System for detecting, deducing, analyzing and solving flight conflict of unmanned aerial vehicle

Abstract

The invention provides an unmanned aerial vehicle flight conflict detection, deduction analysis and solution system. The system comprises a data acquisition and preprocessing module which is used for acquiring and preprocessing low-altitude basic environment data, flight plan data and unmanned aerial vehicle real-time operation data; the unmanned aerial vehicle operation risk assessment module is used for realizing multi-dimensional unmanned aerial vehicle flight environment comprehensive risk assessment analysis and searching for an optimal solution of flight conflicts in the flight process of the unmanned aerial vehicle; the unmanned aerial vehicle operation risk alarm module is used for providing an unmanned aerial vehicle risk alarm service and an unmanned aerial vehicle risk solution by combining different monitoring scenes and risk configurations of the system; and the unmanned aerial vehicle deduction simulation module is used for simulating different unmanned aerial vehicle flight scenes. According to the invention, the flight safety and management efficiency of the unmanned aerial vehicle in the low-altitude environment are realized by combining the beforehand deduction optimization and the in-event real-time conflict monitoring of the flight plan of the unmanned aerial vehicle, the burden of manual monitoring is reduced, and the method has wide application prospect and practical value.

Description

Technical Field

[0001] The present invention relates to the technical field of digital data management systems, and in particular to a system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts. Background Art

[0002] As the performance of drones continues to improve and their application scope continues to expand, their application areas are very wide, covering military, civil, commercial and other aspects. For example, drones can be used for aerial photography and video in the entertainment and film fields, for monitoring and spraying crops in the agricultural field, for express delivery in the logistics field, for aerial reconnaissance and rescue assistance in disaster relief, for monitoring and patrol law enforcement in urban management, and for inspection in industrial environments. Drones are widely used in multiple business fields, and their importance and use are increasing. However, this also brings new problems. Because airspace resources are limited, the large-scale application of drones in the same airspace will face more flight safety issues, such as drone collisions and intrusions into no-fly zones. Especially in dense low-altitude environments, how to effectively monitor and manage drone operations and avoid drone operation risks has become an urgent problem to be solved.

[0003] Existing drone operation monitoring mostly relies on manual work, and there is a serious lag from the occurrence to the discovery and final disposal of operational risks, which makes it impossible to timely discover the risks that may occur during the operation of drones. At the same time, drone operation monitoring basically conducts flight monitoring from a two-dimensional or three-dimensional spatial perspective, lacks information on time and flight operations, cannot fully understand the flight status of drones, and cannot effectively deal with complex three-dimensional spatial environments and airspace flight environments, and is prone to ignoring potential flight risks. Summary of the invention

[0004] In view of this, in order to achieve the above-mentioned purpose of the invention, the present invention provides a system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts, the system comprising:

[0005] Data acquisition and preprocessing module: used to acquire and preprocess low-altitude basic environment data, flight plan data, and real-time operation data of UAVs;

[0006] UAV operation risk assessment module: It is used to combine flight trajectory prediction, collision grid detection, conflict space analysis, space-time grid flight time analysis and real-time analysis of flight conflict events during the flight of UAVs, and output the future flight conflict events of UAVs and the optimal solution to flight conflict events;

[0007] Drone operation risk alarm module: used to provide drone risk alarm services and drone risk solutions based on flight conflict events output by the system in real time, combined with different monitoring scenarios and risk configurations of the system;

[0008] UAV simulation module: used to simulate flight plans and potential flight conflicts, and simulate different UAV flight scenarios.

[0009] Furthermore, the data acquisition and preprocessing module includes:

[0010] Low-altitude basic environment data acquisition unit: used to acquire geographic environment data and airspace data to form air-ground information fusion data, and combine geographic space grid technology, system flight business data, historical airspace flight data and future predicted airspace flight data to output airspace grids with multi-dimensional attributes;

[0011] Flight plan data acquisition unit: used to acquire UAV flight plan data, analyze the time, space and low-altitude flight business attributes of the UAV flight plan data, fuse the information data, and perform rasterization processing, that is, perform spatiotemporal grid matching and binding on the flight routes or flight areas in the UAV flight plan, and determine the associated flight spatiotemporal grid data;

[0012] UAV real-time operation data acquisition unit: used to obtain the real-time flight trajectory data of the UAV and the real-time meteorological data of the flight space-time grid data, filter and fuse them through the data fusion algorithm to form flight data features and perform data standardization processing.

[0013] Furthermore, the drone operation risk assessment module includes:

[0014] Flight trajectory prediction unit: used to predict the future flight trajectory of the UAV through the multi-dimensional airspace grid, flight space-time grid data and flight data features;

[0015] Collision grid detection unit: used to detect whether there are intersecting or close space-time grids in the future flight trajectory of the drone. For the space-time grids with intersecting or close space-time grids in the future flight trajectory of the drone, the space-time conflict analysis is performed in combination with the flight business attributes to determine whether there is a space-time grid that may collide with the future flight trajectory of the drone;

[0016] Conflict space analysis unit: used to perform spatial conflict analysis on space-time grids with collisions;

[0017] Conflict time analysis unit: used to divide the space-time grid where collision occurs into conflict time divisions;

[0018] Flight conflict event real-time analysis unit: used to determine future flight conflict events and find the best solution to them.

[0019] Furthermore, the future flight trajectory of the drone is predicted, specifically:

[0020] S11. Clean and extract features from historical flight data, combine multi-dimensional attribute airspace grid, flight space-time grid data and flight data features, and establish a Gaussian mixture prediction model for UAV flight trajectory prediction;

[0021] S12, define the disturbance of the drone itself and the disturbance of the airspace environment, combine with the Gaussian mixture prediction model, and output the flight trajectory prediction data;

[0022] S13. Continuously compare the predicted flight trajectory data with the actual flight trajectory data to evaluate and adjust the Gaussian mixture prediction model.

[0023] Furthermore, a spatial conflict analysis is performed on the space-time grid where the drones collide. Specifically, the potential conflict points in the horizontal and vertical directions of the three-dimensional space of the space-time grid where the drones collide are analyzed and recorded through a spatial topology analysis algorithm, that is, the geographic location coordinate information, height information and three-dimensional oblique image geographic information are combined into a three-dimensional space for analysis.

[0024] Further, the future flight conflict events are determined, specifically:

[0025] S21. Based on the current UAV flight status, combined with the flight plan data, real-time flight data and airspace grid data, a reachable set analysis algorithm is used to determine whether there is a conflict between the UAV and its relative position at a certain time in the future;

[0026] S22, continuously receiving the actual flight data and the real-time airspace environment information in real time, comparing the judgment result of step S21 with the actual flight data, adjusting the reachable set analysis algorithm in real time, and analyzing the set of future flight trajectories that the UAV may reach within a certain time range;

[0027] S23. Analyze all points of the future flight trajectory set using the A* algorithm, exclude data that is impossible to reach by the future flight trajectory set, and provide feedback to update the existing reachable data set to determine future flight conflict events.

[0028] Further, the optimal solution to the flight conflict is found for the analyzed flight conflict event, specifically:

[0029] S31, using the flight conflict event as initial information, initializing the conflicting space-time grid, obstacles and flight data as information on each path;

[0030] S32, summarizing historical flight trajectory data and current flight data in the airspace, and decomposing conflicting paths into multiple flight segments according to probability rules;

[0031] S33, finding an optimal path consisting of multiple flight segments that can avoid conflicts based on the pheromones on each conflicting path through an ant colony algorithm;

[0032] S34, combining the current flight speed of the UAV and the airspace environment information, assigning a time attribute to the starting point of each optimal path that can avoid conflicts and the flight segment on the original analysis path that has conflicts;

[0033] S35. Adopt annealing simulation algorithm, take optimal path, flight time, space-time grid and real-time flight information as data input, take airspace conflict event as stop condition, and find the global optimal solution in time and path through repeated iteration.

[0034] Furthermore, the drone operation risk alarm module includes:

[0035] Risk Alarm Unit: used to provide drone risk alarm service. When the risk value exceeds the threshold, the system will immediately send an alarm message.

[0036] Risk resolution unit: used to provide a drone risk solution, wherein the drone risk solution is used to instruct the drone to adjust at least one of the flight altitude, flight speed and flight route.

[0037] Furthermore, the UAV simulation module includes:

[0038] Simulation unit: used to combine the data of the UAV operation risk assessment module and the UAV operation risk alarm module to simulate flight scenarios under different flight conditions;

[0039] Visual interface unit: used to provide users with a visual operation interface to display drone risk assessment analysis results and solutions.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention provides a system for detecting, deducing, analyzing and resolving unmanned aerial vehicle flight conflicts. The system can more accurately locate and dynamically analyze airspace flight data by adding time dimensions and space flight business attributes, and has a more comprehensive perspective, higher precision, more efficient data processing capabilities and better business decision support. At the same time, it can realize pre-flight environment analysis and simulation deduction before unmanned aerial vehicle flight, as well as in-flight monitoring and real-time conflict event analysis during unmanned aerial vehicle flight, and provide effective risk resolution solutions. Through the superposition application of system automated deduction simulation scenarios and conflict analysis algorithms, the system effectively improves the safety and management efficiency of unmanned aerial vehicle flight in low-altitude environments, and resolves the risk of flight conflicts, reduces the burden of manual monitoring, and has broad application prospects and practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 It is a schematic diagram of the overall structure of a system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts provided by an embodiment of the present invention;

[0044] Figure 2 It is a flowchart of predicting the future flight trajectory of a drone in a drone operation risk assessment module provided by an embodiment of the present invention;

[0045] Figure 3 It is a flow chart of flight conflict event analysis in a UAV operation risk assessment module provided by an embodiment of the present invention;

[0046] Figure 4 It is a flow chart of the optimal solution for finding flight conflicts in the UAV operation risk assessment module provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The enumerated embodiments are only used to explain the present invention and are not used to limit the scope of the present invention.

[0048] Reference Figure 1 This embodiment provides a system for detecting, analyzing and resolving UAV flight conflicts, and the system includes:

[0049] Data acquisition and preprocessing module: used to acquire and preprocess low-altitude basic environment data, flight plan data and real-time operation data of UAV.

[0050] The data acquisition and preprocessing modules include:

[0051] Low-altitude basic environment data acquisition unit: used to acquire geographic environment data and airspace data to form air-ground information fusion data, and combine geographic space grid technology, system flight business data, historical airspace flight data and future predicted airspace flight data to output airspace grids with multi-dimensional attributes.

[0052] In this embodiment, the system will obtain the geographical environment data and airspace data to form air-ground information fusion data. The airspace data includes suitable flight, no-fly and control area data. The air-ground information fusion data includes but is not limited to facility geographical data, oblique images, airspace electronic fences and other information. The facility geographical data and airspace electronic fence data support the import of data in csv, xml, kml, kmz and other files, and the oblique image data supports the import and loading of data in OSGB, OBJ, FBX, STL, 3Dtiles and other formats. By combining geographic space grid technology, system flight business data, historical airspace flight data and future predicted airspace flight data, the system will output a multi-dimensional airspace grid, that is, compared with the traditional multi-dimensional airspace grid designed based on the three-dimensional space element structure of low-altitude airspace restrictions, it also contains flight business attributes in addition to time and three-dimensional space. The flight business attributes integrate the flight volume, flight risk factor, plan information, noise limit, speed limit and regional wind resistance information, and refine the flight time and space grids at different levels of the airspace, and encode each grid with a unique and unique identification code.

[0053] Flight plan data acquisition unit: used to obtain UAV flight plan data, analyze the time, space and low-altitude flight business attributes of the UAV flight plan data, fuse the information data, and perform rasterization processing, that is, perform spatiotemporal grid matching and binding on the flight routes or flight areas in the UAV flight plan, and determine the associated flight spatiotemporal grid data.

[0054] In this embodiment, the unit mainly obtains and preprocesses the future UAV flight plan data. The system analyzes the time, space and low-altitude flight business attributes of the UAV flight plan and integrates the information data through the collected UAV flight plan. First, the UAV flight plan data is filled in by manual entry in the system or the flight plan data is imported through an Excel table according to the data template format provided by the system. Secondly, the flight route or flight area in the UAV flight plan is matched and bound to the space-time grid, and the space-time grid bound to multiple UAV flight plans at the same time is combined with the flight business to mark different degrees of busy, crowded and idle. Thirdly, according to the flight plan associated with the currently flying UAV, the planned flight trajectory of all flying UAVs is obtained; combined with the flight trajectory data of the currently flying UAV and its associated flight plan data, the starting time range of each UAV flight is analyzed and determined, and the flight time of the UAV in each space-time grid is determined; combined with the above data, all associated space-time grids are determined, and extended to confirm the space-time grid available for flight business. Finally, according to the framed data scope, the UAV flight plan and flight space-time raster data that meet the scope conditions are screened; the UAV flight plan data includes the UAV type, planned flight airspace / flight route, planned flight time, flight mission nature and plan approval status; the flight space-time raster data includes spatial coordinates, spatial size, spatial business attributes and flight time collection data.

[0055] UAV real-time operation data acquisition unit: used to obtain the real-time flight trajectory data of the UAV and the real-time meteorological data of the flight space-time grid data, filter and fuse the flight data features through the data fusion algorithm, and perform data standardization processing. Provide real-time operation data support for subsequent UAV operation risk prediction.

[0056] In this embodiment, the real-time flight trajectory data of the drone is obtained by connecting to the system data interface of the drone operator or the drone manufacturer, the drone positioning terminal, the drone detection equipment, etc., including but not limited to: longitude, latitude, altitude, time, horizontal speed, vertical speed, pitch axis angle, roll axis angle, yaw axis angle, battery remaining power, etc. The real-time meteorological data of the flight time-space grid data obtains cubic meter-level time-space meteorological data through the meteorological system data interface, and associates and combines new time-space meteorological data with the time-space grid. The meteorological data includes but is not limited to: temperature, humidity, air pressure, wind speed, visibility, etc. In the case of multiple data sources for the same drone, the unit will analyze the multiple data, and filter and fuse the multiple data through the data fusion algorithm to form the most accurate flight data features. According to the data format requirements of the system, the flight data features are standardized and processed, and the flying drones are associated with the drone flight plans one by one through the flight data features.

[0057] Drone operation risk assessment module: It is used to combine flight trajectory prediction, collision grid detection, conflict space analysis, space-time grid flight time analysis and real-time analysis of flight conflict events during the flight of drones, and output the optimal solution to the flight conflict events that will occur in the future. Compared with the traditional risk assessment and analysis method based on flight trajectory information, this system not only combines the current flight space-time environment information and flight trajectory information, but also integrates the future flight space-time environment information and the real-time change information of the drone flight trajectory, so as to achieve more accurate, efficient and intelligent flight risk assessment and analysis.

[0058] The drone operation risk assessment module includes:

[0059] Flight trajectory prediction unit: used to predict the future flight trajectory of the drone through multi-dimensional airspace grid, flight space-time grid data and flight data characteristics. The future flight trajectory is output by comprehensively considering the current position, speed, acceleration, power, disturbance parameters and meteorological information of the drone.

[0060] In this embodiment, refer to Figure 2 , predict the future flight trajectory of the drone, specifically:

[0061] S11. Clean and extract features from historical flight data, combine multi-dimensional airspace grids, flight space-time grid data, and flight data features, and establish a Gaussian mixture prediction model for UAV flight trajectory prediction.

[0062] S12. Define the disturbance of the drone itself and the disturbance of the airspace environment, combine with the Gaussian mixture prediction model, and output the flight trajectory prediction data.

[0063] S13. Continuously compare the predicted flight trajectory data with the actual flight trajectory data to evaluate and adjust the Gaussian mixture prediction model.

[0064] The future flight trajectory of the UAV is predicted based on the Gaussian mixture model. The flight simulation is performed by increasing the UAV's own disturbance and the environmental disturbance. The advantage is that the predicted flight trajectory comprehensively considers the factors of the UAV itself and the environment, and will be closer to the actual flight trajectory.

[0065] Collision grid detection unit: used to detect whether there are intersecting or close space-time grids in the future flight trajectory of the drone. For space-time grids with intersecting or close space-time grids in the future flight trajectory of the drone, space-time conflict analysis is performed in combination with flight business attributes to determine whether there is a possibility of collision with space-time grids in the future flight trajectory of the drone.

[0066] Conflict spatial analysis unit: used to perform spatial conflict analysis on space-time grids where conflicts exist.

[0067] The spatial conflict analysis of the space-time grid where the UAVs collide is performed specifically by analyzing and recording the potential conflict points in the horizontal and vertical directions of the three-dimensional space of the space-time grid where the UAVs collide through a spatial topology analysis algorithm, that is, combining the geographic location coordinate information, height information and three-dimensional oblique image geographic information into a three-dimensional space for analysis.

[0068] Conflict time analysis unit: used to divide the space-time grid where there is a collision into conflict moments. By combining flight plan data, actual flight data and space-time grid data, the different moments when the drone stays in the space-time grid are finely divided, providing a time dimension analysis basis for flight conflict events.

[0069] Flight conflict event real-time analysis unit: used to determine future flight conflict events and find the best solution to them.

[0070] Reference Figure 3 , determine the future flight conflict events, specifically:

[0071] S21. Based on the current UAV flight status, combined with flight plan data, real-time flight data and airspace grid data, a reachable set analysis algorithm is used to determine whether there is a conflict between the UAV and its relative position at a certain moment in the future.

[0072] S22. Continuously receive the actual flight data and real-time airspace environment information in real time, compare the judgment result of step S21 with the actual flight data, adjust the reachable set analysis algorithm in real time, and analyze the set of future flight trajectories that the drone may reach within a certain time range.

[0073] S23, using the A* algorithm to analyze all points of the future flight trajectory set, exclude data that is impossible to reach in the future flight trajectory set, and feedback to update the existing reachable data set to determine the flight conflict events that will occur in the future. The points include flight space-time grid data and flight trajectory prediction data.

[0074] The advantage of this real-time analysis method for flight conflict events is that the analysis process not only takes into account the flight dynamic characteristics of the UAV and the uncertainty of the flight space-time environment, but also makes full use of the trajectory prediction ability of the reachable set algorithm and the efficient path search ability unique to the A* algorithm on the basis of the fusion of multiple airspace information. This makes the predicted flight trajectory not only closer to the actual flight trajectory, but also outputs the predicted trajectory data more efficiently and stably, providing a reliable, real-time and accurate flight trajectory data basis for the real-time analysis of flight conflict events, and realizing progressive analysis and correction to determine future flight conflict events.

[0075] Reference Figure 4 , find the optimal solution to the flight conflict for the analyzed flight conflict event, specifically:

[0076] S31, using the flight conflict event as initial information, initializing the conflicting space-time grid, obstacles and flight data as information on each path.

[0077] S32. Summarize historical flight trajectory data and current flight data in the airspace, and decompose conflicting paths into multiple flight segments according to probability rules.

[0078] S33, using an ant colony algorithm to find an optimal path that can avoid conflicts and is composed of multiple flight segments according to the pheromones on each conflicting path.

[0079] S34. In combination with the current flight speed of the UAV and the airspace environment information, a time attribute is assigned to the starting point of each optimal path that can avoid conflicts and the flight segment on the original analysis path that has conflicts.

[0080] S35. Adopt annealing simulation algorithm, take optimal path, flight time, space-time grid and real-time flight information as data input, take airspace conflict event as stop condition, and find the global optimal solution in time and path through repeated iteration.

[0081] In this embodiment, for the analyzed flight conflict events, the system follows the principle of minimum robustness, divides the space-time grid where the conflict point is located into three sections: front, middle and back, and dynamically plans the distance of the flying drone and the take-off time or route of the non-flying drone, and finds the optimal solution to the flight conflict by combining the Ant Colony Optimization (ACO) and the Simulated Annealing algorithm. Compared with the solution of flight conflict events using only one of the algorithms, the advantage of the combination of the two algorithms is that the ant colony algorithm can provide a global optimization perspective of drone flight in the flight airspace and find multiple feasible flight paths for selection, while the annealing simulation algorithm can repeatedly iterate to find the global optimal solution in multiple solutions, which not only improves the efficiency and reliability of solving flight conflict analysis, but also provides flexible, diverse and reliable flight conflict solutions for drones. The solutions include but are not limited to adjusting the flight time, route or other flight parameters of the drone to avoid flight conflicts and flight collision risks, and ensure the safe and efficient completion of drone flights.

[0082] Drone operation risk alarm module: used to provide drone risk alarm services and drone risk solutions based on the flight conflict events output by the system in real time, combined with different monitoring scenarios and risk configurations of the system.

[0083] The UAV operation risk alarm module includes:

[0084] Risk Alarm Unit: It is used to provide drone risk alarm service. When the risk value exceeds the threshold, the system will immediately send an alarm message. This unit determines whether the drone has a risk of flight conflict and collision in four-dimensional space, and issues an alarm prompt. The alarm message is determined based on the risk analysis data to determine whether it will be released. When the risk value exceeds the threshold, the system will immediately send an alarm message to make necessary adjustments or emergency responses. The risk threshold can be configured with rules to adapt to different monitoring scenarios. Alarms can be issued through system pop-up boxes, icon tags, SMS reminders, email reminders, corporate WeChat messages, etc., to ensure that the alarm information can be transmitted to relevant personnel in a timely and accurate manner.

[0085] Risk resolution unit: used to provide drone risk solutions, which are used to instruct drones to adjust at least one of the flight altitude, flight speed, and flight route. This unit combines the rule engine and machine learning model to recommend solutions after the drone encounters operational risks. Based on historical data and machine learning models, combined with risk assessment values, it intelligently recommends suitable risk solutions and provides a variety of solution options. Users can choose the most suitable solution based on actual conditions. All alarm events are recorded, including the content, time, and selected solutions of the alarm. These records can be used for future analysis and improvement. Learn from disposal records and new data, continuously optimize the recommendation algorithm, and combine expert knowledge and rule engines to improve the accuracy and reliability of recommendations.

[0086] UAV simulation module: used to simulate flight plans and potential flight conflicts, and simulate different UAV flight scenarios.

[0087] The UAV simulation module includes:

[0088] Simulation unit: used to combine the data of the UAV operation risk assessment module and the UAV operation risk alarm module to simulate flight scenarios under different flight conditions. Combined with the above system function data, simulated flight data is generated, flight data under different flight conditions are simulated, and the development process of conflict flight is simulated and analyzed. At the same time, the results of conflicts of different severity are simulated and evaluated to form a visual conflict analysis result. The above optimization algorithm is used to find the optimal solution for different simulated conflict analysis results, including adjusting the flight altitude, flight speed, flight route, etc., to avoid or reduce the risk probability of flight conflicts.

[0089] Visual interface unit: used to provide users with a visual operation interface to display the risk assessment analysis results and solutions of drones. Provide users with a friendly visual operation interface to display the risk analysis results and solutions of drone operations, so that users can make decisions and adjust flight plans. At the same time, it provides a real-time monitoring page and drone control interface to monitor the flight status in real time during the flight of the drone, dynamically visualize the conflict analysis results and solutions, so that users can adjust the drone flight plan in time to deal with emergencies.

[0090] As a preferred embodiment, after using this system in the airspace control system of a certain oil plant, compared with the traditional conflict detection algorithm used before, it has significant advantages in patrol and security operations, and solves the actual flight operation problems such as the untimely discovery of conflict detection problems, the lack of appropriate solutions when conflicts occur, and the inability to detect conflicts in real time. The risk of flight operation conflicts is reduced by more than half compared with the original, the accuracy of flight conflict positioning and the advance warning time of flight conflicts are significantly improved and improved, and the application rate of providing effective solutions is greatly increased. The following is a specific description of the advantages and problems solved in the application scenario:

[0091] This system takes into account the three-dimensional space (X, Y, Z) and time dimension (T), and also comprehensively considers the dynamic factors in the current airspace environment, such as movable obstacles, climate, the nature of drone operations, flight speed and predicted flight trajectory, etc. It can accurately calculate the relative position and movement trajectory of aircraft in all dimensions, and can predict the overall risk environment of the airspace where the drone is located for early detection and avoidance of potential conflicts. In inspection and security operations, drones need to cruise at different altitudes and complex terrains, and the routes of security operations may change with the impact of events. This system can more accurately predict flight paths, calculate conflict risks in real time, avoid potential collision risks with other aircraft or buildings, and significantly improve the safety and reliability of operations.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for detecting, analyzing and resolving UAV flight conflicts, characterized in that: The system comprises: Data acquisition and preprocessing module: used to acquire and preprocess low-altitude basic environment data, flight plan data, and real-time operation data of UAVs; UAV operation risk assessment module: It is used to combine flight trajectory prediction, collision grid detection, conflict space analysis, space-time grid flight time analysis and real-time analysis of flight conflict events during the flight of UAVs, and output the future flight conflict events of UAVs and the optimal solution to flight conflict events; Drone operation risk alarm module: used to provide drone risk alarm services and drone risk solutions based on flight conflict events output by the system in real time, combined with different monitoring scenarios and risk configurations of the system; UAV simulation module: used to simulate flight plans and potential flight conflicts, and simulate different UAV flight scenarios.

2. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 1, characterized in that: The data acquisition and preprocessing module includes: Low-altitude basic environment data acquisition unit: used to acquire geographic environment data and airspace data to form air-ground information fusion data, and combine geographic space grid technology, system flight business data, historical airspace flight data and future predicted airspace flight data to output airspace grids with multi-dimensional attributes; Flight plan data acquisition unit: used to acquire UAV flight plan data, analyze the time, space and low-altitude flight business attributes of the UAV flight plan data, fuse the information data, and perform rasterization processing, that is, perform spatiotemporal grid matching and binding on the flight routes or flight areas in the UAV flight plan, and determine the associated flight spatiotemporal grid data; UAV real-time operation data acquisition unit: used to obtain the real-time flight trajectory data of the UAV and the real-time meteorological data of the flight space-time grid data, filter and fuse them through the data fusion algorithm to form flight data features and perform data standardization processing.

3. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 2, characterized in that: The drone operation risk assessment module includes: Flight trajectory prediction unit: used to predict the future flight trajectory of the UAV through the multi-dimensional airspace grid, flight space-time grid data and flight data features; Collision grid detection unit: used to detect whether there are intersecting or close space-time grids in the future flight trajectory of the drone. For the space-time grids with intersecting or close space-time grids in the future flight trajectory of the drone, the space-time conflict analysis is performed in combination with the flight business attributes to determine whether there is a space-time grid that may collide with the future flight trajectory of the drone; Conflict space analysis unit: used to perform spatial conflict analysis on space-time grids with collisions; Conflict time analysis unit: used to divide the space-time grid where collision occurs into conflict time divisions; Flight conflict event real-time analysis unit: used to determine future flight conflict events and find the best solution to them.

4. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 3 is characterized in that: Predict the future flight trajectory of the drone, specifically: S11. Clean and extract features from historical flight data, combine multi-dimensional attribute airspace grid, flight space-time grid data and flight data features, and establish a Gaussian mixture prediction model for UAV flight trajectory prediction; S12, define the disturbance of the drone itself and the disturbance of the airspace environment, combine with the Gaussian mixture prediction model, and output the flight trajectory prediction data; S13. Continuously compare the predicted flight trajectory data with the actual flight trajectory data to evaluate and adjust the Gaussian mixture prediction model.

5. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 3 is characterized in that: The spatial conflict analysis of the space-time grid where the UAVs collide is performed specifically by analyzing and recording the potential conflict points in the horizontal and vertical directions of the three-dimensional space of the space-time grid where the UAVs collide through a spatial topology analysis algorithm, that is, combining the geographic location coordinate information, height information and three-dimensional oblique image geographic information into a three-dimensional space for analysis.

6. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 3, characterized in that: Determine the future flight conflict event, specifically: S21. Based on the current UAV flight status, combined with the flight plan data, real-time flight data and airspace grid data, a reachable set analysis algorithm is used to determine whether there is a conflict between the UAV and its relative position at a certain time in the future; S22, continuously receiving the actual flight data and the real-time airspace environment information in real time, comparing the judgment result of step S21 with the actual flight data, adjusting the reachable set analysis algorithm in real time, and analyzing the set of future flight trajectories that the UAV may reach within a certain time range; S23. Analyze all points of the future flight trajectory set using the A* algorithm, exclude data that is impossible to reach by the future flight trajectory set, and provide feedback to update the existing reachable data set to determine future flight conflict events.

7. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 3, characterized in that: Find the optimal solution to the flight conflict for the analyzed flight conflict event, specifically: S31, using the flight conflict event as initial information, initializing the conflicting space-time grid, obstacles and flight data as information on each path; S32, summarizing historical flight trajectory data and current flight data in the airspace, and decomposing conflicting paths into multiple flight segments according to probability rules; S33, finding an optimal path consisting of multiple flight segments that can avoid conflicts based on the pheromones on each conflicting path through an ant colony algorithm; S34, combining the current flight speed of the UAV and the airspace environment information, assigning a time attribute to the starting point of each optimal path that can avoid conflicts and the flight segment on the original analysis path that has conflicts; S35. Adopt annealing simulation algorithm, take optimal path, flight time, space-time grid and real-time flight information as data input, take airspace conflict event as stop condition, and find the global optimal solution in time and path through repeated iteration.

8. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 1, characterized in that: The UAV operation risk alarm module includes: Risk Alarm Unit: used to provide drone risk alarm service. When the risk value exceeds the threshold, the system will immediately send an alarm message. Risk resolution unit: used to provide a drone risk solution, wherein the drone risk solution is used to instruct the drone to adjust at least one of the flight altitude, flight speed and flight route.

9. The system for detecting, analyzing and resolving unmanned aerial vehicle flight conflicts according to claim 1, characterized in that: The UAV simulation module includes: Simulation unit: used to combine the data of the UAV operation risk assessment module and the UAV operation risk alarm module to simulate flight scenarios under different flight conditions; Visual interface unit: used to provide users with a visual operation interface to display drone risk assessment analysis results and solutions.

Images