Autonomous conflict resolution method and device for unmanned aerial vehicle

Abstract

The invention provides an autonomous conflict resolution method and device for an unmanned aircraft, and relates to the technical field of aircraft control, and the method comprises the steps: determining a first safety protection region of a current aircraft in a three-dimensional space grid based on a first current position and a first flight parameter of the current aircraft; determining a second safety protection area of the adjacent aircraft in the three-dimensional space grid based on a second current position and a second flight parameter of the adjacent aircraft; calculating a relative motion trend between the current aircraft and the adjacent aircraft to obtain a trend value; under the condition that the trend value is smaller than a preset threshold value, the conflict risk between the current aircraft and the adjacent aircraft is determined based on the first safety protection area and the second safety protection area; and based on the conflict risk, performing conflict resolution. According to the autonomous conflict resolution method and device for the unmanned aircraft provided by the invention, the efficiency and real-time performance of autonomous conflict resolution of the aircraft are improved.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle control technology, and in particular to an autonomous conflict resolution method and apparatus for unmanned aerial vehicles. Background Technology

[0002] With the continuous growth in the number of unmanned aerial vehicles (UAVs) in low-altitude airspace and the increasing density of airspace use, especially in complex environments such as cities and industrial parks, the risk of flight conflicts between UAVs has increased significantly.

[0003] Existing unmanned aerial vehicle (UAV) conflict detection and avoidance technologies mainly rely on centralized management or global scanning. However, in the current context of high-frequency, multi-aircraft collaborative operations, the following shortcomings still exist: On the one hand, centralized management relies on manual judgment and intervention, resulting in low automation and low efficiency in UAV conflict resolution; on the other hand, global scanning generally relies on global computing models, which are computationally intensive and have high response latency when facing large-scale concurrent flight missions, making it difficult to meet real-time requirements. Moreover, most models lack comprehensive consideration of factors such as the UAV's communication status and dynamic performance. Especially when the UAV loses contact or communication is interrupted, the safety interval cannot be dynamically adjusted, leading to a decrease in conflict detection accuracy and consequently, an inability to resolve conflicts in a timely manner. Summary of the Invention

[0004] This invention provides an autonomous conflict resolution method and apparatus for unmanned aerial vehicles (UAVs) to solve the technical problems of poor efficiency and real-time performance in the prior art of autonomous conflict resolution for UAVs.

[0005] This invention provides an autonomous conflict resolution method for unmanned aerial vehicles, comprising the following steps: Based on the current position and flight parameters of the aircraft, a first safe protection zone for the aircraft in a three-dimensional spatial grid is determined; the three-dimensional spatial grid is constructed based on a preset aircraft flight area. Based on the second current position and second flight parameters of the neighboring aircraft, a second safety protection zone for the neighboring aircraft is determined in a three-dimensional spatial grid; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. Calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain the trend value; If the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; Based on the aforementioned conflict risk, conflict resolution is carried out; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

[0006] According to the present invention, an autonomous conflict resolution method for unmanned aerial vehicles includes the following steps for determining the neighboring aircraft: Based on the current grid corresponding to the current aircraft in the three-dimensional space grid, a preset number of neighboring grids adjacent to the current grid are determined; One or more aircraft in the current grid and the neighboring grids are considered as the neighboring aircraft.

[0007] According to the present invention, an autonomous conflict resolution method for unmanned aerial vehicles (UAVs) is provided, wherein determining a first safety protection zone for the current UAV in a three-dimensional spatial grid based on the current UAV's first current position and first flight parameters includes: If the current flight status of the aircraft is normal, a first horizontal protection zone for the current aircraft is determined based on the current aircraft's maximum horizontal speed, horizontal acceleration, and communication delay time. Based on the current aircraft’s maximum vertical upward speed, vertical acceleration, and communication delay time, determine the first vertical protection zone of the current aircraft. Based on the first horizontal protection zone and the first vertical protection zone, a first safety protection zone centered on the first current location is obtained.

[0008] According to the autonomous conflict resolution method for unmanned aerial vehicles provided by the present invention, the method for determining a first safety protection zone for the current aircraft in a three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters further includes: If the current flight status of the aircraft is out of contact, a second horizontal protection zone for the aircraft is determined based on the current maximum horizontal speed of the aircraft and the time of loss of contact. Based on the aircraft’s maximum vertical downward speed, maximum vertical upward speed, the time of loss of contact, and free fall speed, the second vertical protection zone of the aircraft is determined. Based on the second horizontal protection zone and the second vertical protection zone, a first safety protection zone centered on the first current location is obtained.

[0009] According to the present invention, an autonomous conflict resolution method for unmanned aerial vehicles includes calculating the relative motion trend between the current aircraft and the neighboring aircraft to obtain a trend value, comprising: Calculate the longitude difference, latitude difference, and velocity vector difference between the current aircraft and the neighboring aircraft; The trend value is obtained by performing a dot product calculation based on the longitude difference, the latitude difference, and the velocity vector difference.

[0010] According to the present invention, an autonomous conflict resolution method for unmanned aerial vehicles (UAVs) is provided, wherein determining the conflict risk between the current UAV and the neighboring UAV based on a first safety protection zone and a second safety protection zone includes: Determine the first predicted position of the current aircraft after a preset time period; Determine the second predicted position of the neighboring aircraft after a preset time period; Based on the first predicted location, the first safety protection zone is updated to obtain a third safety protection zone centered on the first predicted location; Based on the second predicted location, the second safety protection zone is updated to obtain a fourth safety protection zone centered on the second predicted location; In cases where there is overlap between the third and fourth safety protection zones, it is determined that there is a conflict risk between the current aircraft and the neighboring aircraft.

[0011] The present invention also provides an autonomous conflict resolution device for unmanned aerial vehicles, comprising the following modules: The first determining module is used to determine the first safety protection zone of the current aircraft in a three-dimensional spatial grid based on the current current position and the first flight parameters of the current aircraft; the three-dimensional spatial grid is constructed based on a preset aircraft flight area; The second determining module is used to determine the second safety protection zone of the neighboring aircraft in a three-dimensional spatial grid based on the second current position and second flight parameters of the neighboring aircraft; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. The trend calculation module is used to calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain a trend value. The risk detection module is used to determine the conflict risk between the current aircraft and the neighboring aircraft based on the first safety protection zone and the second safety protection zone when the trend value is less than a preset threshold. The conflict resolution module is used to resolve conflicts based on the conflict risk; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement any of the above-described autonomous conflict resolution methods for unmanned aerial vehicles.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the autonomous conflict resolution method for unmanned aerial vehicles as described above.

[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described autonomous conflict resolution methods for unmanned aerial vehicles.

[0015] The present invention provides an autonomous conflict resolution method and apparatus for unmanned aerial vehicles (UAVs). Based on the current aircraft's first current position and first flight parameters, a first safety protection zone is determined for the current aircraft within a three-dimensional spatial grid. This three-dimensional spatial grid is constructed based on a preset aircraft flight area. Based on the second current position and second flight parameters of neighboring aircraft, a second safety protection zone is determined for the neighboring aircraft within the three-dimensional spatial grid. The neighboring aircraft are one or more aircraft determined based on the three-dimensional spatial grid. Thus, by partitioning the three-dimensional grid, the conflict detection range between aircraft is limited from a global scope to a finite number of grids, reducing computational load and improving detection efficiency. The relative motion trend between the current aircraft and the neighboring aircraft is calculated. A trend value is obtained; if the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; thereby, aircraft pairs that are moving away and have no conflict risk are quickly filtered out by relative motion trends, filtering non-conflict scenarios, and only performing deep detection on potential conflict pairs, further reducing deep computation and improving efficiency; based on the conflict risk, conflict resolution is performed; the conflict resolution includes triggering a conflict warning and executing the aircraft control command corresponding to the conflict warning; thereby, the detected conflict risk is transformed into specific warning and automatic control actions, forming a complete closed loop from perception to decision-making to execution, improving the efficiency and real-time performance of autonomous conflict resolution of aircraft. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is one of the flowcharts of the autonomous conflict resolution method for unmanned aerial vehicles provided by the present invention.

[0018] Figure 2 This is a schematic diagram of the geometric structure of the cylindrical PAZ provided by the present invention.

[0019] Figure 3 This is the second flowchart of the autonomous conflict resolution method for unmanned aerial vehicles provided by the present invention.

[0020] Figure 4 This is a schematic diagram of the structure of the autonomous conflict resolution device for unmanned aerial vehicles provided by the present invention.

[0021] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0023] The following is combined Figures 1 to 5 The present invention describes an autonomous conflict resolution method and apparatus for unmanned aerial vehicles.

[0024] Figure 1 This is one of the flowcharts illustrating the autonomous conflict resolution method for unmanned aerial vehicles provided by this invention, such as... Figure 1 As shown, the method includes the following steps: Step 101: Based on the current aircraft's first current position and first flight parameters, determine the first safety protection zone of the current aircraft in a three-dimensional spatial grid; the three-dimensional spatial grid is constructed based on a preset aircraft flight area; Specifically, unmanned aerial vehicles (hereinafter referred to as aircraft) include, but are not limited to, remotely controlled drones flying at low altitudes or drones flying autonomously controlled by a predetermined program. By configuring the three-dimensional mesh file (CSV) corresponding to the aircraft's flight area, the boundaries of the three-dimensional spatial mesh and the position index (such as three-dimensional index: X, Y, Z) corresponding to each mesh are initialized.

[0025] The grid to which the current aircraft belongs in the three-dimensional space grid is determined by matching the grid boundary with the current position (such as longitude, latitude, and altitude) of the aircraft at each moment.

[0026] The information of the current aircraft is stored in the corresponding grid cell, which enables quick retrieval of the list of aircraft in the neighboring grid.

[0027] Each grid includes one or more aircraft. The horizontal and vertical dimensions of each grid can be adaptively set according to the size of the preset aircraft flight area. For example, the horizontal dimension of each grid can be 500 meters, the vertical dimension can be 100 meters, and the origin is a preset fixed geographic coordinate.

[0028] Based on the aircraft's current position and initial flight parameters, the first safety protection zone within a three-dimensional spatial grid is dynamically calculated. The initial flight parameters include various parameters such as the aircraft's flight speed, communication latency, and acceleration. The first safety protection zone is centered on the current position. Specifically, based on the Geometrically Approximate Separation (GAS) model, a cylindrical Protection Air Zone (PAZ) centered on the first current position is constructed.

[0029] Figure 2 This is a schematic diagram of the geometric structure of the cylindrical PAZ provided by the present invention, as shown below. Figure 2 As shown, the PAZ is a three-dimensional cylindrical protective space with the aircraft's center of gravity as the center, the horizontal safety distance R as the radius, and the vertical safety distance H as the height.

[0030] Step 102: Based on the second current position and second flight parameters of the neighboring aircraft, determine the second safety protection zone of the neighboring aircraft in the three-dimensional spatial grid; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid; Furthermore, the steps for determining nearby aircraft include: Based on the current grid corresponding to the current aircraft in the three-dimensional space grid, a preset number of neighboring grids adjacent to the current grid are determined; One or more aircraft in the current grid and the neighboring grids are considered as the neighboring aircraft.

[0031] Specifically, in a 3D mesh system, each mesh has a unique index (such as X, Y, Z). The mesh in which the current aircraft is located is called the current mesh, and the meshes adjacent to the current mesh or at a preset distance are called neighboring meshes.

[0032] For example, in one embodiment, a three-dimensional grid partition (500 meters horizontally × 100 meters vertically) limits the collision detection range to the current grid and 26 neighboring grids. Neighboring grids are defined as those offset by -1, 0, and +1 in the X, Y, and Z dimensions, respectively. By querying the list of registered aircraft in the current grid and the 26 neighboring grids, the system can quickly obtain all potential neighboring aircraft without traversing the entire airspace, thus reducing computation by approximately 70% and lowering the time complexity from O(n log n) for global scanning. 2 The efficiency of the system is reduced to O(n), thereby improving the efficiency of subsequent collision detection between aircraft and enabling the system to handle collision problems of high-density aircraft groups in real time.

[0033] After identifying nearby aircraft, the same method as in step 101 is used to construct a cylindrical PAZ centered on the second current position, based on the second current position and second flight parameters of the nearby aircraft. This serves as a second safety protection zone for the nearby aircraft within the three-dimensional spatial grid. The second flight parameters include various flight parameters such as the nearby aircraft's flight speed, communication delay time, and acceleration.

[0034] Step 103: Calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain the trend value; Further, the relative motion trend between the current aircraft and the neighboring aircraft is calculated to obtain a trend value, including: Calculate the longitude difference, latitude difference, and velocity vector difference between the current aircraft and the neighboring aircraft; The trend value is obtained by performing a dot product calculation based on the longitude difference, the latitude difference, and the velocity vector difference.

[0035] Specifically, the longitude difference (i.e., lateral distance), latitude difference (i.e., longitudinal distance), and velocity vector difference (i.e., lateral relative velocity and longitudinal relative velocity) between the current aircraft and neighboring aircraft are calculated first. Then, based on the dot product formula, the relative motion trend of the two aircraft is analyzed, eliminating the detection of non-conflict directions and reducing invalid calculations. The expression for calculating the trend value is as follows: In the formula, The trend values ​​are represented by dx (horizontal distance) and dy (vertical distance). Indicates lateral relative velocity, This indicates the longitudinal relative velocity.

[0036] Step 104: If the trend value is less than a preset threshold, determine the conflict risk between the current aircraft and the neighboring aircraft based on the first safety protection zone and the second safety protection zone; Specifically, potential conflict detection is performed based on the calculated trend value. For example, in one embodiment, if the preset threshold is 0, then if the trend value is less than 0, it is determined that there is a potential conflict and further detection is required; if the trend value is greater than or equal to 0, it is determined that there is no conflict and no further detection is required.

[0037] This invention uses trend values ​​for conflict detection, which can quickly eliminate more than 70% of aircraft pairs that are moving away and have no possibility of conflict in the early stages of detection. This avoids the complex calculations that would otherwise be time-consuming and risky, and improves the efficiency of subsequent calculations.

[0038] If a potential conflict is identified, the conflict risk between the current aircraft and neighboring aircraft is further assessed based on the first and second safety protection zones.

[0039] For example, if there is an overlap between the first safety protection zone corresponding to the current aircraft at the current moment and the second safety protection zone corresponding to the neighboring aircraft at the current moment, then it is determined that there is a risk of conflict between the current aircraft and the neighboring aircraft; otherwise, it is determined that there is no risk of conflict.

[0040] For example, if there is an overlap between the first safety protection zone corresponding to the current aircraft at the next moment and the second safety protection zone corresponding to the neighboring aircraft at the next moment, then it is determined that there is a risk of conflict between the current aircraft and the neighboring aircraft; otherwise, it is determined that there is no risk of conflict.

[0041] It is understandable that the safety protection zone corresponding to an aircraft is calculated dynamically in real time based on the changes in the aircraft's flight position. Therefore, in three-dimensional space, although the size of the first and second safety protection zones remains unchanged, their center positions change dynamically with the aircraft's flight time.

[0042] The embodiments of the present invention determine the conflict risk between the current aircraft and neighboring aircraft by calculating the first and second safety protection zones in real time, thereby improving the real-time performance of the system response and the accuracy of the conflict risk assessment.

[0043] Step 105: Based on the conflict risk, perform conflict resolution; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

[0044] Specifically, based on the conflict risk, the urgency of the conflict is assessed, and corresponding response measures are taken.

[0045] For example, if the predicted time of conflict is within the next 30 seconds, and the urgency of the conflict is determined to be low, a level two alarm will be triggered. The system interface will then issue an audible and visual alarm to prompt staff to take over.

[0046] For example, if a conflict is predicted to occur within the next 6 seconds, and the urgency of the conflict is deemed high, a Level 1 alarm is triggered. The system then automatically issues a hovering command to the aircraft, which immediately hovers. This tiered response strategy ensures that the system makes reasonable decisions.

[0047] The aircraft's command distribution mechanism publishes control commands through the Message Queuing Telemetry Transport (MQTT) communication protocol and is equipped with encryption methods such as CRC and timestamp verification to ensure accurate transmission of commands.

[0048] Based on the above embodiments, the present invention also conducted the following simulations to verify the efficiency and real-time performance of aircraft conflict resolution.

[0049] Extreme performance verification: In 1000 Monte Carlo simulations, the system maintained a 100% detection success rate in a scenario with 50 aircraft flying densely. The gridded partitioning kept the computation time stable within 200ms, with no missed or false alarms.

[0050] Comprehensive scenario coverage: Through actual tests under different weather conditions (wind speed ≤ 5m / s) and communication status (normal / loss of contact for 2-6 seconds), the consistency between interface warning and hovering command response reached 100%, proving that the aircraft can efficiently and in real time resolve conflicts in complex low-altitude environments.

[0051] The autonomous conflict resolution method for unmanned aerial vehicles provided by this invention determines a first safety protection zone for the current aircraft within a three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters. This three-dimensional spatial grid is constructed based on a preset aircraft flight area. A second safety protection zone for neighboring aircraft is determined within the three-dimensional spatial grid based on their second current position and second flight parameters. The neighboring aircraft are one or more aircraft determined based on the three-dimensional spatial grid. Thus, by partitioning the three-dimensional grid, the conflict detection range between aircraft is limited from a global scope to a finite number of grids, reducing computational load and improving detection efficiency. The method also calculates the relative motion trend between the current aircraft and the neighboring aircraft to obtain... A trend value is obtained; if the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; thereby, aircraft pairs that are moving away and have no conflict risk are quickly filtered out by relative motion trend, filtering non-conflict scenarios, and only performing deep detection on potential conflict pairs, further reducing deep computation and improving efficiency; based on the conflict risk, conflict resolution is performed; the conflict resolution includes triggering a conflict warning and executing the aircraft control command corresponding to the conflict warning; thereby, the detected conflict risk is transformed into specific warning and automatic control actions, forming a complete closed loop from perception to decision-making to execution, improving the efficiency and real-time performance of autonomous conflict resolution of aircraft.

[0052] Further, based on the current aircraft's first current position and first flight parameters, the first safety protection zone of the current aircraft in the three-dimensional spatial grid is determined, including: If the current flight status of the aircraft is normal, a first horizontal protection zone for the current aircraft is determined based on the current aircraft's maximum horizontal speed, horizontal acceleration, and communication delay time. Based on the current aircraft’s maximum vertical upward speed, vertical acceleration, and communication delay time, determine the first vertical protection zone of the current aircraft. Based on the first horizontal protection zone and the first vertical protection zone, a first safety protection zone centered on the first current location is obtained.

[0053] Specifically, under the condition that the current flight status of the aircraft is normal, the safety protection zones in the horizontal and vertical directions are dynamically calculated based on parameters such as the aircraft's maximum horizontal flight speed, communication delay time, and horizontal acceleration.

[0054] In the horizontal direction, the formula for calculating the horizontal safety distance within the first horizontal protection zone is: In the formula, This indicates that the current flight status of the aircraft is within the normal horizontal safe distance range. Indicates the aircraft's maximum horizontal speed. This indicates the communication delay time for issuing commands. Indicates the collision detection computation time. Indicates the horizontal acceleration of an aircraft. This indicates the horizontal safety redundancy distance.

[0055] In the vertical direction, the formula for calculating the vertical upward safety distance in the first vertical protection zone is: In the formula, This indicates the safe vertical upward distance for the current aircraft's flight status under normal conditions. Indicates the maximum vertical upward speed. This indicates the communication delay time for issuing commands. Indicates the collision detection computation time. Indicates the vertical acceleration of an aircraft. This indicates the vertical safety redundancy distance.

[0056] In the vertical direction, the formula for calculating the vertically downward safety distance in the first vertical protection zone is: In the formula, This indicates the current aircraft's safe vertical downward distance under normal flight conditions. Indicates the maximum vertical downward velocity. This indicates the communication delay time for issuing commands. Indicates the collision detection computation time. Indicates the maximum vertical upward speed. Represents vertical acceleration. This indicates the vertical safety redundancy distance.

[0057] Assuming the aircraft's current flight status is normal, a cylindrical PAZ is constructed with the first current position as the center, a horizontal safety distance as the radius, and a vertical safety distance as the height, based on the first horizontal protection zone and the first vertical protection zone. This serves as the first safety protection zone, providing a basis for subsequent conflict risk detection.

[0058] Furthermore, determining the first safety protection zone of the current aircraft in the three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters also includes: If the current flight status of the aircraft is out of contact, a second horizontal protection zone for the aircraft is determined based on the current maximum horizontal speed of the aircraft and the time of loss of contact. Based on the aircraft’s maximum vertical speed, maximum vertical speed, the time of loss of contact, and free fall speed, a second vertical protection zone for the aircraft is determined. Based on the second horizontal protection zone and the second vertical protection zone, a first safety protection zone centered on the first current location is obtained.

[0059] Specifically, when the aircraft is currently in a state of being out of contact, the safety protection zones in the horizontal and vertical directions are dynamically calculated based on parameters such as the aircraft's maximum vertical speed, time of loss of contact, and free fall speed.

[0060] In the horizontal direction, the formula for calculating the horizontal safety distance within the first horizontal protection zone is: In the formula, This indicates the horizontal safe distance for the aircraft in a state of loss of contact. Indicates the aircraft's maximum horizontal speed. Indicates the time of loss of contact. This indicates the horizontal safe distance under normal flight conditions for the current aircraft.

[0061] In the vertically upward direction, the formula for calculating the vertically upward safety distance in the first vertical protection zone is: In the formula, This indicates the vertical upward safe distance for the aircraft when it is in a state of loss of contact. Indicates the maximum vertical upward speed. Indicates the time of loss of contact. This indicates the safe vertical upward distance for the current aircraft's flight status under normal conditions.

[0062] In the vertically downward direction, the flight state of an aircraft in a state of loss of contact can be approximated as a free fall state. Therefore, the formula for calculating the vertical safety distance in the first vertical protection zone is: In the formula, This indicates the vertical downward safe distance in the event of a loss of contact. Indicates the maximum vertical downward velocity. The time of loss of contact is represented by g, and the velocity of free fall is represented by g. This indicates the safe vertical downward distance for the current aircraft's flight status under normal conditions.

[0063] If the aircraft is currently out of contact, a cylindrical PAZ (Protective Area Zone) is constructed with the first current location as the center, a horizontal safety distance as the radius, and a vertical safety distance as the height, as the second safety protection zone, thus providing a basis for subsequent conflict risk detection.

[0064] This invention distinguishes between normal and disconnected states. In the normal state, it accurately calculates the safety boundary based on parameters such as speed and delay time to establish a first safety protection zone. In the disconnected state, it automatically expands the protection zone and establishes a second safety protection zone by combining a free-fall model in the vertical downward direction. This provides safety redundancy for the system, ensuring airspace safety even in extreme situations. This covers all scenarios of conflict risks, enabling the safety protection zone to adapt to different aircraft operating states, improving the system's robustness in different scenarios, and thus enhancing the accuracy of subsequent conflict risk detection.

[0065] Further, based on the first safety protection zone and the second safety protection zone, the conflict risk between the current aircraft and the neighboring aircraft is determined, including: Determine the first predicted position of the current aircraft after a preset time period; Determine the second predicted position of the neighboring aircraft after a preset time period; Based on the first predicted location, the first safety protection zone is updated to obtain a third safety protection zone centered on the first predicted location; Based on the second predicted location, the second safety protection zone is updated to obtain a fourth safety protection zone centered on the second predicted location; In cases where there is overlap between the third and fourth safety protection zones, it is determined that there is a conflict risk between the current aircraft and the neighboring aircraft.

[0066] Specifically, in order to detect conflict risks in advance and reserve reaction time for conflict resolution operations, this embodiment of the invention upgrades conflict detection from static prediction to dynamic prediction. Based on the flight parameters of the current aircraft and neighboring aircraft, the first and second predicted positions are calculated after a preset time period, respectively.

[0067] For example, in one embodiment, the prediction time period can be set to 30 seconds, with a step size of 3 seconds. This allows for the calculation of the predicted positions of the current aircraft and neighboring aircraft after 3 seconds, 6 seconds, 9 seconds...30 seconds. Then, using these predicted positions as centers, prediction protection zones (such as the third and fourth safety protection zones) are redefined, and it is determined whether there is overlap between the third and fourth safety protection zones. If overlap is found between two prediction protection zones, a conflict risk is identified.

[0068] Furthermore, the system can further determine the urgency of the conflict based on the predicted time. For example, if two predicted protection zones overlap at the 6th second, it is determined that the conflict is expected to occur 6 seconds later and the urgency is high, triggering a Level 1 alarm. The system can then automatically issue a hovering command to the aircraft, which will immediately hover. If two predicted protection zones overlap at the 30th second, it is determined that the conflict is expected to occur 30 seconds later and the urgency is low, triggering a Level 2 alarm. The system interface will issue an audible and visual alarm to prompt personnel to take over, thus allowing sufficient time for the aircraft to perform obstacle avoidance or hovering operations.

[0069] Based on the above embodiments, Figure 3 This is the second flowchart illustrating the autonomous conflict resolution method for unmanned aerial vehicles provided by this invention, as shown below. Figure 3 As shown, in the steps of the autonomous conflict resolution method for unmanned aerial vehicles (UAVs), the first step is to calculate the aircraft grid cells to initialize the grid system, i.e., initialize the boundaries of the three-dimensional spatial grid and the position index (e.g., three-dimensional index: X, Y, Z) corresponding to each grid cell. Then, the method identifies nearby aircraft within the grid cell. Next, it detects relative motion trends, including whether the aircraft is approaching or moving away from each other. Based on the trend value of the relative motion trend, if the trend value is less than a preset threshold, it is determined that the current aircraft and nearby aircraft are approaching each other, indicating a potential conflict. Then, it predicts the aircraft trajectory, calculating the first and second predicted positions after a preset time period based on the flight parameters of the current and nearby aircraft, thereby determining the conflict risk between the current and nearby aircraft. This includes sequential vertical and horizontal conflict determinations. Finally, a flight conflict alarm is issued based on the determination results. If no conflict risk is determined at the current moment, the next long-term (i.e., the next moment) conflict risk determination is performed.

[0070] In vertical conflict determination, the risk of vertical conflict between the current aircraft and its neighboring aircraft is assessed based on the altitude changes and vertical safety distances between the current aircraft and its neighboring aircraft within the predicted time period.

[0071] The vertical height at time t within the prediction time period. The calculation expression is: In the formula, Indicates the initial altitude coordinates of the aircraft. This indicates the vertical speed of the aircraft.

[0072] Based on the above calculation expression, the vertical height difference between the current aircraft and the neighboring aircraft is: ,in, This represents the current vertical altitude of the aircraft at time t. This represents the vertical altitude of the nearby aircraft at time t.

[0073] If the sum of the vertical safe distances between the current aircraft and neighboring aircraft is If the height difference is less than the sum of the vertical safety distances, then it is determined that the third and fourth safety protection zones overlap in the vertical direction.

[0074] In the determination of horizontal conflict, the risk of conflict between the current aircraft and its neighboring aircraft in the horizontal direction is determined based on the changes in latitude and longitude and the horizontal safe distance between the current aircraft and its neighboring aircraft within the predicted time period.

[0075] The horizontal position at time t within the predicted time period ( , The expression for calculating ) is: In the formula, This represents the initial X-axis coordinate (longitude direction). Indicates the aircraft's speed relative to the ground. Indicates the yaw angle. This indicates the deviation in heading angle caused by the roll angle. This represents the initial Y-axis coordinate (latitude direction).

[0076] Based on the above calculation expression, the current horizontal position of the aircraft at time t is ( , The horizontal position of the neighboring aircraft at time t is ( ). , The horizontal distance between the current aircraft and its neighboring aircraft at time t within the predicted time period. for: If the sum of the horizontal safety distances between the current aircraft and neighboring aircraft in the horizontal direction is Then it is only necessary to determine whether the horizontal distance at time t is less than the sum of the horizontal safety distances. If the horizontal distance at time t is less than the sum of the horizontal safety distances, then it is determined that the third and fourth safety protection zones overlap in the horizontal direction.

[0077] When the third and fourth safety protection zones overlap in both the vertical and horizontal directions, a conflict risk is determined between the current aircraft and a neighboring aircraft. Based on the above calculation expression, it can be understood that the computational complexity of vertical conflict determination is much lower than that of horizontal conflict determination. Therefore, by prioritizing vertical conflict determination, if it is determined that the third and fourth safety protection zones do not overlap in the vertical direction, it can be determined that there is no conflict risk at the current moment, and the conflict risk detection for the next moment can be directly performed, thereby further reducing unnecessary calculations and improving detection efficiency and the real-time nature of conflict resolution.

[0078] The following describes one possible parameter design for the above-mentioned autonomous conflict resolution method for unmanned aerial vehicles in practical applications. In this method, the aircraft system establishes a low-latency communication link via the MQTT protocol.

[0079] In an optional embodiment, the aircraft's real-time status (Osd data) includes: subscribing to the topic atct / conflictdetection / drone / osd and receiving DroneOsd objects (defined in DroneOsd.cs), which specifically include the following fields: Unique identifier Sn; Location parameters: Latitude (in degrees), Longitude (in degrees), Altitude (in meters); Speed ​​parameters: Horizontal Speed ​​(0-15m / s), Vertical Speed ​​(0 to 8m / s); Attitude parameters: Heading (0-360 degrees), Pitch, Roll; Timestamp (Unix timestamp, used for timeliness verification); Offline flag IsOffline (Boolean, indicating whether the connection is lost).

[0080] Aircraft status data includes normal status and offline status. The offline status is obtained through aircraft offline notification, specifically: the topic atct / conflictdetection / drone / offline receives a DroneOffline object and triggers an aircraft loss of contact event.

[0081] Data reception is implemented by the MqttService class, which deserializes MQTT messages using System.Text.Json.JsonSerializer through MessageHandler and its subclasses (such as PlatformMessageHandler and ProjectMessageHandler) and triggers events such as DroneOsdReceived and DroneOffline.

[0082] After receiving the data, reliability is ensured through a three-level verification process. The specific parameters and rules are as follows: (1) Integrity verification Sn verification: The regular expression [\w]+ / [\w]+ / (\w+) / * (defined in MqttService) ensures that Sn is not empty and conforms to the device numbering specification (such as the D3 format in the example).

[0083] Timestamp verification: Timestamp is a long integer and its value must be greater than 0 (valid Unix timestamp value).

[0084] (2) Reasonableness verification Location rationality: Latitude ∈ [-90°, 90°], Longitude ∈ [-180°, 180°]; Altitude ≥ 0 (150-160 meters in the example, which is consistent with the low-altitude operation scenario).

[0085] Speed ​​justification: Horizontal Speed ​​≤ 20 m / s (the maximum speed limit for conventional aircraft is 15 m / s, which meets the requirement); Vertical Speed ​​∈ [0, 10 m / s] (3) Timeliness verification The difference between the timestamp and the current system time is ≤5 seconds (MqttCycleTime=2.0 seconds in appsettings.json to ensure that the data update frequency is higher than the detection cycle). Outdated data (such as data older than 5 seconds) will be discarded and will not participate in conflict detection.

[0086] After verification, to improve detection efficiency, the aircraft's flight airspace is divided into three-dimensional grid cells. The partitioning parameters and dynamic update rules are as follows: (1) Mesh generation parameters Latitude and longitude span: Taking the current average position of the aircraft as the center, the span is 100 meters. Calculate the different latitude and longitude spans (due to the curvature of the earth, the longitude span decreases with latitude. For example, at latitude 39.37°, cos(39.37°)≈0.77, then Δlon≈0.00077°, about 85 meters).

[0087] Altitude span: Δalt = 50 meters (covering common altitude layers for low-altitude operations, such as aircraft altitudes of 150-160 meters, distributed in the same or adjacent altitude grids).

[0088] Grid storage: Grid data is stored in the GridFolder="grids" directory (configured in appsettings.json), supporting persistence and fast retrieval.

[0089] (2) Dynamic update logic Dynamic grid management is achieved through the SpatialPartitioning class: When each aircraft first connects, its grid is calculated based on its latitude, longitude, and altitude (e.g., latitude and longitude 39.3752°N, 116.9252°E, altitude 155 meters, belonging to the grid (lat=39.375°, lon=116.925°, alt=150-200 meters)).

[0090] When an aircraft's position changes and its latitude and longitude exceed the Δlat or Δlon range of the current grid, or its altitude exceeds the Δalt range, it is removed from the original grid and added to the new grid.

[0091] The adjacent grid is defined as the 26 neighborhoods (27 grids in total) of the current grid in the three-dimensional space of latitude, longitude and height, to ensure that the detection range covers potential conflict areas.

[0092] Based on the above embodiments, in an optional embodiment, the aircraft system performs conflict detection cyclically with a period of 2 seconds (MqttCycleTime=2.0 seconds in appsettings.json), and the specific process is as follows: (1) Status Update. The newly received DroneOsd data is converted into an AircraftStatus object (defined in AircraftStatus.cs). The converted data includes: Location (latitude and longitude, altitude), speed (horizontal / vertical), attitude (heading, pitch, roll), last update time LastTimestamp, lost connection status IsLostConnection, lost connection duration LostTime (e.g., if IsLostConnection=true, then LostTime=current time-LastTimestamp).

[0093] (2) After updating the state list of the grid where the aircraft is located using the SpatialPartitioning.UpdateAircraft method, for each aircraft, only other aircraft in its own grid and its 26 adjacent grids (assuming a total of 27 grids) are extracted as candidate detection objects. This operation reduces the computational complexity from O(n^2) for full detection. 2 The time complexity is reduced to O(n) (where n is the number of aircraft in a single grid, typically ≤10), significantly improving real-time performance.

[0094] (3) Multi-dimensional conflict detection, specifically including three dimensions: relative motion trend analysis, vertical conflict detection and horizontal conflict detection, to screen risk targets layer by layer. The key parameters come from the SafetyParameters configuration in appsettings.json.

[0095] First, by analyzing the relative motion trend, we determine whether further testing is needed. The specific calculations are as follows: 1) Location difference conversion: Convert longitude and latitude differences into metric distances.

[0096] Latitude difference for: In the formula, and These represent the latitudes of the current aircraft and neighboring aircraft, respectively.

[0097] Longitude difference for: In the formula, and These represent the longitudes of the current aircraft and the nearby aircraft, respectively.

[0098] Decompose the horizontal velocities of the current aircraft and neighboring aircraft into latitudinal directions according to their heading angles: In the formula, This represents the horizontal speed in the latitudinal direction. HorizontalSpeed ​​represents the horizontal speed, and Heading represents the heading angle.

[0099] Decompose the horizontal velocities of the current aircraft and neighboring aircraft into longitude directions based on their heading angles: In the formula, HorizontalSpeed ​​represents the horizontal speed along the longitude direction, and lat represents the latitude value.

[0100] Assuming the current aircraft number is Aircraft 1 and the neighboring aircraft number is Aircraft 2, the expression for calculating the relative velocity components is: In the formula, This indicates the relative speed between two aircraft along the longitude direction. This indicates the aircraft's speed in the longitude direction. Indicates the speed of the aircraft in the longitude direction. This indicates the relative speed between two aircraft in the latitudinal direction. This indicates the aircraft's speed in the 2nd latitude direction. This indicates the speed of the aircraft in the 1st latitude direction.

[0101] The trend value of the relative motion trend between the current aircraft and neighboring aircraft is: In the formula, Indicates the trend value, if <0 indicates that the two aircraft are approaching each other (relative motion directions are pointing towards each other), and further detection is required; if If the value is ≥0, it means that the two aircraft are far apart and can skip the detection, reducing unnecessary calculations and improving computational efficiency.

[0102] In cases where further testing is required ( Under conditions <0, predict the vertical position within Δt=30 seconds in the future, and determine the conflict based on the dynamic safety envelope. The parameters are as follows: The predicted vertical altitude of the current aircraft at time t Represented as: In the formula, Altitude1 represents the altitude coordinate of aircraft 1, and VerticalSpeed1 represents the vertical speed of aircraft 1.

[0103] Predicted vertical altitude of neighboring aircraft at time t Represented as: In the formula, Altitude2 represents the altitude coordinate of aircraft 2, and VerticalSpeed2 represents the vertical speed of aircraft 2.

[0104] When the aircraft is in a normal flight condition, the safe ascent envelope Represented as: In this embodiment, VerticalUpMaxSpeed ​​= 8.0 m / s. This represents the sum of all communication delays. Indicates the safe redundancy distance.

[0105] Safe descent envelope (i.e., the safe vertical upward distance of an aircraft under normal conditions) Represented as: In this embodiment, VerticalDownMaxSpeed ​​= 6.0 m / s.

[0106] When the aircraft is in a state of lost contact, the safety envelope expands to: In the formula, This indicates the safe vertical upward distance when communication is lost. This indicates the vertical downward safe distance when communication is lost. Indicates the time of loss of contact. This represents the velocity of a free fall.

[0107] If the current aircraft and neighboring aircraft are in normal flight status, then If so, then a risk of vertical conflict is determined. In the formula, This indicates the safe vertical downward distance for an aircraft under normal conditions.

[0108] If the current aircraft and nearby aircraft are in a state of loss of contact, If so, it is determined that there is a risk of vertical conflict.

[0109] In cases where further testing is required ( Under conditions <0, predict the horizontal position within Δt=30 seconds in the future, and determine the conflict based on the dynamic safety envelope. The parameters are as follows: Projecting the horizontal velocity of the aircraft at time t onto the longitude direction, it can be expressed as: In the formula, This represents the value of horizontal velocity in the longitude direction. The initial longitude coordinates are represented by Heading, the aircraft heading angle is represented by Heading, and latitude is represented by lat.

[0110] Projecting the horizontal velocity of the aircraft at time t onto the latitude direction, it can be expressed as: In the formula, This represents the horizontal velocity in the latitudinal direction. It means XXX.

[0111] When the aircraft is in normal flight condition, horizontal safety distance Represented as: In the formula, HorizontalMaxSpeed ​​represents the maximum horizontal speed. This represents the sum of all communication delays. Indicates the safe redundancy distance.

[0112] When the aircraft is in a state of flight loss, the horizontal safe distance Represented as: In the formula, HorizontalMaxSpeed ​​represents the maximum horizontal speed. Indicates the time of loss of contact.

[0113] Assuming the current and neighboring aircraft are in normal flight conditions, the horizontal distance between the predicted positions of the two aircraft is... If so, then a risk of horizontal conflict is determined. It represents the sum of horizontal safety distances.

[0114] If the current aircraft and a nearby aircraft are out of contact, and the horizontal distance between the predicted positions of the two aircraft is... If so, it is determined that there is a risk of horizontal conflict.

[0115] If all detection dimensions detect conflicts, meaning there is a risk of conflict in both the vertical and horizontal directions, the system will execute the following handling procedure: (1) Generate different alarm levels according to different levels of urgency.

[0116] Alarm Level: AlarmLevel=1 (e.g., the highest level is predicting a conflict within 6 seconds), AlarmLevel=2 (the lowest level is predicting a conflict within 30 seconds). Alarm message: For example, "Aircraft D3 (Sn=D3) and D4 (Sn=D4) are expected to have a flight conflict within 6 seconds."

[0117] (2) Send hovering commands to the aircraft in conflict via the MQTT topic HoverCommandTopic (e.g., when the predicted time of future conflict is less than 6 seconds) to force it to stop approaching (Hovering command response time InstructionTime = 0.4 seconds to ensure rapid effect) and wait for manual judgment and takeover.

[0118] (3) Record conflict details through Serilog, including: aircraft status (latitude and longitude, altitude, speed, heading), detection parameters (prediction time Δt, safety envelope / radius) and handling measures (hover command sending time, alarm level), etc., for subsequent accident tracing and algorithm optimization (log storage path is configured by Serilog.Sinks.File).

[0119] This invention improves detection efficiency and real-time collision avoidance by performing collision detection sequentially in the vertical and horizontal directions, prioritizing collision determination in the vertical direction where computation is less demanding. By upgrading collision detection from static prediction to dynamic prediction, when a collision risk is detected between the current aircraft and a neighboring aircraft within a threshold time, an alarm is issued and a hovering command is executed. This allows for early detection of collision risks, providing reaction time for collision avoidance operations and achieving more reasonable and forward-looking autonomous obstacle avoidance control.

[0120] The autonomous conflict resolution device for unmanned aerial vehicles provided by the present invention is described below. The autonomous conflict resolution device for unmanned aerial vehicles described below can be referred to in correspondence with the autonomous conflict resolution method for unmanned aerial vehicles described above.

[0121] Figure 4 This is a schematic diagram of the structure of the autonomous conflict resolution device for unmanned aerial vehicles provided by the present invention, as shown below. Figure 4 As shown. An embodiment of the present invention provides an autonomous conflict resolution device for unmanned aerial vehicles, comprising a first determining module 401, a second determining module 402, a trend calculation module 403, a risk detection module 404, and a conflict resolution module 405, wherein: The first determining module 401 is used to determine a first safety protection zone of the current aircraft in a three-dimensional spatial grid based on the first current position and first flight parameters of the current aircraft; the three-dimensional spatial grid is constructed based on a preset aircraft flight area; the second determining module 402 is used to determine a second safety protection zone of the neighboring aircraft in the three-dimensional spatial grid based on the second current position and second flight parameters of the neighboring aircraft; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid; the trend calculation module 403 is used to calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain a trend value; the risk detection module 404 is used to determine the conflict risk between the current aircraft and the neighboring aircraft based on the first safety protection zone and the second safety protection zone if the trend value is less than a preset threshold; the conflict resolution module 405 is used to perform conflict resolution based on the conflict risk; the conflict resolution includes triggering a conflict warning and executing the aircraft control command corresponding to the conflict warning.

[0122] The autonomous conflict resolution device for unmanned aerial vehicles provided by this invention determines a first safety protection zone for the current aircraft within a three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters; the three-dimensional spatial grid is constructed based on a preset aircraft flight area; and determines a second safety protection zone for neighboring aircraft within the three-dimensional spatial grid based on the second current position and second flight parameters of neighboring aircraft; the neighboring aircraft are one or more aircraft determined based on the three-dimensional spatial grid; thereby, by partitioning the three-dimensional grid, the conflict detection range between aircraft is limited from globally to a finite number of grids, reducing computational load and improving detection efficiency; and the relative motion trend between the current aircraft and the neighboring aircraft is calculated to obtain... A trend value is obtained; if the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; thereby, aircraft pairs that are moving away and have no conflict risk are quickly filtered out by relative motion trend, filtering non-conflict scenarios, and only performing deep detection on potential conflict pairs, further reducing deep computation and improving efficiency; based on the conflict risk, conflict resolution is performed; the conflict resolution includes triggering a conflict warning and executing the aircraft control command corresponding to the conflict warning; thereby, the detected conflict risk is transformed into specific warning and automatic control actions, forming a complete closed loop from perception to decision-making to execution, improving the efficiency and real-time performance of autonomous conflict resolution of aircraft.

[0123] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute an autonomous conflict resolution method for unmanned aerial vehicles, the method including: Based on the current position and flight parameters of the aircraft, a first safe protection zone for the aircraft in a three-dimensional spatial grid is determined; the three-dimensional spatial grid is constructed based on a preset aircraft flight area. Based on the second current position and second flight parameters of the neighboring aircraft, a second safety protection zone for the neighboring aircraft is determined in a three-dimensional spatial grid; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. Calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain the trend value; If the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; Based on the aforementioned conflict risk, conflict resolution is carried out; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

[0124] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0125] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is capable of executing the autonomous conflict resolution method for unmanned aerial vehicles provided by the above methods, the method comprising: Based on the current position and flight parameters of the aircraft, a first safe protection zone for the aircraft in a three-dimensional spatial grid is determined; the three-dimensional spatial grid is constructed based on a preset aircraft flight area. Based on the second current position and second flight parameters of the neighboring aircraft, a second safety protection zone for the neighboring aircraft is determined in a three-dimensional spatial grid; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. Calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain the trend value; If the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; Based on the aforementioned conflict risk, conflict resolution is carried out; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

[0126] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the autonomous conflict resolution method for unmanned aerial vehicles provided by the methods described above, the method comprising: Based on the current position and flight parameters of the aircraft, a first safe protection zone for the aircraft in a three-dimensional spatial grid is determined; the three-dimensional spatial grid is constructed based on a preset aircraft flight area. Based on the second current position and second flight parameters of the neighboring aircraft, a second safety protection zone for the neighboring aircraft is determined in a three-dimensional spatial grid; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. Calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain the trend value; If the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; Based on the aforementioned conflict risk, conflict resolution is carried out; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

[0127] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0128] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0129] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0130] In this application's embodiments, "determine B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determine B based on A and C," "determine B based on A, C, and E," "determine C based on A, and further determine B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A meets the first condition, determine B using the first method"; another example, "when A meets the second condition, determine B," etc.; another example, "when A meets the third condition, determine B based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A meets the first condition, determine C using the first method, and further determine B based on C," etc.

[0131] It should also be noted that the terms "first," "second," etc., used in this invention are used to distinguish similar objects, and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, and the number of objects is not limited; for example, the first object can be one or more.

[0132] In this invention, the term "multiple" refers to two or more kinds, and other quantifiers are similar.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for autonomous conflict resolution of unmanned aerial vehicles, characterized in that, include: Based on the current current position and the first flight parameters of the current aircraft, the first safety protection zone of the current aircraft in the three-dimensional spatial grid is determined; The three-dimensional spatial grid is constructed based on a pre-defined aircraft flight area; Based on the second current position and second flight parameters of the neighboring aircraft, a second safety protection zone for the neighboring aircraft is determined in a three-dimensional spatial grid; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. Calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain the trend value; If the trend value is less than a preset threshold, the conflict risk between the current aircraft and the neighboring aircraft is determined based on the first safety protection zone and the second safety protection zone; Based on the aforementioned conflict risk, conflict resolution is carried out; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

2. The autonomous conflict resolution method for unmanned aerial vehicles according to claim 1, characterized in that, The steps for determining the nearby aircraft include: Based on the current grid corresponding to the current aircraft in the three-dimensional space grid, a preset number of neighboring grids adjacent to the current grid are determined; One or more aircraft in the current grid and the neighboring grids are considered as the neighboring aircraft.

3. The autonomous conflict resolution method for unmanned aerial vehicles according to claim 1, characterized in that, The determination of the first safety protection zone of the current aircraft in the three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters includes: If the current flight status of the aircraft is normal, a first horizontal protection zone for the current aircraft is determined based on the current aircraft's maximum horizontal speed, horizontal acceleration, and communication delay time. Based on the current aircraft’s maximum vertical upward speed, vertical acceleration, and communication delay time, determine the first vertical protection zone of the current aircraft. Based on the first horizontal protection zone and the first vertical protection zone, a first safety protection zone centered on the first current location is obtained.

4. The autonomous conflict resolution method for unmanned aerial vehicles according to claim 1, characterized in that, The method of determining the first safety protection zone of the current aircraft in the three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters further includes: If the current flight status of the aircraft is out of contact, a second horizontal protection zone for the aircraft is determined based on the current maximum horizontal speed of the aircraft and the time of loss of contact. Based on the aircraft’s maximum vertical downward speed, maximum vertical upward speed, the time of loss of contact, and free fall speed, the second vertical protection zone of the aircraft is determined. Based on the second horizontal protection zone and the second vertical protection zone, a first safety protection zone centered on the first current location is obtained.

5. The autonomous conflict resolution method for unmanned aerial vehicles according to claim 1, characterized in that, The calculation of the relative motion trend between the current aircraft and the neighboring aircraft to obtain a trend value includes: Calculate the longitude difference, latitude difference, and velocity vector difference between the current aircraft and the neighboring aircraft; The trend value is obtained by performing a dot product calculation based on the longitude difference, the latitude difference, and the velocity vector difference.

6. The autonomous conflict resolution method for unmanned aerial vehicles according to claim 1, characterized in that, The determination of the conflict risk between the current aircraft and the neighboring aircraft based on the first safety protection zone and the second safety protection zone includes: Determine the first predicted position of the current aircraft after a preset time period; Determine the second predicted position of the neighboring aircraft after a preset time period; Based on the first predicted location, the first safety protection zone is updated to obtain a third safety protection zone centered on the first predicted location; Based on the second predicted location, the second safety protection zone is updated to obtain a fourth safety protection zone centered on the second predicted location; In cases where there is overlap between the third and fourth safety protection zones, it is determined that there is a conflict risk between the current aircraft and the neighboring aircraft.

7. An autonomous conflict resolution device for unmanned aerial vehicles, characterized in that, include: The first determining module is used to determine the first safety protection zone of the current aircraft in a three-dimensional spatial grid based on the current aircraft's first current position and first flight parameters; The three-dimensional spatial grid is constructed based on a pre-defined aircraft flight area; The second determining module is used to determine the second safety protection zone of the neighboring aircraft in a three-dimensional spatial grid based on the second current position and second flight parameters of the neighboring aircraft; the neighboring aircraft is one or more aircraft determined based on the three-dimensional spatial grid. The trend calculation module is used to calculate the relative motion trend between the current aircraft and the neighboring aircraft to obtain a trend value. The risk detection module is used to determine the conflict risk between the current aircraft and the neighboring aircraft based on the first safety protection zone and the second safety protection zone when the trend value is less than a preset threshold. The conflict resolution module is used to resolve conflicts based on the conflict risk; the conflict resolution includes triggering a conflict warning and executing the aircraft control commands corresponding to the conflict warning.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the autonomous conflict resolution method for unmanned aerial vehicles as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the autonomous conflict resolution method for unmanned aerial vehicles as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the autonomous conflict resolution method for unmanned aerial vehicles as described in any one of claims 1 to 6.

Images