A Beidou-based patrol and inspection drone positioning system

Abstract

The present invention discloses a Beidou-based patrol and inspection drone positioning system, which relates to the field of drones. The method includes: a drone positioning estimation module: based on Beidou satellite and drone data, positioning optimization is performed through cloud processing to achieve position estimation; a drone position correction module: obtains the precise position of the drone through an intelligent error correction function; a multi-drone task allocation module: constructs a scene impact index and uses the task execution adaptation score to allocate tasks between multiple drones to improve efficiency; a map construction and path planning module: constructs an environmental map and optimizes the A* algorithm based on the scene impact index to perform optimal path planning; a real-time positioning and obstacle avoidance module: obtains drone data and performs obstacle detection, and makes obstacle avoidance decisions based on obstacle information. Through intelligent error correction and real-time obstacle detection, the positioning accuracy, flight stability and obstacle avoidance capabilities of drones in complex environments are improved, ensuring the efficient and safe execution of tasks.

Description

Technical Field

[0001] The present invention relates to the field of drones, and in particular to a Beidou-based patrol and inspection drone positioning system. Background Art

[0002] With the rapid development of drone technology, drones are increasingly being used in patrol and inspection applications, playing a particularly important role in environmental monitoring, power inspections, and agricultural inspections. However, in complex operating environments, drones' positioning accuracy, path planning, and obstacle avoidance capabilities are critical factors affecting their efficiency and safety. Especially in high-risk or obstacle-laden scenarios, drones' dynamic positioning, task allocation, path planning, and real-time obstacle avoidance technologies still face significant challenges.

[0003] Traditional drone positioning systems rely primarily on GPS, inertial navigation systems, and other positioning technologies. However, in complex environments or with obstructions, GPS signals can be lost or interfered with, resulting in reduced positioning accuracy. Furthermore, as mission complexity increases, a single path planning algorithm often cannot meet the demands of multi-task, multi-drone collaboration. Furthermore, drones inevitably encounter interference from dynamic obstacles during patrols and inspections.

[0004] Based on the above problems, the existing patrol and inspection drone positioning systems still face challenges in positioning accuracy, task allocation and real-time obstacle avoidance when dealing with complex environments, dynamic tasks and obstacle avoidance requirements. Therefore, there is an urgent need for a system that combines the Beidou satellite system, flight status characteristics, intelligent error correction, environmental map construction, task allocation algorithm and multi-sensor fusion technology to solve the shortcomings of existing technologies and improve the efficiency and safety of drone patrol and inspection. Summary of the Invention

[0005] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a Beidou-based patrol and inspection drone positioning system to solve the above-mentioned technical problems.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: a Beidou-based patrol and inspection drone positioning system, comprising:

[0007] UAV positioning estimation module: Based on BeiDou satellite system data and UAV data, positioning optimization is completed in the cloud to achieve position estimation in various environments;

[0008] UAV position correction module: It realizes estimated position correction through intelligent error correction function to obtain the precise position of the UAV;

[0009] Multi-UAV task allocation module: Builds a scenario impact index and uses an auction algorithm to allocate tasks among multiple UAVs to improve the efficiency of patrol tasks;

[0010] Map construction and path planning module: Builds an environment map and optimizes the A* algorithm based on the scene impact index to perform optimal path planning;

[0011] Real-time positioning and obstacle avoidance module: obtains real-time data from the drone and detects obstacles, and makes obstacle avoidance decisions based on the obstacle data.

[0012] The present invention is further configured to construct a flight state vector feature: S t =TimeSeries(p UAV ,v UAV ,a UAV ), where S t is the flight state feature vector at time t, p UAV is the position of the drone, v UAV is the speed, a UAV is acceleration; estimated position calculation logic: Among them, p t is the estimated position at the current moment, N is the number of particles, is the state of the i-th particle, w i is the particle weight, and the calculation logic is: Among them, z t It is the observation value of Beidou system.

[0013] The present invention is further configured such that the intelligent error correction calculation logic: p final =p t -α t ·(p t -z t )+β·(|p t -z t |·|p t-1 -z t-1 |), where p final is the final precise position, β is the dynamic error adjustment coefficient, α t is the adaptive correction coefficient, and the calculation logic is: t =α t-1 +β·|p t -z t |.

[0014] The present invention is further configured to collect information of each drone to construct a drone set and mission model;

[0015] Construct a scenario impact index and calculate the task execution adaptation score of each drone for the task based on the drone set and the task model;

[0016] Assign tasks based on task execution fitness scores;

[0017] Drone status collection construction logic: Among them, U i is a single drone state set, is the current precise position of the UAV, E i is the current battery power of the drone, E i is the current maximum mission load capacity of the UAV, Current UAV flight status characteristics, T j To perform the task, the drone state set is: U = [U1, U2…U n ]; Task model construction logic: T j =[R j ,TIME j ], where T j is the task model, R j The resources required for the task, TIME j The time when the task is completed.

[0018] The present invention is further configured as follows: the scene impact index calculation formula is: Among them, C t is the scene impact index, α i is the dynamic object weight, n is the number of obstacles, d i is the obstacle distance, r i is the obstacle radius, v i Obstacle speed, θ i Obstacle direction, ∈ is a constant to prevent division by zero, V max is the maximum speed in the flight mission, and the mission execution adaptation score is calculated as follows: Among them, V ij is the task execution adaptation score, β1, β2, β3, 4, β5 are weight coefficients, D(U i ,T j ) is the distance from the UAV to the mission point.

[0019] The present invention is further configured to match the task with the drone in a logical manner: in, For the final selected drone, each task selects a drone based on its maximum bidding value, and updates the drone’s status information after assigning the task to the selected drone.

[0020] The present invention is further configured such that the environment map calculation logic: Among them, M t is the current environment map, M is the environment map, and p is the probability function.

[0021] The present invention is further configured such that the optimal path calculation logic is: Among them, p opt is the optimal path, f(p path ) is the optimized path cost function, and the optimization logic is: f(p path )=g(p path )+C t ·h(p path ,p target ), where p path is the starting position, p target is the target position, g(p path ) is the actual cost, h(p path ,p target ) is the estimated cost.

[0022] The present invention is further configured to collect real-time data of the UAV, perform fusion extraction, and obtain a set of obstacle entry states;

[0023] Generate obstacle avoidance path nodes by adjusting the optimal path nodes according to the set of intruding obstacles, and transmit the data to the UAV for emergency obstacle avoidance;

[0024] The camera collects visual data, the lidar obtains 3D electric cloud data, and the infrared sensor obtains temperature data. The multi-sensor data is combined with the LiDAR point cloud data using the YOLO target detection algorithm to identify intrusion obstacles in real time and build an intrusion obstacle set. obs .

[0025] The present invention is further configured such that the obstacle avoidance node calculation logic is: Among them, p avoid (t) is the current obstacle avoidance node, p opt (t) is the current node of the optimal path, λ is the obstacle avoidance coefficient, d weather is the meteorological data, Δp is the displacement vector function, and the calculation logic is: Among them, x final The x coordinate and y coordinate of the precise position of the drone final is the y coordinate of the precise position of the drone, are the coordinates of the obstacle, are the coordinates of the obstacle.

[0026] The present invention provides a Beidou-based patrol and inspection drone positioning system. The method comprises: a drone positioning estimation module: performing positioning optimization based on Beidou satellite system data and drone data in the cloud to achieve position estimation in various environments; a drone position correction module: implementing estimated position correction through an intelligent error correction function to obtain the precise position of the drone; a multi-drone task allocation module: constructing a scene impact index and using an auction algorithm to allocate tasks among multiple drones to improve the efficiency of patrol tasks; a map construction and path planning module: constructing an environmental map and optimizing the A* algorithm according to the scene impact index to perform optimal path planning; a real-time positioning and obstacle avoidance module: acquiring real-time data from the drone and performing obstacle detection, and making obstacle avoidance decisions based on the obstacle data. The beneficial effects produced include:

[0027] Intelligent Error Correction: The system utilizes an intelligent error correction module that dynamically adjusts error correction coefficients and adaptive correction factors to accurately correct the drone's position based on real-time data, significantly reducing the impact of positioning errors. This feature is particularly useful for inspections involving long or complex routes, ensuring the drone's accuracy and stability.

[0028] Real-time obstacle detection and avoidance: By integrating multiple sensors, including cameras, LiDAR, and infrared sensors, the system uses the YOLO target detection algorithm combined with LiDAR point cloud data to accurately identify and detect obstacles in real time. It dynamically adjusts the path based on the location and status of obstacles, ensuring the drone can react quickly during flight and avoid collisions. This technology effectively enhances the drone's adaptability and safety in complex environments.

[0029] Environmental adaptability and intelligent decision support: The system calculates the scenario impact index, taking into account multiple factors such as dynamic obstacles, weather conditions, obstacle speed, and maximum flight mission speed. When optimizing task allocation, path planning, and obstacle avoidance decisions, it can comprehensively consider changes in environmental complexity, enabling drones to adapt to environmental changes in real time and perform more intelligent and flexible tasks.

[0030] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. In the drawings:

[0032] Figure 1 The figure is a schematic structural diagram of a Beidou-based patrol and inspection drone positioning system according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0034] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0035] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0036] Example

[0037] A Beidou-based inspection drone positioning system, such as Figure 1 Shown, including:

[0038] UAV positioning estimation module: Based on BeiDou satellite system data and UAV data, positioning optimization is completed in the cloud to achieve position estimation in various environments;

[0039] UAV positioning estimation module: Based on BeiDou satellite system data and UAV data, positioning optimization is completed in the cloud to achieve position estimation in various environments;

[0040] UAV position correction module: It realizes estimated position correction through intelligent error correction function to obtain the precise position of the UAV;

[0041] Multi-UAV task allocation module: Builds a scenario impact index and uses an auction algorithm to allocate tasks among multiple UAVs to improve the efficiency of patrol tasks;

[0042] Map construction and path planning module: Builds an environment map and optimizes the A* algorithm based on the scene impact index to perform optimal path planning;

[0043] Real-time positioning and obstacle avoidance module: obtains real-time data from the drone and detects obstacles, and makes obstacle avoidance decisions based on the obstacle data.

[0044] The present invention is further configured to construct a flight state vector feature: S t =TimeSeries(p UAV ,v UAV ,a UAV ), where S t is the flight state feature vector at time t, p UAV is the position of the drone, v UAV is the speed, a UAV is acceleration; estimated position calculation logic: Among them, p t is the estimated position at the current moment, N is the number of particles, is the state of the i-th particle, w i is the particle weight, and the calculation logic is: Among them, z t The BeiDou system observations are used. Specifically, the time series records describe the UAV's motion state at each moment, which is used for subsequent positioning estimation and error correction. Position estimation uses a particle filter method to combine the UAV's flight state and BeiDou satellite system observations to estimate the UAV's current position. Particle weights are updated based on the degree of match between the observed data and the particle's predicted position; particles that match the observed value better have higher weights.

[0045] The present invention is further configured such that the intelligent error correction calculation logic: p final =p t -α t ·(p t -z t )+β·(|p t -z t |·|p t-1 -z t-1 |), where p final is the final precise position, β is the dynamic error adjustment coefficient, α t is the adaptive correction coefficient, and the calculation logic is:t =α t-1 +β·|p t -z t |. Specifically, p t -α t ·(p t -z t ) This step is error correction, p t -z t It is used to calculate the deviation between the estimated position at the current moment and the Beidou observation value, and adjust the deviation according to the adaptive correction coefficient, (|p t -z t |·|p t-1 -z t-1 |) This step is the historical correction factor, which takes into account the deviation between the current moment and the previous moment and weighs the impact of the historical correction factor on the error correction based on the adjustment coefficient.

[0046] The present invention is further configured to collect information of each drone to construct a drone set and mission model;

[0047] Construct a scenario impact index and calculate the task execution adaptation score of each drone for the task based on the drone set and the task model;

[0048] Assign tasks based on task execution fitness scores;

[0049] Drone status collection construction logic: Among them, U i is a single drone state set, is the current precise position of the UAV, E i is the current battery power of the drone, E i is the current maximum mission load capacity of the UAV, Current UAV flight status characteristics, T j To perform the task, the drone state set is: U = [U1, U2…U n ]; Task model construction logic: T j =[R j ,TIME j ], where T j is the task model, R j The resources required for the task, TIME j The time it takes to complete a mission. Specifically, the drone state set describes the drone's state at a specific moment, including its location, energy, battery status, and flight capabilities. This helps determine whether the drone is suitable for a particular mission. Each mission model includes the resources and time required to complete the mission. The mission model helps assess whether the drone is capable of completing the mission on time.

[0050] The present invention is further configured as follows: the scene impact index calculation formula is: Among them, C t is the scene impact index, α i is the dynamic object weight, n is the number of obstacles, d i is the obstacle distance, r i is the obstacle radius, v i Obstacle speed, θ i Obstacle direction, ∈ is a constant to prevent division by zero, V max is the maximum speed in the flight mission, and the mission execution adaptation score is calculated as follows: Among them, V ij is the task execution adaptation score, β1, β2, β3, 4, β5 are weight coefficients, D(U i ,T j ) is the distance between the UAV and the mission point. Specifically, the scenario impact index is used to describe the degree of influence of environmental factors on mission execution. It is an important reference factor in task allocation and helps optimize the UAV's task selection and path planning. The mission execution adaptability indicates the degree of matching between the UAV and the mission, taking into account the UAV's status and mission requirements. β1, β2, β3, 4, and β5 are weight coefficients. The weight coefficients are used to control the degree of influence of various parameters during mission execution, and their value range is [0, 1]. The distance from the UAV to the mission point is used to represent the actual distance between the UAV and the mission point. The calculation formula is: Among them, x final is the x coordinate of the precise position of drone i, y final is the y coordinate of the precise position of UAV i, x target,j is the x coordinate of task j, y target,j is the y coordinate of task j.

[0051] The present invention is further configured to match the task with the drone logic: in, For the final selection of drones, each task is assigned based on the drone's maximum bid value. After assigning the task to the selected drone, the drone's status information is updated. Specifically, for each task, the task execution fitness score of each drone for that task is calculated. Then, the argmax function is used to find the drone with the maximum task execution fitness score. This drone is the most suitable for the task because it has the highest task execution fitness score.

[0052] The present invention is further configured such that the environment map calculation logic: Among them, M tis the current environment map, M is the environment map, and p is the probability function. Specifically, the environment map is calculated by estimating the environment map at each moment, thereby optimizing the drone's position estimate and ultimately finding the environment map that maximizes the estimated probability. The probability function is calculated by multiplying and maximizing the observed data at each moment to find the most likely environment map. This means that by comparing different environment maps, the probability of the observations is evaluated, ultimately determining the environment map that best matches the data at the current moment.

[0053] The present invention is further configured such that the optimal path calculation logic is: Among them, p opt is the optimal path, f(p path ) is the optimized path cost function, and the optimization logic is: f(p path )=g(p path )+C t ·h(p path ,p target ), where p path is the starting position, p target is the target position, g(p path ) is the actual cost, h(p path ,p target ) is the estimated cost. Specifically, It means that the path with the minimum path cost is selected as the optimal path; the optimization logic of the path cost function is to consider the scene impact index in the process of path planning, and to use the scene impact index as one of the conditions for measuring path planning in the calculation of each node cost.

[0054] The present invention is further configured to collect real-time data of the UAV, perform fusion extraction, and obtain a set of obstacle entry states;

[0055] Generate obstacle avoidance path nodes by adjusting the optimal path nodes according to the set of intruding obstacles, and transmit the data to the UAV for emergency obstacle avoidance;

[0056] The camera collects visual data, the lidar obtains 3D electric cloud data, and the infrared sensor obtains temperature data. The multi-sensor data is combined with the LiDAR point cloud data using the YOLO target detection algorithm to identify intrusion obstacles in real time and build an intrusion obstacle set. obs. Specifically, first, the drone obtains different types of environmental data through multiple sensors, and then fuses the information of these sensors to generate a comprehensive environmental perception model. Then, through the YOLO target detection algorithm, combined with the point cloud data of the lidar and the visual data of the camera, obstacles in the scene are detected and identified in real time. The YOLO algorithm identifies objects in the image and assigns a bounding box to each target, extracts target category, location and other information, and combines the LiDAR point cloud data to identify more accurate obstacle location and shape information. According to the output of the target detection algorithm, all obstacles detected in real time are grouped into an obstacle set, which contains the status information of all intruding obstacles. This obstacle does not exist during path planning, but is detected in real time during the flight of the drone. In order to prevent collisions, the drone's inspection path needs to be adjusted in time.

[0057] The present invention is further configured such that the obstacle avoidance node calculation logic is: Among them, p avoid (t) is the current obstacle avoidance node, p opt (t) is the current node of the optimal path, λ is the obstacle avoidance coefficient, d weather is the meteorological data, Δp is the displacement vector function, and the calculation logic is: Among them, x final The x coordinate and y coordinate of the precise position of the drone final is the y coordinate of the precise position of the drone, are the coordinates of the obstacle, are the coordinates of the obstacle. Specifically, the current obstacle avoidance node represents the path node that the drone needs to avoid the obstacle and continue flying at the current moment. The obstacle avoidance coefficient is used to control the amplitude of the optimal path node adjustment. When the obstacle avoidance coefficient is large, the drone will adjust its path more strongly to avoid the obstacle. Conversely, when the obstacle avoidance coefficient is small, the path adjustment is more gentle. The obstacle avoidance coefficient usually ranges from [0,1]. The larger the value, the more sensitive the obstacle avoidance response. Meteorological data includes environmental factors of flight. Different environments have different effects on the speed and stability of the drone. Meteorological data is a comprehensive indicator with different ranges set according to different mission execution environments. The displacement vector function calculates the relative offset between the drone's current path and the obstacle. It includes the difference between the drone's current position, the target position, and the obstacle position, including the offset in the x and y directions. The difference in these two directions is used to calculate the amount of movement that the drone needs to adjust.

[0058] It should be noted that the Beidou-based patrol and inspection drone positioning system provided in the above embodiment and the Beidou-based patrol and inspection drone positioning system provided in the above embodiment belong to the same concept, and the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual application, the Beidou-based patrol and inspection drone positioning system provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0059] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0060] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0061] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0062] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0063] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0064] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0066] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0067] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0068] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0069] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A Beidou-based patrol and inspection drone positioning system, characterized in that: include: UAV positioning estimation module: based on BeiDou satellite system data and UAV data processing in the cloud Positioning optimization to achieve position estimation in various environments, including: Constructing flight state vector features: ,in, For the moment The flight state feature vector, is the drone location, For speed, is acceleration; estimated position calculation logic: ,in, is the estimated position at the current moment, is the number of particles, For the The state of a particle, is the particle weight, and the calculation logic is: ,in, is the BeiDou system observation value; UAV position correction module: This module implements estimated position correction through intelligent error correction function to obtain the precise position of the UAV, including: intelligent error correction calculation logic: ,in, For the final precise position, is the dynamic error adjustment coefficient, is the adaptive correction coefficient, and the calculation logic is: ; Multi-UAV task allocation module: Constructs a scenario impact index and uses an auction algorithm to allocate tasks among multiple UAVs to improve the efficiency of patrol tasks, including: Scenario impact index calculation formula: ,in, is the scene impact index, is the dynamic object weight, is the number of obstacles, is the obstacle distance, is the obstacle radius, Obstacle speed, Obstacle direction, is a constant used to prevent division by zero, is the maximum speed in the flight mission, and the mission execution adaptation score is calculated as follows: ,in, is the task execution fitness score, is the weight coefficient, is the distance from the UAV to the mission point, is a single drone state set, For the task model, The resources required for the task, The current battery level of the drone. is the maximum mission load capacity of the current UAV; Map construction and path planning module: Builds an environment map and optimizes the A* algorithm based on the scene impact index to perform optimal path planning; Real-time positioning and obstacle avoidance module: obtains real-time data from the drone and detects obstacles, and makes obstacle avoidance decisions based on the obstacle data.

2. A Beidou-based inspection drone positioning system according to claim 1, characterized in that: Collect information about each drone to build a drone collection and mission model; Construct a scenario impact index and calculate the task execution adaptation score of each drone for the task based on the drone set and the task model; Assign tasks based on task execution fitness scores; Drone status collection construction logic: ,in, is a single drone state set, The current precise location of the drone, The current battery level of the drone. is the current maximum mission load capacity of the UAV, Current drone flight status characteristics, For the mission to be performed, the drone status collection: ;Task model construction logic: ,in, For the task model, The resources required for the task, The time when the task is completed.

3. The Beidou-based inspection drone positioning system according to claim 2 is characterized in that: Mission and drone matching logic: ,in, For the final selected drone, each task selects a drone based on its maximum bidding value, and updates the drone’s status information after assigning the task to the selected drone.

4. The Beidou-based inspection drone positioning system according to claim 1 is characterized in that: Environment map calculation logic: ,in, is the current environment map, For the environment map, is the probability function.

5. The Beidou-based inspection drone positioning system according to claim 1 is characterized in that: Optimal path calculation logic: ,in, is the optimal path, is the optimized path cost function, and the optimization logic is: ,in, is the starting position, is the target position, For the actual cost, For estimated cost.

6. The Beidou-based inspection drone positioning system according to claim 1 is characterized in that: Collect real-time data from drones, perform fusion extraction, and obtain the state set of intrusion obstacles; Generate obstacle avoidance path nodes by adjusting the optimal path nodes according to the set of intruding obstacles, and transmit the data to the UAV for emergency obstacle avoidance; The camera collects visual data, the lidar obtains 3D point cloud data, and the infrared sensor obtains temperature data. The multi-sensor data is combined with the LiDAR point cloud data using the YOLO target detection algorithm to identify intrusion obstacles in real time and build an intrusion obstacle set. .

7. The Beidou-based inspection drone positioning system according to claim 6 is characterized in that: Obstacle avoidance node calculation logic: ,in, is the current obstacle avoidance node, is the current node of the optimal path, is the obstacle avoidance coefficient, For meteorological data, is the displacement vector function, and the calculation logic is: ,in, Precise location of drones coordinate, Precise location of drones coordinate, are the coordinates of the obstacle, are the coordinates of the obstacle.

Images