Multi-airfield cooperative unmanned aerial vehicle full-automatic inspection scheduling system

Abstract

The application relates to the technical field of unmanned planes and discloses a multi-airport coordinated unmanned plane full-automatic inspection scheduling system, which comprises a central scheduling module, a plurality of distributed airports and an unmanned plane cluster. The central scheduling module is used for receiving a plurality of inspection tasks and generating global scheduling instructions according to task attributes, airport resource states and real-time airspace information. Each distributed airport is provided with an unmanned plane hangar, a charging facility, a communication terminal and a local control unit and is used for receiving and executing the global scheduling instructions. The unmanned plane cluster comprises a plurality of unmanned planes with autonomous flight and task execution capabilities. The central scheduling module and the plurality of distributed airports are cooperatively matched, global intelligent scheduling of the unmanned plane cluster is realized, optimized instructions are dynamically generated according to real-time task attributes, airport resources and airspace conditions, and the task coordination efficiency and the resource utilization level of large-scale regional inspection are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a fully automated UAV inspection and scheduling system for multi-airport collaboration. Background Technology

[0002] With the widespread application of drone technology in large-scale inspection tasks such as power line inspection, pipeline monitoring, and border patrol, the demand for automated and intelligent scheduling of drone swarms is becoming increasingly urgent.

[0003] Existing inspection systems mostly employ single-airport deployment or simple preset route modes, making it difficult to achieve efficient cross-regional and multi-task collaboration. These systems often lack global optimization capabilities, failing to flexibly adjust based on real-time task priorities, airport resource status, and dynamic airspace changes. This results in low inspection efficiency, insufficient resource utilization, slow response to unexpected tasks, equipment failures, or severe weather, and limited collaborative obstacle avoidance capabilities, thus restricting the application effectiveness of drone swarms in large-scale, complex scenarios. Summary of the Invention

[0004] This invention provides a fully automated UAV inspection and scheduling system for multi-airport collaboration to solve existing technical problems, thereby addressing the difficulty of existing inspection systems in achieving efficient collaborative operations across regions and multiple tasks.

[0005] To solve the above-mentioned technical problems, according to one aspect of the present invention, more specifically, a multi-airport collaborative fully automated unmanned aerial vehicle (UAV) inspection and dispatch system, comprising: The central dispatch module is used to receive multiple inspection tasks and generate global dispatch instructions based on task attributes, airport resource status, and real-time airspace information. Multiple distributed airports, each equipped with a drone hangar, charging facilities, communication terminals, and a local control unit, are used to receive and execute the global scheduling instructions; A drone swarm consists of multiple drones capable of autonomous flight and mission execution. A communication network is used to connect the central dispatch module, various distributed airports, and the UAV cluster to enable real-time transmission of commands and data. The central scheduling module includes: The task analysis and priority assessment unit evaluates the priority of inspection tasks based on their urgency, geographical location, and equipment importance. The airspace potential field calculation unit constructs an airspace potential field based on the priority of all inspection tasks, the real-time position of the UAV, and known obstacle information. This airspace potential field is used to guide the UAV swarm to efficiently cover the task area while avoiding collisions. The dynamic response and rescheduling unit is used to dynamically adjust task priorities, rematch airports and tasks, and update the airspace potential field during the inspection process based on new tasks, UAV malfunctions, weather changes, or abnormal alarms at task points.

[0006] Furthermore, the spatial potential field constructed by the spatial potential field calculation unit... It consists of the superposition of attractive and repulsive potential fields: The attractive potential field is generated by each inspection task point, and its strength is positively correlated with the task priority and negatively correlated with the distance between the UAV and the task point. The repulsive potential field is generated by the current position of each UAV, known static obstacles, and no-fly zones, and is used to prevent collisions between UAVs and between UAVs and obstacles.

[0007] Furthermore, the aforementioned spatial potential field The specific calculation formula is as follows: ; In the above formula, Represents the coordinates of any position in space; Indicates time; This indicates the total number of currently active inspection tasks; Indicates the time of the nth task. Priority; This represents the target location coordinates of the nth task; This represents a small constant to prevent the denominator from being zero; This indicates the total number of drones currently in the air; This represents the constant of the repulsive potential field strength between unmanned aerial vehicles (UAVs). Indicates the first A drone at all times Position coordinates; This indicates the total number of known static obstacles and no-fly zones; This represents the constant of the repulsive potential field strength of the obstacle; Indicates the first The center coordinates of an obstacle or no-fly zone.

[0008] Furthermore, the specific working steps of the central scheduling module are as follows: S1. Assess the priority of the inspection task and construct the airspace potential field based on the priority of the inspection task, the real-time position of the UAV and the known obstacle information. S2. Based on the information of the attractive and repulsive potential fields in the airspace potential field, increase the inspection frequency of the UAV in the attractive potential field region and reduce the inspection frequency in the repulsive potential field region. S3. Locate the UAV between two identical airspace potential fields and perform a priority analysis between the two identical airspace potential fields and the nearest distributed airport. S4. Based on the priority analysis results, control the UAV between the two airspace potential fields to prioritize the inspection of the airspace potential field with higher priority.

[0009] Furthermore, the specific steps for prioritizing two identical airspace potential fields with the nearest distributed airport are as follows: S301. The urgency of the task and the proximity of the airport to obtain the potential fields of two identical airspaces; S302. Input the mission urgency and airport proximity of the two airspace potential fields into the priority model respectively; S303. Based on the priority analysis model, output the corresponding airspace potential field priority, and allow UAVs located between two airspace potential fields to prioritize the airspace potential field with the higher priority for inspection.

[0010] Furthermore, the specific steps for constructing the priority analysis model are as follows: 1) Based on existing cases in the database, obtain the task urgency and airport proximity in the airspace potential field, as well as the actual degree of priority reduction of the airspace potential field after subsequent work; 2) By controlling variables, the relationship between task urgency, airport proximity, and priority reduction was obtained separately; 3) And based on the correlation between task urgency and airport proximity, a priority analysis model is constructed.

[0011] Furthermore, the urgency of the task is assessed based on the priority of the inspection task. The higher the priority, the greater the urgency of the task. The UAV should prioritize going to the airspace potential field area corresponding to the task. The airport proximity is based on the geographical distance between the inspection task point and the nearest distributed airport, reflecting the ease with which the UAV can travel from the airport to the task point.

[0012] Furthermore, the priority analysis model is a deterministic mathematical model that calculates the overall priority based on the urgency of the task and the proximity to the airport; By quantifying and fusing two parameters, mission urgency and airport proximity, a comprehensive evaluation value representing the scheduling priority of mission areas is output, which can provide a quantitative decision-making basis for the selection of UAV inspection direction in multi-mission conflict scenarios.

[0013] Furthermore, the process of the dynamic response and rescheduling unit responding to task point anomaly alarms includes: 1) When an abnormal signal is received in a certain inspection task area, the priority of the corresponding inspection task shall be immediately increased; 2) Based on the priority of the upgraded inspection task, the airspace potential field calculation unit recalculates the airspace potential field, which significantly enhances the attraction potential field of the cliff around the abnormal task point. 3) The updated attractive and repulsive potential field information is sent to the drones in the inspection task area in real time; 4) Based on the new attractive and repulsive potential field information, the affected drones will increase the frequency of inspections in the area.

[0014] This invention provides a fully automated UAV inspection and scheduling system for multi-airport collaboration. Compared with existing technologies, the advantages of this method are as follows: 1. This invention achieves global intelligent scheduling of UAV clusters through the coordinated cooperation of a central scheduling module and multiple distributed airports. It dynamically generates optimized instructions based on real-time task attributes, airport resources and airspace conditions, which significantly improves the task coordination efficiency and resource utilization level of large-scale regional inspections.

[0015] 2. The present invention is based on a guidance mechanism of an airspace potential field model, which integrates task priority, UAV real-time position and obstacle information into a unified potential field function, enabling UAVs to autonomously avoid collisions in complex airspace and gather towards high-priority task areas, thereby achieving dynamic optimization of inspection paths and improvement of coverage efficiency while ensuring flight safety.

[0016] 3. This invention has strong dynamic response and rescheduling capabilities. During the inspection process, it can adjust task priorities and update the airspace potential field in real time based on new tasks, equipment failures, weather changes or abnormal alarms, thereby effectively responding to various emergencies and enhancing the system's adaptability and robustness in changing environments.

[0017] 4. By constructing a priority analysis model based on task urgency and airport proximity, this invention enables the system to quantitatively assess the scheduling priority of each area in multi-task conflict scenarios, thereby providing a scientific basis for the selection of UAV inspection directions and further improving task completion efficiency and overall airport resource utilization. Attached Figure Description

[0018] Figure 1 This is a flowchart of the present invention; Figure 2 This is a graph showing the relationship between the urgency of a task and the degree of priority reduction in this invention. Figure 3 This is a graph showing the relationship between airport proximity and priority reduction in this invention. Figure 4 This is a graph showing the relationship between mission urgency and airport proximity in this invention. Detailed Implementation

[0019] To make the technical solution of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] Example 1 like Figure 1 As shown, according to one aspect of the present invention, a multi-airport collaborative fully automated UAV inspection and scheduling system is provided, comprising: a central scheduling module for receiving multiple inspection tasks and generating global scheduling instructions based on task attributes, airport resource status, and real-time airspace information; multiple distributed airports, each of which is equipped with a UAV hangar, charging facilities, communication terminals, and a local control unit for receiving and executing global scheduling instructions; a UAV swarm comprising multiple UAVs capable of autonomous flight and task execution; and a communication network for connecting the central scheduling module, each distributed airport, and the UAV swarm to achieve real-time transmission of instructions and data. The central scheduling module includes: The task analysis and priority assessment unit evaluates the priority of inspection tasks based on their urgency, geographical location, and equipment importance. The airspace potential field calculation unit constructs an airspace potential field based on the priority of all inspection tasks, the real-time position of the UAV, and known obstacle information. This airspace potential field is used to guide the UAV swarm to efficiently cover the task area while avoiding collisions. The dynamic response and rescheduling unit is used to dynamically adjust task priorities, rematch airports and tasks, and update the airspace potential field during the inspection process based on new tasks, UAV malfunctions, weather changes, or abnormal alarms at task points.

[0021] In this embodiment, the spatial potential field constructed by the spatial potential field calculation unit It consists of the superposition of an attractive potential field and a repulsive potential field. The attractive potential field is generated by each inspection task point, and its strength is positively correlated with the task priority and negatively correlated with the distance of the UAV from the task point. The repulsive potential field is generated by the current position of each UAV, known static obstacles, and no-fly zones, and is used to prevent collisions between UAVs and between UAVs and obstacles.

[0022] Among them, the airspace potential field The specific calculation formula is as follows: ; In the above formula, Represents the coordinates of any position in space; Indicates time; This indicates the total number of currently active inspection tasks; Indicates the time of the nth task. Priority; This represents the target location coordinates of the nth task; This represents a small constant to prevent the denominator from being zero; This indicates the total number of drones currently in the air; This represents the constant of the repulsive potential field strength between unmanned aerial vehicles (UAVs). Indicates the first A drone at all times Position coordinates; This indicates the total number of known static obstacles and no-fly zones; This represents the constant of the repulsive potential field strength of the obstacle; Indicates the first The center coordinates of an obstacle or no-fly zone.

[0023] The process for the dynamic response and rescheduling unit to respond to task point anomaly alarms includes: 1) When an abnormal signal is received in a certain inspection task area, the priority of the corresponding inspection task shall be immediately increased; 2) Based on the priority of the upgraded inspection task, the airspace potential field calculation unit recalculates the airspace potential field, which significantly enhances the attraction potential field of the cliff around the abnormal task point. 3) The updated attractive and repulsive potential field information is sent to the drones in the inspection task area in real time; 4) Based on the new attractive and repulsive potential field information, the affected drones will increase the frequency of inspections in the area.

[0024] By constructing a dynamic airspace potential field model, task priorities, real-time UAV positions, and obstacle information are uniformly quantified as a superposition of attractive and repulsive potential fields, enabling autonomous collaborative scheduling and collision avoidance of UAV swarms in complex airspace. Its core principle is to use a potential field function to guide UAVs to converge towards high-priority task areas in real time, while simultaneously moving them away from other UAVs and obstacles. Combined with a dynamic response mechanism, the potential field and task priorities are updated in real time under abnormal conditions, thereby improving the system's scheduling efficiency and robustness in changing environments, achieving efficient global task coverage and real-time emergency response. Example 2 like Figure 1 As shown, according to one aspect of the present invention, a multi-airport collaborative fully automated UAV inspection and scheduling system is provided, comprising: a central scheduling module for receiving multiple inspection tasks and generating global scheduling instructions based on task attributes, airport resource status, and real-time airspace information; multiple distributed airports, each of which is equipped with a UAV hangar, charging facilities, communication terminals, and a local control unit for receiving and executing global scheduling instructions; a UAV swarm comprising multiple UAVs capable of autonomous flight and task execution; and a communication network for connecting the central scheduling module, each distributed airport, and the UAV swarm to achieve real-time transmission of instructions and data. The specific working steps of the central scheduling module are as follows: S1. Assess the priority of the inspection task and construct the airspace potential field based on the priority of the inspection task, the real-time position of the UAV and the known obstacle information. S2. Based on the information of the attractive and repulsive potential fields in the airspace potential field, increase the inspection frequency of the UAV in the attractive potential field region and reduce the inspection frequency in the repulsive potential field region. S3. Locate the UAV between two identical airspace potential fields and perform a priority analysis between the two identical airspace potential fields and the nearest distributed airport. S4. Based on the priority analysis results, control the UAV between the two airspace potential fields to prioritize the inspection of the airspace potential field with higher priority.

[0025] In this embodiment, the specific steps for prioritizing two identical airspace potential fields with the nearest distributed airport are as follows: S301. The urgency of the task and the proximity of the airport to obtain the potential fields of two identical airspaces; Mission urgency The urgency of a task is assessed based on its priority. Higher priority indicates greater urgency, and the drone should prioritize heading to the corresponding airspace potential field area. The specific formula is as follows: ; In the above formula, Indicates the time of the nth task. Priority; and These are the minimum and maximum priorities among all currently active inspection tasks; For very small positive numbers (e.g.) ( ), to prevent the denominator from being zero.

[0026] Its output range is: 0≤ ≤1. When the task priority is at its minimum. = 0, when it is the maximum value = 1.

[0027] Airport proximity It is based on the geographical distance between the inspection task point and the nearest distributed airport, reflecting the convenience of the drone traveling from the airport to the task point. The specific formula is as follows: ; In the above formula, Let be the Euclidean distance between the nth inspection task point and the nearest distributed airport; This is the distance decay constant, which can be set according to the actual scenario (such as the average distance from all airports to all mission points) to adjust the decay rate.

[0028] Its output range is: 0 < ≤1. When the distance is 0 = 1, as the distance increases Approaching 0.

[0029] S302. Input the mission urgency and airport proximity of the two airspace potential fields into the priority model respectively; S303. Based on the priority analysis model, output the corresponding airspace potential field priority, and allow UAVs located between two airspace potential fields to prioritize the airspace potential field with the higher priority for inspection.

[0030] The specific steps for constructing the priority analysis model are as follows: 1) Based on existing cases in the database, obtain the task urgency and airport proximity in the airspace potential field, as well as the actual degree of priority reduction of the airspace potential field after subsequent work; We obtain the priority reduction degree when the drone flies to the two airspace potential fields from existing cases in the database (i.e., the drone faces the same choice between two airspace potential fields). (Priority reduction degree = {Priority before reduction - Priority after reduction} / Priority after reduction. Its value is between 0 and 1.)

[0031] Furthermore, the corresponding airspace potential fields and their indices are obtained by arranging the priority reduction levels of these existing cases in an arithmetic progression. For example, the task urgency and airport proximity of the airspace potential fields with priority reduction levels of 0.44, 0.46, 0.48, ..., 0.78 are obtained.

[0032] 2) By controlling variables, the relationship between task urgency, airport proximity, and priority reduction was obtained separately; Retrieve the relationship between task urgency and priority reduction from an existing database. Specifically, select 100 pairs of task urgency and priority reduction levels where the airport proximity is 0.5, and denote the priority reduction level as the priority reduction degree. .

[0033] Therefore, the mathematical formula constructed based on the urgency and priority reduction of the task will output... With the urgency of the task The mathematical formula between them is: ; In the above formula, , Used for control With the degree of priority reduction A constant that approaches an approximation.

[0034] For example, based on an analysis of 100 pairs of task urgency and priority reduction, by Figure 2 Able to determine , When, in the formula With the degree of priority reduction Approaching approximation.

[0035] The relationship between airport proximity and priority reduction degree was retrieved from an existing database. Specifically, 100 pairs of airport proximity and priority reduction degrees were selected from the database, where both tasks had an urgency level of 0.5. The degree of priority reduction was then denoted as the priority reduction degree. .

[0036] Therefore, the mathematical formula constructed based on airport proximity and priority reduction will output... Proximity to the airport The mathematical formula between them is: ; In the above formula, , Used for control With the degree of priority reduction A constant that approaches an approximation.

[0037] For example, based on an analysis of 100 pairs of airport proximity and priority reduction, by Figure 3 Able to determine , When, in the formula With the degree of priority reduction Approaching approximation.

[0038] 3) And based on the correlation between task urgency and airport proximity, a priority analysis model is constructed.

[0039] Retrieve the priority reduction level from the database The task urgency and airport proximity are given by airspace potential fields of 0.44, 0.46, 0.48, ..., 0.78. The mathematical formula for constructing a priority analysis model based on the correlation between task urgency and airport proximity is as follows: ; In the above formula, , Used for control With the degree of priority reduction A constant that approaches an approximation.

[0040] For example, based on the degree of priority reduction Analyze the data at values ​​of 0.44, 0.46, 0.48, ..., 0.78. Figure 4 Able to determine , When, in the formula With the degree of priority reduction The results are close to approximate. Therefore, the specific formula for the priority analysis model obtained using existing data is: ; Abbreviated as: ; In the above formula, This indicates the urgency of a mission in two identical airspace potential fields. Airport proximity in two airspace potential fields.

[0041] By training with historical data, we can obtain statistical relationships between mission urgency, airport proximity, and mission completion benefits. We can then construct an interpretable mathematical model to quantitatively assess the scheduling priority of each area when faced with multiple mission conflicts. This will guide UAVs to select the mission direction with the highest overall benefits, thereby improving the overall system's mission completion efficiency and airport resource utilization.

[0042] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A fully automated unmanned aerial vehicle (UAV) inspection and dispatch system for multi-airport collaboration, characterized in that, include: The central dispatch module is used to receive multiple inspection tasks and generate global dispatch instructions based on task attributes, airport resource status, and real-time airspace information. Multiple distributed airports, each equipped with a drone hangar, charging facilities, communication terminals, and a local control unit, are used to receive and execute the global scheduling instructions; A drone swarm consists of multiple drones capable of autonomous flight and mission execution. A communication network is used to connect the central dispatch module, various distributed airports, and the UAV cluster to enable real-time transmission of commands and data. The central scheduling module includes: The task analysis and priority assessment unit evaluates the priority of inspection tasks based on their urgency, geographical location, and equipment importance. The airspace potential field calculation unit constructs an airspace potential field based on the priority of all inspection tasks, the real-time position of the UAV, and known obstacle information. This airspace potential field is used to guide the UAV swarm to efficiently cover the task area while avoiding collisions. The dynamic response and rescheduling unit is used to dynamically adjust task priorities, rematch airports and tasks, and update the airspace potential field during the inspection process based on new tasks, UAV malfunctions, weather changes, or abnormal alarms at task points.

2. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 1, characterized in that: The spatial potential field constructed by the spatial potential field calculation unit It consists of the superposition of attractive and repulsive potential fields: The attractive potential field is generated by each inspection task point, and its strength is positively correlated with the task priority and negatively correlated with the distance between the UAV and the task point. The repulsive potential field is generated by the current position of each UAV, known static obstacles, and no-fly zones, and is used to prevent collisions between UAVs and between UAVs and obstacles.

3. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 2, characterized in that: The spatial potential field The specific calculation formula is as follows: ； In the above formula, Represents the coordinates of any position in space; Indicates time; This indicates the total number of currently active inspection tasks; Indicates the time of the nth task. Priority; This represents the target location coordinates of the nth task; This represents a small constant to prevent the denominator from being zero; This indicates the total number of drones currently in the air; This represents the constant of the repulsive potential field strength between unmanned aerial vehicles (UAVs). Indicates the first A drone at all times Position coordinates; This indicates the total number of known static obstacles and no-fly zones; This represents the constant of the repulsive potential field strength of the obstacle; Indicates the first The center coordinates of an obstacle or no-fly zone.

4. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 1, characterized in that: The specific working steps of the central scheduling module are as follows: S1. Assess the priority of the inspection task and construct the airspace potential field based on the priority of the inspection task, the real-time position of the UAV and the known obstacle information. S2. Based on the information of the attractive and repulsive potential fields in the airspace potential field, increase the inspection frequency of the UAV in the attractive potential field region and reduce the inspection frequency in the repulsive potential field region. S3. Locate the UAV between two identical airspace potential fields and perform a priority analysis between the two identical airspace potential fields and the nearest distributed airport. S4. Based on the priority analysis results, control the UAV between the two airspace potential fields to prioritize the inspection of the airspace potential field with higher priority.

5. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 4, characterized in that: The specific steps for prioritizing two identical airspace potential fields with the nearest distributed airport are as follows: S301. The urgency of the task and the proximity of the airport to obtain the potential fields of two identical airspaces; S302. Input the mission urgency and airport proximity of the two airspace potential fields into the priority model respectively; S303. Based on the priority analysis model, output the corresponding airspace potential field priority, and allow UAVs located between two airspace potential fields to prioritize the airspace potential field with the higher priority for inspection.

6. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 5, characterized in that: The specific steps for constructing the priority analysis model are as follows: 1) Based on existing cases in the database, obtain the task urgency and airport proximity in the airspace potential field, as well as the actual degree of priority reduction of the airspace potential field after subsequent work; 2) By controlling variables, the relationship between task urgency, airport proximity, and priority reduction was obtained separately; 3) And based on the correlation between task urgency and airport proximity, a priority analysis model is constructed.

7. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 5, characterized in that: The urgency of the task is assessed based on the priority of the inspection task. The higher the priority, the greater the urgency of the task. The UAV should prioritize going to the airspace potential field area corresponding to the task. The airport proximity is based on the geographical distance between the inspection task point and the nearest distributed airport, reflecting the ease with which the UAV can travel from the airport to the task point.

8. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 5, characterized in that: The priority analysis model is a deterministic mathematical model that calculates the overall priority based on the urgency of the task and the proximity to the airport. By quantifying and fusing two parameters, mission urgency and airport proximity, a comprehensive evaluation value representing the scheduling priority of mission areas is output, which can provide a quantitative decision-making basis for the selection of UAV inspection direction in multi-mission conflict scenarios.

9. The multi-airport collaborative fully automated UAV inspection and dispatch system according to claim 1, characterized in that: The process of dynamic response and rescheduling unit responding to task point anomaly alarms includes: 1) When an abnormal signal is received in a certain inspection task area, the priority of the corresponding inspection task shall be immediately increased; 2) Based on the priority of the upgraded inspection task, the airspace potential field calculation unit recalculates the airspace potential field, which significantly enhances the attraction potential field of the cliff around the abnormal task point. 3) The updated attractive and repulsive potential field information is sent to the drones in the inspection task area in real time; 4) Based on the new attractive and repulsive potential field information, the affected drones will increase the frequency of inspections in the area.

Images