilots. All drone autopilots that meet the bidding conditions can receive the inspection task information. To facilitate automatic analysis of the estimated cost of task execution by each drone autopilot, the task information for the corresponding power inspection task may include the inspection time, target inspection area location, and corresponding inspection items. After receiving the bid-worthy power inspection task, each drone autopilot can analyze the task information to obtain the corresponding estimated cost of task execution and feedback it to the power inspection dispatch center to update the bidding information in the bidding task pool.

[0050] In this embodiment, the estimated cost of task execution reported by each drone autopilot is used as the main basis for the power inspection dispatching center to allocate inspection tasks. In order to ensure the comprehensiveness and reliability of the analysis of the estimated cost of task execution, this embodiment takes into account various factors such as the drone autopilot status, weather changes and geographical environment, and preferably designs a task execution cost evaluation function based on the loss cost, risk cost, time cost and task priority of task execution.

[0051] Taking into account that in actual applications, each time the drone autopilot performs an inspection task, it consumes a certain amount of electricity and there will be a certain degree of depreciation. In order to ensure the comprehensiveness of the loss cost analysis, this embodiment preferably sets the loss cost to include electricity cost and equipment depreciation cost. The electricity cost can be understood as the cost of electricity consumed by the drone autopilot to perform the inspection task, and the equipment depreciation cost can be understood as the equipment depreciation loss caused by the drone autopilot performing the inspection task. Specifically, the steps for obtaining the loss cost include:

[0052] The flight power of the UAV autopilot is obtained based on the accumulated values of the hovering power, climbing power, and power to overcome air resistance of the UAV autopilot. The electricity cost is obtained based on the flight power of the UAV autopilot, the total inspection flight time of the UAV autopilot, and the unit electricity price. The hovering power can be calculated based on the load condition of the UAV autopilot and is expressed as:

[0053]

[0054] Where, and They represent the UAV autopilot load and the corresponding hovering power coefficient respectively, and the hovering power coefficient can be set according to actual application requirements; Indicates hovering power.

[0055] Considering that the climbing power of the UAV autopilot is related to the altitude change and the gravitational potential energy of the UAV autopilot, it can be expressed as:

[0056]

[0057] Where, Indicates the total mass of the UAV autopilot, including the payload weight and the body weight; Indicates the acceleration due to gravity, take 9.8m / s 2 ; Indicates the average flight altitude; Indicates the total flight time; Indicates climb power.

[0058] Considering that the air resistance that the UAV autopilot is subjected to during flight is related to the flight speed and the drag coefficient, the climbing power can be expressed as:

[0059]

[0060] Where, Indicates the power to overcome air resistance; 、 、 and They represent air density, drag coefficient, frontal area of the UAV autopilot and flight speed of the UAV autopilot respectively.

[0061] After obtaining the hovering power, climbing power, and air resistance power of the UAV autopilot through the above method, the required UAV autopilot flight power can be obtained by adding them together. The corresponding electricity cost can be calculated using the following formula:

[0062]

[0063] Where, represents the electricity cost; Indicates the unit electricity price; Indicates the flight power of the drone autopilot; Indicates the total duration of the drone's autopilot inspection flight.

[0064] The task execution life consumption is obtained based on the task complexity score coefficient, the UAV autopilot task load, the UAV autopilot task flight altitude, and the total inspection flight time of the UAV autopilot. The equipment depreciation cost is obtained based on the task execution life consumption, the UAV autopilot design life, and the UAV autopilot purchase cost. The task execution life consumption can be understood as the actual consumption of life by a single inspection task (in hours), preferably expressed as:

[0065]

[0066] Where, Indicates the task execution life consumption; Indicates the task complexity scoring coefficient. The more complex the task, the higher the corresponding score. This can be obtained by comprehensive analysis based on the distance between the inspection area location in the task information and the UAV autopilot, the number of inspection items, and the preset operation difficulty corresponding to each inspection item. In principle, the task complexity scoring coefficient is proportional to the distance, the number of inspection items, and the difficulty of the inspection item operation. Represents the UAV autopilot mission load; Indicates the average flight altitude of the UAV autopilot mission; Indicates the total duration of the UAV autopilot inspection flight, which can be determined based on the length of the inspection path generated based on the inspection area location in the mission information; and They respectively represent correction coefficients, which measure the effects of flight altitude and flight time on lifespan, and can be obtained based on fitting of relevant historical data and are not specifically limited here.

[0067] After obtaining the task execution life consumption through the above method steps, the depreciation cost of the equipment corresponding to the task can be calculated using the following expression:

[0068]

[0069] Where, represents the depreciation cost of equipment; represents the purchase cost of the drone autopilot; Indicates the design life of the UAV autopilot; Indicates the task execution life consumption.

[0070] The loss cost is obtained based on the accumulated value of the electricity cost and the equipment depreciation cost; that is, the loss cost is expressed as:

[0071]

[0072] Where, Represents the loss cost of task execution; and Expressed as electricity cost and equipment depreciation cost respectively.

[0073] The risk cost in this embodiment can be understood as the environmental risk that the UAV autopilot may face when performing power inspection tasks. Considering that environmental risks include bad weather, altitude, and signal obstruction, the risk cost is preferably set to include bad weather risk, altitude risk, and signal obstruction risk. Specifically, the steps for obtaining the risk cost include:

[0074] Real-time weather data for task execution is obtained, and UAV autopilot failure prediction is performed based on the real-time weather data for task execution and a pre-built failure probability prediction model to obtain the severe weather risk; wherein, the real-time weather data for task execution can be understood as the weather data corresponding to the inspection time in the task information corresponding to the power inspection task, obtained through the meteorological platform, including information such as wind speed, precipitation, temperature and thunderstorm index; considering that in actual applications, when the wind speed is high, the UAV autopilot is prone to wind disturbance instability, resulting in flight path deviation or even crash; when the precipitation is high, rain may affect the normal operation of the UAV autopilot sensor, and temperature and thunderstorms may also affect the normal operation of the UAV autopilot sensor, the corresponding failure probability prediction model can be understood as a machine learning model constructed based on training of historical data of UAV autopilot flight failure probability under different weather data conditions, which can calculate the potential failure probability of the UAV autopilot under different weather conditions. It can be used to reliably determine the risk of performing inspection tasks under the current mission weather conditions to ensure the efficiency and accuracy of severe weather risk assessment.

[0075] Obtain the geographic data of the task execution area, and obtain the altitude risk based on the geographic data of the task execution area and the maximum allowable flight altitude of the UAV autopilot; wherein, the geographic data of the task execution area can be understood as the terrain data obtained by querying the shared geographic information system based on the target inspection area location in the task information corresponding to the power inspection task, and may include the terrain height information of the target inspection area; wherein, the maximum allowable flight altitude of the UAV autopilot can be understood as the flight altitude limit determined based on the production design of the UAV autopilot. Different UAV autopilots have different corresponding maximum allowable flight altitudes, which are not specifically limited here. The corresponding altitude risk can be understood as the feasibility of the UAV autopilot to perform tasks in different altitude areas, which is obtained by considering factors such as the UAV autopilot's flight altitude being unable to meet the flight requirements of complex terrain and the low air density in high altitude areas affecting the lift and battery life of the UAV autopilot. In actual applications, multiple allowable flight altitude ranges can be set according to the maximum allowable flight altitude of the drone autopilot, and a corresponding risk score can be set for each allowable flight altitude range based on the principle that the lower the altitude, the lower the risk score. The corresponding altitude risk can be determined by judging which allowable flight altitude range the terrain height of the target inspection area belongs to.

[0076] Acquire communication signal coverage data for the task execution area, and perform a loss of connection risk prediction based on the communication signal coverage data and a pre-built loss of connection probability prediction model to obtain the signal obstruction risk. The communication signal coverage data for the task execution area can be understood as taking into account that in actual applications, communication signals in areas such as high-rise buildings, valleys, and tunnels may be weakened due to obstruction, resulting in communication interruption or data loss. Furthermore, when there are large signal blind spots in the task path, the inspection task may not be completed and may even face the risk of loss of connection. The mobile communication network signal coverage obtained based on the target inspection area location in the task information corresponding to the power inspection task may include the signal strength distribution of 5G, 4G, or dedicated wireless networks in the target inspection area, and is used to assess the reliability of data transmission and remote control. The corresponding loss of connection probability prediction model can be understood as a neural network model trained and constructed based on historical data collected on the communication status of the drone autopilot under different communication signal coverage conditions. It can output a corresponding signal obstruction risk probability value based on the actual input communication signal coverage data to ensure the efficiency and accuracy of signal obstruction risk assessment.

[0077] The time cost in this embodiment can be understood as the total time required for the drone autopilot to execute the inspection task based on the target inspection area location in the task information and its own current location, including the total inspection flight time of the drone autopilot and the total inspection battery replenishment time of the drone autopilot. Specifically, the steps for obtaining the time cost include:

[0078] An optimal inspection path is obtained based on a path planning algorithm, and the total inspection flight duration of the UAV autopilot is obtained based on the optimal inspection path and the flight speed of the UAV autopilot. The path planning algorithm can be an existing shortest path planning algorithm, and the corresponding optimal inspection path can be understood as the shortest path obtained by the path planning algorithm based on the location of the target inspection area and the current location of the UAV autopilot. The specific acquisition method can be implemented with reference to relevant existing technologies. The UAV autopilot flight speed is obtained by correcting the maximum flight speed of the UAV autopilot based on meteorological conditions and load status. The specific implementation process may include obtaining a flight speed correction coefficient (a value greater than 0 and less than 1) or a flight speed correction value (a negative value whose absolute value is less than the maximum flight speed) based on a comprehensive analysis of the meteorological conditions and load status during the inspection mission. The desired UAV autopilot flight speed is then determined by multiplying the flight speed correction coefficient by the maximum flight speed of the UAV autopilot, or by summing the flight speed correction value and the maximum flight speed of the UAV autopilot. After determining the flight speed of the UAV autopilot, the required total UAV autopilot inspection flight time can be obtained by dividing the route length of the optimal inspection path by the flight speed of the UAV autopilot.

[0079] According to the total inspection flight time of the drone autopilot, the maximum battery capacity of the drone autopilot and the unit flight energy consumption of the drone autopilot, the required amount of replenishment for task execution is obtained, and according to the required amount of replenishment for task execution and the average charging power of the charging station, the total inspection replenishment time of the drone autopilot is obtained; wherein, the route length of the optimal inspection path varies due to the different locations of different drone autopilots, and the maximum battery capacity of the drone autopilot also varies due to the type or status of the drone autopilot; the corresponding unit flight energy consumption of the drone autopilot can be understood as the flight power consumption of the drone autopilot per unit time during the journey, which may vary due to the type or status of the drone autopilot and can be set based on the historical flight experience of the drone autopilot.

[0080] The amount of power required to perform the task in this embodiment can be understood as the difference between the total power required to perform the task and the existing power of the drone autopilot, wherein the total power required to perform the task can be obtained based on the product of the total inspection flight time of the drone autopilot and the unit flight energy consumption of the drone autopilot; after determining the amount of power required to perform the task, the number of times the drone autopilot needs to be replenished for inspection can be calculated based on the existing power of the drone autopilot and the maximum battery capacity of the drone autopilot; then, after obtaining the single charging time based on the ratio of the maximum battery capacity of the drone autopilot to the average charging power of the charging station, the product of the single charging time and the number of times the drone autopilot needs to be replenished for inspection is used to obtain the total time the drone autopilot needs to be charged due to insufficient power during the performance of the power inspection task, that is, the total time for the drone autopilot to replenish power for inspection.

[0081] The time cost is obtained according to the accumulated value of the total flight time of the UAV autopilot inspection and the total time of the UAV autopilot inspection to replenish power.

[0082] The task priority in this embodiment is not the same for different drone autopilots participating in the auction. It can be understood as the execution priority of the power inspection task currently being auctioned by a single drone autopilot among all the tasks it participates in the auction (the order of task execution). In actual applications, the standards for evaluating the priority of inspection tasks by different drone autopilots are unified. For example, it can be determined based on the principle that the higher the urgency of the task, the higher the priority (the earlier it is executed). No specific limitation is made here.

[0083] After each UAV autopilot analyzes the current auctioned power inspection task information and obtains the corresponding loss cost, risk cost, time cost, and task priority, it can perform a weighted sum of the loss cost, risk cost, time cost, and task priority according to the preset weight coefficient to obtain the required task execution estimated cost, which is expressed as:

[0084]

[0085] Where, Indicates the estimated cost of task execution; 、 、 and They represent the loss cost, risk cost, time cost and task priority of task execution respectively; 、 、 and Represents the weight coefficient, which can be a fixed value or dynamically adjusted.

[0086] In this embodiment, the drone autopilot conducts a multi-faceted assessment of the loss cost, risk cost, time cost, and task priority based on the task information of the power inspection task, and performs a weighted fusion of the evaluation results from various aspects to determine the estimated cost of task execution. This can effectively improve the comprehensiveness and accuracy of the drone autopilot task execution cost estimate, and thus provide reliable guarantees for the power inspection dispatching center to rationally dispatch and allocate drone autopilot resources.

[0087] S12. Based on the principle of minimizing task execution costs, the power inspection dispatch center assigns the power inspection task to a target UAV autopilot based on the comparison results of all task execution estimated costs corresponding to the power inspection task; the target UAV autopilot is the UAV autopilot corresponding to the minimum task execution estimated cost. In actual applications, the power inspection dispatch center continuously monitors the task execution estimated costs fed back by the UAV autopilots in the auction task pool and sorts the bids for the task execution estimated costs in real time. When all participating UAV autopilots have completed the task execution cost feedback, the UAV autopilot corresponding to the minimum task execution estimated cost obtained in the sorting is determined as the successful bidder, completing the allocation of power inspection tasks.

[0088] S13. In response to receiving the power inspection task, the target UAV autopilot plans a route in real time to execute the power inspection task. Upon receiving the power inspection task assigned by the power inspection dispatch center, the target UAV autopilot may initiate the inspection task based on the corresponding task information and plan a route in real time to ensure safe and efficient completion of the inspection task.

[0089] Considering that in actual applications, the target UAV autopilot may encounter obstacles or lose connection while traveling to the target inspection area and performing area inspections, in order to ensure the continuous and efficient completion of power inspection tasks, this embodiment preferably designs an emergency adaptive scheduling optimization mechanism to ensure the continuity, flexibility and safety of task execution. Specifically, the target UAV autopilot plans a path in real time to perform the power inspection task, including the following steps:

[0090] When the target UAV autopilot detects a path obstacle, an obstacle avoidance path is generated based on the improved A* algorithm according to the obstacle information of the path obstacle, and the task execution cost after obstacle avoidance is evaluated based on the obstacle avoidance path; the obstacle information includes obstacle type, obstacle position and obstacle speed; wherein, the improved A* algorithm can be understood as considering that the distance and moving speed of the obstacle are risk factors affecting the UAV autopilot, and introducing them into the A* algorithm for the design of a cost function for path optimization, so as to realize dynamic optimization and adjustment of the path based on real-time perceived obstacle information, and improve the safety of the UAV autopilot during task execution. Specifically, the cost function of the improved A* algorithm includes actual cost, heuristic estimation cost and obstacle risk cost, wherein the actual cost represents the cost from the starting node to the current node The actual cost of the current node, the heuristic estimated cost The heuristic estimated cost to the target node can be calculated using the Euclidean distance formula in three-dimensional space; the obstacle risk cost is expressed as:

[0091]

[0092] in, Indicates the current path node The corresponding obstacle risk cost; Indicates the current path node The minimum distance to the obstacle. When the obstacle is dynamic, the existing relevant LSTM (Long Short-Term Memory) prediction algorithm can be used to obtain the obstacle's motion trajectory and obtain the current path node. Minimum distance to obstacles; Indicates the current path node The corresponding obstacle speed. When the obstacle is stationary, this value is 0. When the obstacle is dynamic, it can also be obtained by using the existing relevant LSTM prediction algorithm to obtain the obstacle's motion trajectory; and The distance weight and speed weight represent the impact of the distance from the drone's autopilot to the obstacle on the risk. The closer the distance, the higher the risk. The minimum distance is used as the weight, with the nearest obstacle point on the autopilot's planned path used as the basis for risk calculation. The speed weight reflects the impact of the moving speed of dynamic obstacles on the drone's obstacle avoidance. The faster the moving speed, the higher the collision risk. This applies to moving obstacles (such as birds and other drones). High-speed obstacles are more difficult to avoid and require a higher weight. Compared to the traditional A* algorithm that only considers static obstacles, the improved A* algorithm used in this embodiment can effectively ensure the safety of the drone's autopilot by sensing dynamic obstacles in real time and adjusting the path.

[0093] During the actual drone autopilot inspection process, the configured relevant sensors will detect the presence of obstacles in real time. Obstacle types include static obstacles and dynamic obstacles. Static obstacles include buildings, utility poles, and trees, while dynamic obstacles include birds and other low-altitude aircraft. All are monitored and identified in real time by the drone autopilot. If the drone autopilot encounters a temporary obstacle, it will automatically analyze the obstacle's type, location, and movement characteristics, generate an obstacle avoidance path, and perform a risk assessment. The specific steps for generating an obstacle avoidance path include:

[0094] The UAV autopilot flight environment is divided into a three-dimensional grid space. The grid unit is voxel. The center point of each voxel is represented by a three-dimensional coordinate. Representation; construct a three-dimensional grid map based on environmental information. The voxel states in the map include free space and obstacle space, where free space is marked as "0", indicating that it is passable, and obstacle space is marked as "1", indicating an impassable area; define the starting position of the UAV autopilot as the starting node , the target location is defined as the target node ; Using the neighborhood model, the neighborhood of each node includes the voxels directly adjacent to the current node; Based on the A* algorithm, an improved cost function is constructed:

[0095]

[0096]

[0097] Where, Indicates the current node The three-dimensional coordinates of 、 、 and Represents the current node The cost function from the starting node to the current node The actual cost of the current node Heuristic estimated cost to the target node and the current path node The corresponding obstacle risk cost.

[0098] The execution path planning process is as follows: first put the starting node S into the open list, set the initial cost , set the initial cost of all other nodes to infinity, and select the cost function from the open list each time Smallest node As the current node, if the current node is the target node G, end the search and enter the path backtracking step, otherwise, move the current node from the open list to the closed list; evaluate the neighbor nodes of the current node one by one, skip the nodes that are already in the closed list, and calculate the cost of each neighbor node. If the neighbor node is not in the open list, or the new cost is less than its current cost, update its cost and record the parent node. If the position or speed of the dynamic obstacle changes, update the dynamic obstacle risk cost in real time and recalculate the path. Repeat the above steps until the target node is found or the open list is empty (the path does not exist). Starting from the target node G, backtrack to the starting node S according to the parent node recorded by each node to obtain the complete path.

[0099] After the target UAV autopilot generates an obstacle avoidance path based on the improved A* algorithm, the task execution estimated cost evaluation method given above can be used to obtain the task execution cost after obstacle avoidance based on the obstacle avoidance path. Based on the task execution cost after obstacle avoidance, the current position information of the UAV autopilot, and the task destination location, obstacle information is generated and fed back to the power inspection and dispatching center in real time, which decides whether to continue the current inspection task.

[0100] According to the task execution cost after obstacle avoidance, the obstacle information is sent to the power inspection and dispatching center, so that the power inspection and dispatching center decides whether the target UAV autopilot should avoid the obstacle and continue to perform the task based on the obstacle information; the obstacle information includes the current position information of the UAV autopilot, the task destination position and the task execution cost after obstacle avoidance.

[0101] In order to ensure the reliability of the power dispatching center's decision on whether the target UAV autopilot should avoid obstacles and continue to perform the task based on the obstacle information, and to make full use of the UAV autopilot resources to ensure the flexibility and efficiency of the inspection task execution, in this embodiment, after the power inspection dispatching center receives the obstacle information sent by the target UAV autopilot, it will preferably issue a new inspection task based on the obstacle information to determine whether there is a more suitable UAV autopilot to replace the target UAV autopilot to perform the current inspection task; specifically, the step of the power inspection dispatching center deciding whether the target UAV autopilot should avoid obstacles and continue to perform the task based on the obstacle information includes:

[0102] The power inspection and dispatching center issues a new inspection task based on the obstacle information, and compares the estimated execution cost of the new inspection task received from the drone autopilot with the task execution cost after obstacle avoidance in the obstacle information; wherein, the estimated execution cost of each new inspection task can also be obtained based on the task execution cost evaluation function. The specific acquisition process can refer to the relevant description of the aforementioned task execution estimated cost, which will not be repeated here.

[0103] When the post-obstacle avoidance task execution cost is the minimum, the target UAV autopilot is notified to continue executing the power inspection task based on the obstacle avoidance path; that is, the post-obstacle avoidance task execution cost of the target UAV autopilot is still the minimum cost compared with the estimated cost of executing the new inspection task fed back by other UAV autopilots, so it will continue to execute the task by avoiding obstacles.

[0104] When the post-obstacle avoidance task execution cost is not the minimum value, the new inspection task is assigned to the UAV autopilot corresponding to the minimum value, and the target UAV autopilot is notified to exit the inspection task; that is, the post-obstacle avoidance task execution cost of the target UAV autopilot is not the minimum cost compared with the new inspection task execution estimated cost fed back by other UAV autopilots, then the power inspection dispatching center assigns the new inspection task to the UAV autopilot with the minimum new inspection task execution estimated cost, which takes over the target UAV autopilot to perform the inspection task, and the target UAV autopilot exits the inspection task and returns to the standby state to prepare for the next inspection task.

[0105] In addition, if a drone autopilot suddenly fails or loses connection during the inspection mission, the power inspection dispatching center can also obtain other drone autopilots that can take over the task based on the drone autopilot's last location information and the mission destination. It will give priority to other drone autopilots near the faulty drone autopilot or the lost drone autopilot to relay the remaining tasks, and synchronize the relevant inspection mission data to the relay drone autopilot to achieve seamless connection of inspection mission succession.

[0106] The embodiment of the present application provides a technical solution in which a power inspection task is issued by a power inspection and dispatching center, and each UAV autopilot calculates the corresponding task execution estimated cost based on the task execution cost evaluation function according to the power inspection task and sends it to the power inspection and dispatching center. The power inspection and dispatching center allocates the power inspection task to a target UAV autopilot based on the principle of minimizing the task execution cost according to the comparison result of all task execution estimated costs corresponding to the power inspection task, and then the target UAV autopilot plans a path in real time according to the received power inspection task to execute the power inspection task. The UAV autopilot deployment and scheduling mechanism can reasonably allocate inspection tasks based on factors such as the UAV autopilot status, weather changes, and geographical environment, and realize adaptive scheduling optimization of inspection tasks for emergencies. This can not only effectively improve the resource utilization rate and inspection efficiency of UAV autopilots, but also ensure the continuity and flexibility of inspection task execution, and effectively reduce inspection costs.

[0107] In addition, in order to better improve the accuracy of the estimated cost evaluation of task execution and provide reliable guidance for the subsequent power inspection task bidding, this embodiment preferably corrects the task execution cost evaluation function based on the error feedback mechanism; specifically, Figure 2As shown, the method further includes:

[0108] S14. When the power inspection task is completed, the target UAV autopilot generates the actual cost of executing the power inspection task and optimizes and adjusts the weight coefficients of each cost in the task execution cost evaluation function based on the deviation between the actual cost of each item in the task execution actual cost and the estimated cost of the corresponding item in the task execution estimated cost. That is, after the power inspection task is completed, the target UAV autopilot will calculate the various costs consumed in executing the inspection task and compare and analyze them with the corresponding task execution estimated cost. If the deviation of a cost item is large (exceeding a preset deviation threshold), the weight coefficient in the corresponding task execution cost evaluation function will be automatically adjusted according to the following formula:

[0109]

[0110] Where, and They represent the current weight coefficient and the revised weight coefficient of the i-th cost respectively; and They represent the estimated value and actual value corresponding to the i-th cost respectively; Represents the learning rate, which can be set to a fixed value or optimized based on the reinforcement learning method to improve the reliability of the cost weight coefficient optimization. For example, the state space can be defined based on the parameters and task priorities required for the actual cost calculation collected during the task execution. , Correction factors used in calculating equipment depreciation costs and , the hovering power coefficient used in electricity cost calculation The action space is defined by equal coefficients, and reinforcement learning is performed based on the following reward function designed by comprehensive analysis of the task execution cost prediction error and execution efficiency after the task is completed. This function updates the task execution cost evaluation function in real time and improves the accuracy of subsequent inspection task execution cost evaluation:

[0111]

[0112] Where, Represents the reward value; and They represent the estimated cost of task execution and the actual cost of task execution respectively; represents the mean absolute error function; and Represent the actual execution time and expected execution time of the task respectively; Indicates the efficiency factor constant, which can be set according to actual application requirements.

[0113] It should be noted that after the inspection mission is completed, the drone autopilot will transmit the actual consumption cost of the power inspection, which it has calculated, back to the power inspection dispatch center to complete the task settlement. At the same time, the power inspection dispatch center will share the actual cost-related data collected from all drone autopilots in various inspection missions within the drone autopilot cluster. Each drone autopilot can obtain the inspection mission execution data of other drone autopilots to optimize and adjust its own task execution cost evaluation function. This allows each drone autopilot to optimize the cost evaluation function based on collective experience, effectively improving the accuracy of cost evaluation. In addition to adjusting the weighting coefficients of loss cost, risk cost, and time cost, the optimization and adjustment of the task execution cost evaluation function can also update and adjust the models and parameters involved in the loss cost and risk cost evaluation based on regression analysis methods to maximize the accuracy of the estimated task execution cost.

[0114] It should be noted that although the steps in the above flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders.

[0115] In one embodiment, Figure 3 As shown, a power inspection UAV autopilot deployment and scheduling system is provided, which includes a power inspection and scheduling center and several UAV autopilots;

[0116] The power inspection dispatch center 1 is used to issue power inspection tasks, receive task execution estimated costs fed back by various UAV autopilots, and, based on the comparison results of all task execution estimated costs corresponding to the power inspection tasks, assign the power inspection tasks to target UAV autopilots based on the principle of minimizing task execution costs; the target UAV autopilot is the UAV autopilot corresponding to the minimum task execution estimated cost;

[0117] The UAV autopilot 2 is used to calculate the corresponding task execution estimated cost based on the task execution cost evaluation function according to the power inspection task issued by the power inspection dispatching center, and send the task execution estimated cost to the power inspection dispatching center; the task execution cost evaluation function is obtained based on the loss cost, risk cost, time cost and task priority of the task execution; it is also used to plan the path in real time according to the power inspection task assigned by the power inspection dispatching center to execute the power inspection task.

[0118] In one embodiment, a power inspection UAV autopilot deployment and scheduling system is provided, wherein the UAV autopilot 2 is further configured to generate the actual task execution cost of the power inspection task by the target UAV autopilot when the power inspection task is completed, and optimize and adjust the weight coefficient of each cost in the task execution cost evaluation function based on the deviation between the actual cost of each item in the task execution actual cost and the estimated cost of the corresponding item in the task execution estimated cost.

[0119] Regarding the specific limitations of the deployment and scheduling system for the autopilot of the power inspection drone, please refer to the limitations of the deployment and scheduling method for the autopilot of the power inspection drone mentioned above. The corresponding technical effects can also be obtained in the same way, so we will not go into details here. Each module in the above-mentioned deployment and scheduling system for the autopilot of the power inspection drone can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0120] Figure 4 FIG. 1 shows an internal structure diagram of a computer device in one embodiment, which may be a terminal or a server. Figure 4 As shown, the computer device includes a processor, memory, network interface, display, camera and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for deploying and scheduling an autopilot for a power inspection drone can be implemented. The display screen of the computer device can be a liquid crystal display or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0121] It can be understood by those skilled in the art that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have the same component arrangement.

[0122] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0123] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0124] In summary, the embodiments of the present invention provide a method and system for deploying and scheduling power inspection drone autopilots. The method for deploying and scheduling power inspection drone autopilots realizes that the power inspection task is issued by the power inspection dispatching center, and each drone autopilot calculates the corresponding task execution estimated cost based on the task execution cost evaluation function according to the power inspection task and sends it to the power inspection dispatching center. The power inspection dispatching center allocates the power inspection task to the target drone autopilot based on the principle of minimizing the task execution cost according to the comparison result of all task execution estimated costs corresponding to the power inspection task, and then the target drone autopilot plans the path in real time according to the received power inspection task to execute the power inspection task. The technical solution is that the method can reasonably allocate inspection tasks based on factors such as the drone autopilot status, weather changes and geographical environment, and can adaptively schedule and optimize for emergencies. It can not only effectively improve the resource utilization rate, task execution flexibility and inspection efficiency of the drone autopilot, but also reduce the inspection cost.

[0125] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0126] The above-described embodiments merely represent several preferred implementations of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art can make several improvements and substitutions without departing from the technical principles of the present invention, and such improvements and substitutions should also be considered within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be based on the scope of protection of the claims.

Claims

1. A method for deploying and scheduling an electric power inspection drone autopilot, characterized in that: Applied to the deployment and dispatching of several UAV autopilots by a power inspection and dispatching center, the method includes the following steps: In response to the power inspection task released by the power inspection dispatch center, each UAV autopilot calculates the corresponding task execution estimated cost based on the power inspection task and a task execution cost evaluation function, and sends the task execution estimated cost to the power inspection dispatch center; the task execution cost evaluation function is obtained based on the loss cost, risk cost, time cost and task priority of the task execution; the risk cost includes the risk of bad weather, altitude risk and signal obstruction risk; the task priority is the execution priority level of the power inspection task currently bid by each UAV autopilot among all the tasks it participates in the bidding; Based on the principle of minimizing task execution costs, the power inspection dispatch center allocates the power inspection task to a target UAV autopilot according to the comparison results of all task execution estimated costs corresponding to the power inspection task; the target UAV autopilot is the UAV autopilot corresponding to the minimum task execution estimated cost; In response to receiving the power inspection task, the target UAV autopilot plans a path in real time to perform the power inspection task; The loss cost includes equipment depreciation cost; and the steps for obtaining the loss cost include: The task execution life consumption is obtained based on the task complexity score coefficient, the UAV autopilot task load, the UAV autopilot task flight altitude, and the total inspection flight time of the UAV autopilot. The equipment depreciation cost is obtained based on the task execution life consumption, the UAV autopilot design life, and the UAV autopilot purchase cost. The equipment depreciation cost is expressed as: Where, represents the depreciation cost of equipment; represents the purchase cost of the drone autopilot; Indicates the design life of the UAV autopilot; Indicates the task execution life consumption; represents the task complexity rating coefficient; Indicates the UAV autopilot mission load, Indicates the average flight altitude of the UAV autopilot mission; Indicates the total duration of the drone autopilot inspection flight; and They represent correction coefficients respectively; The time cost includes the total flight time of the UAV autopilot inspection and the total time of the UAV autopilot inspection to replenish power; the steps for obtaining the time cost include: Obtaining an optimal inspection path based on a path planning algorithm, and obtaining the total inspection flight duration of the UAV autopilot based on the optimal inspection path and the flight speed of the UAV autopilot; the flight speed of the UAV autopilot is obtained by correcting the maximum flight speed of the UAV autopilot based on weather conditions and load status; The amount of power required for task execution is obtained based on the total duration of the UAV autopilot inspection flight, the maximum battery capacity of the UAV autopilot, and the unit flight energy consumption of the UAV autopilot. The total duration of the UAV autopilot inspection power replenishment is obtained based on the amount of power required for task execution and the average charging power of the charging station. The time cost is obtained according to the accumulated value of the total flight time of the UAV autopilot inspection and the total time of the UAV autopilot inspection to replenish power.

2. The method for deploying and scheduling an electric power inspection drone autopilot according to claim 1, wherein: The loss cost also includes electricity cost; and the step of obtaining the loss cost also includes: Obtaining the flight power of the UAV autopilot based on the accumulated values of the hovering power, climbing power, and power to overcome air resistance of the UAV autopilot, and obtaining the electricity cost based on the flight power of the UAV autopilot, the total inspection flight time of the UAV autopilot, and the unit electricity price; The loss cost is obtained according to the accumulated value of the electricity cost and the equipment depreciation cost.

3. The method for deploying and scheduling an electric power inspection drone autopilot according to claim 1, wherein: The steps of obtaining the risk cost include: Acquire real-time weather data for mission execution, and perform UAV autopilot failure prediction based on the real-time weather data for mission execution and a pre-built failure probability prediction model to obtain the severe weather risk; Obtaining geographic data of the mission execution area, and obtaining the altitude risk based on the geographic data of the mission execution area and the maximum allowable flight altitude of the UAV autopilot; Communication signal coverage data of the mission execution area is obtained, and loss of connection risk prediction is performed based on the communication signal coverage data of the mission execution area and a pre-built loss of connection probability prediction model to obtain the signal blocking risk.

4. The method for deploying and scheduling an electric power inspection drone autopilot according to claim 1, wherein: The target UAV autopilot plans a path in real time to perform the power inspection task, including: When the target UAV autopilot detects a path obstacle, an obstacle avoidance path is generated based on the improved A* algorithm according to the obstacle information of the path obstacle, and the task execution cost after obstacle avoidance is evaluated based on the obstacle avoidance path; the obstacle information includes obstacle type, obstacle position and obstacle speed; the cost function of the improved A* algorithm includes actual cost, heuristic estimated cost and obstacle risk cost; the obstacle risk cost is expressed as: in, Indicates the current path node The corresponding obstacle risk cost; Indicates the current path node Minimum distance to obstacles; Indicates the current path node The corresponding obstacle speed; and Indicates the distance influence weight and speed influence weight; According to the task execution cost after obstacle avoidance, the obstacle information is sent to the power inspection and dispatching center, so that the power inspection and dispatching center decides whether the target UAV autopilot should avoid the obstacle and continue to perform the task based on the obstacle information; the obstacle information includes the current position information of the UAV autopilot, the task destination position and the task execution cost after obstacle avoidance.

5. The method for deploying and scheduling an electric power inspection drone autopilot according to claim 4, wherein: The step of the power inspection and dispatching center deciding whether the target UAV autopilot should avoid the obstacle and continue to perform the mission according to the obstacle information includes: The power inspection and dispatching center issues a new inspection task based on the obstacle information, and compares the estimated execution cost of the new inspection task fed back by the drone autopilot with the post-obstacle avoidance task execution cost in the obstacle information; When the task execution cost after obstacle avoidance is the minimum, notifying the target UAV autopilot to continue executing the power inspection task based on the obstacle avoidance path; When the task execution cost after obstacle avoidance is not the minimum value, the new inspection task is assigned to the UAV autopilot corresponding to the minimum value, and the target UAV autopilot is notified to exit the inspection task.

6. The method for deploying and scheduling an electric power inspection drone autopilot according to claim 1, wherein: The method further comprises: When the power inspection task is completed, the target UAV autopilot generates the actual cost of the task execution of the power inspection task, and optimizes and adjusts the weight coefficient of each cost in the task execution cost evaluation function based on the deviation between the actual cost of each item in the actual cost of the task execution and the estimated cost of the corresponding item in the estimated cost of the task execution.

7. A power inspection UAV autopilot deployment and scheduling system, characterized by: Applying the method for deploying and dispatching the power inspection UAV autopilot as claimed in claim 1, the system includes a power inspection dispatch center and a plurality of UAV autopilots; The power inspection dispatch center is used to issue power inspection tasks, receive task execution estimated costs fed back by various UAV autopilots, and, based on the comparison results of all task execution estimated costs corresponding to the power inspection tasks, assign the power inspection tasks to target UAV autopilots based on the principle of minimizing task execution costs; the target UAV autopilot is the UAV autopilot corresponding to the minimum task execution estimated cost; The UAV autopilot is used to calculate the corresponding task execution estimated cost based on the task execution cost evaluation function according to the power inspection task issued by the power inspection dispatching center, and send the task execution estimated cost to the power inspection dispatching center; the task execution cost evaluation function is obtained based on the loss cost, risk cost, time cost and task priority of the task execution; it is also used to plan the path in real time according to the power inspection task assigned by the power inspection dispatching center to execute the power inspection task.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images