Distributed unmanned aerial vehicle detection system

Abstract

The invention discloses a distributed unmanned aerial vehicle detection system, and belongs to the technical field of unmanned aerial vehicle detection planning, and the system specifically comprises the steps: obtaining all to-be-allocated tasks and the number of unmanned aerial vehicles of an unmanned aerial vehicle base station; obtaining importance grade scores of the to-be-allocated tasks, sorting the to-be-allocated tasks according to the importance grade scores to obtain a first sequence, and formulating planning routes of all unmanned aerial vehicles based on the first sequence; any unmanned aerial vehicle is selected and flies according to the corresponding planned route, the consumed electric quantity and the remaining electric quantity of the unmanned aerial vehicle are obtained in real time, whether the electric quantity of the unmanned aerial vehicle meets the task allocation requirement or not is judged, and if yes, the unmanned aerial vehicle is controlled to continue to fly along the current planned route; if not, a target unmanned aerial vehicle is selected from all the remaining unmanned aerial vehicles, the planned route of the target unmanned aerial vehicle is corrected, and a final planned route is obtained, and efficient unmanned aerial vehicle management and route planning are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle detection planning, and in particular to a distributed unmanned aerial vehicle detection system. Background Art

[0002] When a single drone performs a mission, the flight time and coverage are usually limited, while the collaborative operation of multiple drones can significantly expand the detection area and shorten the time to complete the mission. UAV collaborative detection improves the efficiency of mission execution and the accuracy of data collection through the cooperation of multiple drones. By optimizing flight paths and task allocation between drones, it is possible to achieve simultaneous coverage of multiple areas, avoid repeated flights, and maximize resource utilization and mission efficiency. This collaborative method is widely used in many fields such as disaster monitoring, environmental assessment, and agricultural management, and has significant advantages and application potential.

[0003] At present, in the control of multiple UAVs coordinating tasks, in order to avoid chaos caused by each task occupying on-board resources, most of them are completed one by one according to the priority of the tasks, so as to reduce the competition for limited resources between different tasks and avoid potential conflicts and interference. However, in the face of some special circumstances, such as partial UAV failures and failure of UAVs to complete the tasks, UAVs with similar geographical locations are often selected to establish task transfer contacts. The original intention of this method is to reduce the flight distance and duration, ensure the redistribution and execution of unfinished tasks in the shortest time, thereby improving the task completion efficiency of the entire UAV formation. However, this ignores the turning path consumption of UAVs to a certain extent. Although UAVs with similar geographical locations can quickly take over tasks, in actual operations, frequent turning and path adjustments will increase energy consumption. This additional energy consumption may affect the endurance of the UAV, thereby limiting its ability to perform more tasks. Summary of the invention

[0004] The purpose of the present invention is to provide a distributed drone detection system to solve the following technical problems: At present, in order to avoid each task occupying the onboard resources and causing chaos, the control of multiple drone formations to coordinate tasks is mostly completed one by one according to the priority of the tasks, so as to reduce the competition for limited resources between different tasks and avoid potential conflicts and interference. However, in some special circumstances, such as partial drone failures and failure of drones to complete the tasks, drones with similar geographical locations are often selected to establish task transfer contacts. The original intention of this method is to reduce the flight distance and duration, ensure the redistribution and execution of unfinished tasks in the shortest time, thereby improving the task completion efficiency of the entire drone formation. However, this ignores the turning path consumption of drones to a certain extent. Although drones with similar geographical locations can quickly take over tasks, in actual operations, frequent turning and path adjustments will increase energy consumption. This additional energy consumption may affect the endurance of the drone, thereby limiting its ability to perform more tasks.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A distributed drone detection system, comprising: A data acquisition module is used to obtain all the tasks to be assigned M and the number of drones N of the drone base station; A data analysis module, used for obtaining the importance level scores of the tasks to be inspected, sorting the tasks to be assigned according to the importance level scores to obtain a first sorting, and formulating the planned routes of all drones based on the first sorting; The data optimization module is used to select any UAV and fly it according to its corresponding planned route, and obtain the power consumption and remaining power of the UAV in real time, and judge whether the power of the UAV meets the requirements of the assigned task. If so, the UAV is controlled to continue flying along the current planned route; if not, the remaining power and position information of all remaining UAVs are obtained, and a target UAV is selected from all remaining UAVs according to the remaining power and position information, and the planned route of the target UAV is corrected to obtain the final planned route.

[0006] As a further solution of the present invention: In the data analysis module, the specific process of formulating the planned routes of all drones is as follows: S1, according to the first sorting, select the top M inspection tasks from the inspection tasks in turn and mark them as target inspection tasks, obtain the initial position of any UAV and the position of the target inspection task to generate a cost matrix, perform minimum matching calculation on the Cost matrix, and obtain the first inspection task corresponding to any UAV; S2, calibrating the location information of the first inspection task as the second geographical location of the corresponding drone, generating a cost matrix according to the second geographical location and the location information of the remaining inspection tasks, performing minimum matching calculation on the cost matrix, and obtaining the second inspection task corresponding to any drone; S3, repeat S1 and S2 to obtain the inspection task sequence corresponding to any UAV, and generate a planned route corresponding to any UAV according to the position and sequence order corresponding to the inspection task.

[0007] As a further solution of the present invention: S2 also includes that when the remaining tasks to be assigned are less than the number of drones, the remaining tasks to be assigned and all drones are sequentially combined to generate a cost matrix and perform a minimum matching calculation to obtain a drone that matches any remaining task to be assigned.

[0008] As a further solution of the present invention: In the data optimization module, the specific process of judging whether the power of the drone meets the requirements of the assigned task is as follows: S21, obtaining the flight route and power consumption C of the drone, and calculating the flight distance S and steering angle W of the drone according to the flight route; S22, build consumption model ; Among them, Cw is the set of flight angle turning points in the flight route of the UAV, and Cd is the corresponding length of any straight line segment in the flight route of the UAV; S23, obtain the current position of the drone and the position of the next inspection task to be inspected, and substitute them into the consumption model to calculate the estimated power consumption C'; take the position of the next inspection task to be inspected as the starting point and the initial position of the drone as the end point, construct a return planning route, substitute the return planning route into the consumption model, and obtain the return power consumption C''. If the remaining power of the drone C 剩 is greater than or equal to (C'+C''+α), then the UAV's power level is judged to meet the requirements of the assigned task; if the remaining power of the UAV C 剩 If it is less than (C'+C''+α), it is judged that the power of the UAV does not meet the requirements of the assigned task, where α is the preset power reserve.

[0009] As a further solution of the present invention: in the data optimization module, the target drone selection process is: S31, obtaining any drone that does not meet the current task requirements, marking the remaining tasks of the drone as temporary inspection tasks, and sending temporary inspection task information to the remaining drones; S32, if any UAV receives temporary inspection task information during the inspection process, it is determined whether the remaining battery power of the UAV meets the work requirements based on the current remaining task volume and the temporary inspection task. If so, the UAV is marked as a target UAV; if not, the planned route of the UAV is maintained.

[0010] As a further solution of the present invention: S31 also includes if the current task is the last task of the drone, then marking the current task requirement as a temporary inspection task; if the current task requirement is not the last task requirement of the drone, then marking all remaining tasks of the drone as temporary inspection tasks one by one.

[0011] As a further solution of the present invention: in S32, if there are two or more drones that meet the task requirements, the estimated power consumption of any drone to complete the temporary inspection task is calculated, and the drone with the smallest estimated power consumption is selected and calibrated as the target drone.

[0012] As a further solution of the present invention: in the data optimization module, the process of correcting the planned route is: The temporary task is incorporated into the remaining tasks of the target UAV and sorted according to the importance level, and the route planning is carried out according to the sorted remaining tasks.

[0013] Beneficial effects of the present invention: The present invention firstly obtains all the to-be-assigned task amounts and the number of drones of the drone base station, and plans the flight route of each drone according to the priority of the to-be-assigned tasks, obtains the power consumption and remaining power of the drone in real time, and judges whether the power of the drone meets the requirements of the assigned tasks, avoids task interruption or delay caused by insufficient power, and improves the stability and continuity of the inspection. If not, the remaining power and position information of all the remaining drones are obtained, and a target drone is selected from all the remaining drones according to the remaining power and position information, and the planned route of the target drone is corrected to obtain the final planned route, thereby ensuring the continuity of the tasks and improving the efficiency of task completion. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings.

[0015] Figure 1 It is a schematic diagram of the flow of a distributed UAV detection system of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 As shown, the present invention is a distributed UAV detection system, comprising: A data acquisition module is used to obtain all the tasks to be assigned M and the number of drones N of the drone base station; A data analysis module, used for obtaining the importance level scores of the tasks to be inspected, sorting the tasks to be assigned according to the importance level scores to obtain a first sorting, and formulating the planned routes of all drones based on the first sorting; Task decomposition and allocation: In multi-UAV collaborative control, the complex overall task must first be decomposed into multiple subtasks. This process involves a detailed analysis of task requirements, including task objectives, execution process, inter-task dependencies, etc. The decomposed tasks are assigned to different UAVs or UAV groups to ensure that each task receives appropriate attention and resource support. Therefore, in the present invention, all the tasks to be assigned and the number of UAVs of the UAV base station are first obtained, and the flight route of each UAV is planned according to the priority of the tasks to be assigned, so as to assign tasks to each UAV.

[0018] The data optimization module is used to select any UAV and fly it according to its corresponding planned route, and obtain the power consumption and remaining power of the UAV in real time, and judge whether the power of the UAV meets the requirements of the assigned task. If so, the UAV is controlled to continue flying along the current planned route; if not, the remaining power and position information of all remaining UAVs are obtained, and a target UAV is selected from all remaining UAVs according to the remaining power and position information, and the planned route of the target UAV is corrected to obtain the final planned route.

[0019] Dynamic task scheduling system: For the control of multiple drones to perform tasks in coordination, in order to avoid each task occupying the onboard resources and causing confusion, most of them are completed one by one according to the priority of the tasks, so as to reduce the competition for limited resources between different tasks and avoid potential conflicts and interference. However, in the face of some special circumstances, such as some drones fail to complete the task, drones with similar geographical locations are often selected to establish task transfer links. The original intention of this method is to reduce the flight distance and duration, ensure the redistribution and execution of unfinished tasks in the shortest time, thereby improving the task completion efficiency of the entire drone formation. However, this To a certain extent, the turning path consumption of the UAV is ignored. Although UAVs with similar geographical locations can quickly take over tasks, in actual operations, frequent turning and path adjustments will increase energy consumption. This additional energy consumption may affect the endurance of the UAV, thereby limiting its ability to perform more tasks. In the present invention, the power consumption and remaining power of the UAV are obtained, and it is determined whether the power of the UAV meets the requirements of the assigned task, thereby avoiding task interruptions or delays due to insufficient power, improving the stability and continuity of the inspection, and correcting the planned route of the target UAV to obtain the final planned route, ensuring the continuity of the task and improving the efficiency of task completion.

[0020] The present invention firstly obtains all the to-be-assigned task amounts and the number of drones of the drone base station, and plans the flight route of each drone according to the priority of the to-be-assigned tasks, obtains the power consumption and remaining power of the drone in real time, and judges whether the power of the drone meets the requirements of the assigned tasks, avoids task interruption or delay caused by insufficient power, and improves the stability and continuity of the inspection. If not, the remaining power and position information of all the remaining drones are obtained, and a target drone is selected from all the remaining drones according to the remaining power and position information, and the planned route of the target drone is corrected to obtain the final planned route, thereby ensuring the continuity of the tasks and improving the efficiency of task completion.

[0021] In a preferred embodiment of the present invention, in the data analysis module, the specific process of formulating the planned routes of all drones is: S1, according to the first sorting, select the top M inspection tasks from the inspection tasks in turn and mark them as target inspection tasks, obtain the initial position of any UAV and the position of the target inspection task to generate a cost matrix, perform minimum matching calculation on the Cost matrix, and obtain the first inspection task corresponding to any UAV; S2, calibrating the location information of the first inspection task as the second geographical location of the corresponding drone, generating a cost matrix according to the second geographical location and the location information of the remaining inspection tasks, performing minimum matching calculation on the cost matrix, and obtaining the second inspection task corresponding to any drone; S3, repeat S1 and S2 to obtain the inspection task sequence corresponding to any UAV, and generate a planned route corresponding to any UAV according to the position and sequence order corresponding to the inspection task.

[0022] By sorting the inspection tasks according to priority and selecting the top M tasks as target inspection tasks, it can ensure that the drones prioritize the most important or urgent tasks, thereby improving the overall inspection efficiency. Using the minimum matching calculation method to process the cost matrix can effectively match drones with inspection tasks, so that each drone can take on the appropriate amount of tasks, avoiding the situation where some drones are overloaded while other drones are idle, and achieving reasonable allocation of resources. This method allows the parameter M (i.e., the number of target inspection tasks selected each time) to be adjusted according to actual needs to adapt to inspection needs of different scales and complexities.

[0023] Multi-layer task scheduling model: The present invention adopts a multi-layer task scheduling model that is refined to the module level. By scheduling tasks from the cloud layer by layer to specific drone functional modules for execution, the average completion time of a single task is effectively reduced and the task throughput is improved.

[0024] In another preferred embodiment of the present invention, S2 also includes the step of generating a cost matrix for the remaining tasks to be assigned and all drones in turn and performing a minimum matching calculation to obtain a drone that matches any remaining task to be assigned when the number of remaining tasks to be assigned is less than the number of drones.

[0025] In another preferred embodiment of the present invention, in the data optimization module, the specific process of determining whether the power of the drone meets the requirements of the assigned task is as follows: S21, obtaining the flight route and power consumption C of the drone, and calculating the flight distance S and steering angle W of the drone according to the flight route; S22, build consumption model ; Where Cw is the set of flight angle turning points in the UAV flight route, and Cd is the corresponding length of any straight line segment in the UAV flight route; S23, obtain the current position of the drone and the position of the next inspection task to be inspected, and substitute them into the consumption model to calculate the estimated power consumption C'; take the position of the next inspection task to be inspected as the starting point and the initial position of the drone as the end point, construct a return planning route, substitute the return planning route into the consumption model, and obtain the return power consumption C''. If the remaining power of the drone C 剩 is greater than or equal to (C'+C''+α), then the UAV's power level is judged to meet the requirements of the assigned task; if the remaining power of the UAV C 剩If it is less than (C'+C''+α), it is judged that the power of the UAV does not meet the requirements of the assigned task, where α is the preset power reserve.

[0026] By combining the current position of the drone, the location of the task to be inspected, and the power demand of the return route, the task can be calculated and evaluated in real time to see if it can be successfully completed. This dynamic power consumption estimation can make reasonable judgments when allocating tasks, avoid allocating tasks that exceed the drone's power carrying capacity, and improve the efficiency and safety of task allocation. The calculation of the return path takes into account the power consumption model, which not only optimizes the flight path in a one-way task, but also ensures the power budget of the return process. By calculating the return power consumption (C''), the return trip after the task is completed can be better planned to avoid the drone being unable to return smoothly due to insufficient power. The introduction of the preset power margin α further ensures safety and avoids unexpected situations caused by low power in the drone. By considering the complexity of the flight path (such as the turning point Cw of the flight angle and the length of the straight line segment Cd), a more accurate power budget can be allocated for different tasks. This allows the drone to adjust its flight plan based on specific circumstances when facing complex terrain or missions, rather than relying solely on fixed power consumption standards. By fully considering factors such as flight routes, angle turns, and power consumption, it can assess the feasibility of the mission in advance and avoid mission interruptions due to insufficient power, greatly improving the reliability and efficiency of the mission. By accurately calculating power consumption and path planning, it can avoid unnecessary flight distances or excessive power consumption, reduce ineffective flights, and thus optimize energy use and mission execution costs.

[0027] In another preferred embodiment of the present invention, in the data optimization module, the target drone selection process is: S31, obtaining any drone that does not meet the current task requirements, marking the remaining tasks of the drone as temporary inspection tasks, and sending temporary inspection task information to the remaining drones; S32, if any UAV receives temporary inspection task information during the inspection process, it is determined whether the remaining battery power of the UAV meets the work requirements based on the current remaining task volume and the temporary inspection task. If so, the UAV is marked as a target UAV; if not, the planned route of the UAV is maintained.

[0028] Dynamic task scheduling system: For the control of multiple drone formations to perform tasks in coordination, in order to avoid each task occupying the onboard resources and causing confusion, most of them are completed one by one according to the priority of the tasks, so as to reduce the competition for limited resources between different tasks, thereby avoiding potential conflicts and interference. However, in the face of some special circumstances, such as partial drone failures and drones failing to complete the task, drones with similar geographical locations are often selected to establish task transfer contacts. The original intention of this method is to reduce the flight distance and duration, ensure the redistribution and execution of unfinished tasks in the shortest time, thereby improving the task completion efficiency of the entire drone formation. However, This ignores the turning path consumption of the UAV to a certain extent. Although UAVs with similar geographical locations can quickly take over tasks, in actual operations, frequent turning and path adjustments will increase energy consumption. This additional energy consumption may affect the endurance of the UAV, thereby limiting its ability to perform more tasks. In the present invention, the power consumption and remaining power of the UAV are obtained, and it is determined whether the power of the UAV meets the requirements of the assigned task, so as to avoid task interruption or delay due to insufficient power, improve the stability and continuity of the inspection, and correct the planned route of the target UAV to obtain the final planned route, thereby ensuring the continuity of the task and improving the efficiency of task completion.

[0029] In another preferred embodiment of the present invention, the S31 also includes if the current task is the last task of the drone, then the current task requirement is marked as a temporary inspection task; if the current task requirement is not the last task requirement of the drone, then all remaining tasks of the drone are marked as temporary inspection tasks one by one.

[0030] In another preferred embodiment of the present invention, in S32, if there are two or more drones that meet the task requirements, the estimated power consumption of any drone to complete the temporary inspection task is calculated, and the drone with the smallest estimated power consumption is selected and calibrated as the target drone.

[0031] Multi-machine collaborative task scheduling method: By using the TTNT data link multiple access protocol to build a hierarchical clustered drone swarm model with a highly dynamic topology, message transmission is optimized, data transmission conflicts are reduced, and the system's network throughput and information interaction capabilities are improved, so that each drone can participate in the election for temporary inspection tasks, thereby finding the optimal target drone.

[0032] In another preferred embodiment of the present invention, in the data optimization module, the process of correcting the planned route is: The temporary task is incorporated into the remaining tasks of the target UAV and sorted according to the importance level, and the route planning is carried out according to the sorted remaining tasks.

[0033] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A distributed drone detection system, characterized in that: include: A data acquisition module is used to obtain all the tasks to be assigned M and the number of drones N of the drone base station; A data analysis module, used for obtaining importance level scores of the tasks to be assigned, sorting the tasks to be assigned according to the importance level scores to obtain a first sorting, and formulating planned routes for all drones based on the first sorting; The data optimization module is used to select any UAV and fly it according to its corresponding planned route, and obtain the power consumption and remaining power of the UAV in real time, and judge whether the power of the UAV meets the requirements of the assigned task. If so, the UAV is controlled to continue flying along the current planned route; if not, the remaining power and position information of all remaining UAVs are obtained, and a target UAV is selected from all remaining UAVs according to the remaining power and position information, and the planned route of the target UAV is corrected to obtain the final planned route.

2. A distributed drone detection system according to claim 1, characterized in that: In the data analysis module, the specific process of formulating the planned routes of all drones is as follows: S1, according to the first sorting, select the top M inspection tasks from the inspection tasks and mark them as target inspection tasks, obtain the initial position of any UAV and the position of the target inspection task to generate a cost matrix, perform minimum matching calculation on the Cost matrix, and obtain the first inspection task corresponding to any UAV; S2, calibrating the location information of the first inspection task as the second geographical location of the corresponding drone, generating a cost matrix according to the second geographical location and the location information of the remaining inspection tasks, performing minimum matching calculation on the cost matrix, and obtaining the second inspection task corresponding to any drone; S3, repeat S1 and S2 to obtain the inspection task sequence corresponding to any UAV, and generate a planned route corresponding to any UAV according to the position and sequence order corresponding to the inspection task.

3. A distributed drone detection system according to claim 2, characterized in that: The S2 also includes that when the remaining tasks to be assigned are less than the number of drones, the remaining tasks to be assigned and all drones are sequentially combined to generate a cost matrix and perform a minimum matching calculation to obtain a drone that matches any remaining task to be assigned.

4. A distributed drone detection system according to claim 1, characterized in that: In the data optimization module, the specific process of determining whether the power of the drone meets the requirements of the assigned task is as follows: S21, obtaining the flight route and power consumption C of the drone, and calculating the flight distance S and steering angle W of the drone according to the flight route; S22, build consumption model ; Among them, Cw is the set of flight angle turning points in the flight route of the UAV, and Cd is the corresponding length of any straight line segment in the flight route of the UAV; S23, obtain the current position of the drone and the position of the next inspection task to be inspected, and substitute them into the consumption model to calculate the estimated power consumption C'; take the position of the next inspection task to be inspected as the starting point and the initial position of the drone as the end point, construct a return planning route, obtain the return distance and return steering angle and substitute them into the consumption model to obtain the return power consumption C''. If the remaining power of the drone C 剩 is greater than or equal to (C'+C''+α), then the UAV's power level is judged to meet the requirements of the assigned task; if the remaining power of the UAV C 剩 If it is less than (C'+C''+α), it is judged that the power of the UAV does not meet the requirements of the assigned task, where α is the preset power reserve.

5. A distributed drone detection system according to claim 1, characterized in that: In the data optimization module, the target drone selection process is as follows: S31, obtaining any drone that does not meet the current task requirements, marking the remaining tasks of the drone as temporary inspection tasks, and sending temporary inspection task information to the remaining drones; S32, if any UAV receives temporary inspection task information during the inspection process, it is determined whether the remaining battery power of the UAV meets the work requirements based on the current remaining task volume and the temporary inspection task. If so, the UAV is marked as a target UAV; if not, the planned route of the UAV is maintained.

6. A distributed drone detection system according to claim 5, characterized in that: The S31 also includes marking the current task requirement as a temporary inspection task if the current task is the last task of the drone; if the current task requirement is not the last task requirement of the drone, marking all remaining tasks of the drone as temporary inspection tasks one by one.

7. A distributed drone detection system according to claim 5, characterized in that: In S32, if there are two or more drones that meet the task requirements, the estimated power consumption of any drone to complete the temporary inspection task is calculated, and the drone with the smallest estimated power consumption is selected and calibrated as the target drone.

8. A distributed drone detection system according to claim 1, characterized in that: In the data optimization module, the process of correcting the planned route is as follows: The temporary task is incorporated into the remaining tasks of the target UAV and sorted in descending order according to the importance level score, and the route planning is carried out according to the sorted remaining tasks.

Images