A traffic management system, method, electronic device and medium for unmanned aerial vehicles (UAVs)

Abstract

This invention provides a traffic management system, method, electronic device, and medium for unmanned aerial vehicles (UAVs). The system's central scheduler acquires the current pose data of the UAV; based on the current pose data, combined with preset flight tasks and target areas, it generates dynamic scheduling requirements; according to the dynamic scheduling requirements, it uses task decomposition rules to divide the preset flight tasks into multiple sub-tasks; based on a load balancing strategy, it assigns each sub-task to a corresponding edge node; the edge nodes, based on the target sub-tasks assigned to them, use a two-layer conflict detection mechanism and path replanning algorithm to generate conflict avoidance schemes and send them to the UAVs. The central scheduler decomposes the scheduling task into multiple sub-tasks and distributes them to edge nodes for processing through a distributed computing architecture. The edge nodes then generate conflict avoidance schemes for each sub-task, achieving dynamic scheduling and conflict avoidance of the UAVs, thereby improving real-time processing and avoiding single-point-of-failure risks.

Description

Technical Field

[0001] This invention relates to the field of information technology, and specifically to a traffic management system, method, electronic device, and medium for unmanned aerial vehicles (UAVs). Background Technology

[0002] Unmanned Traffic Management (UTM) refers to the use of technology to coordinate the flight paths, speeds, altitudes, and priorities of multiple drones in low-altitude airspace in real time to prevent airspace conflicts, optimize flight efficiency, and ensure safety.

[0003] The current development of drone traffic management technology can be divided into three stages: The first stage (before 2015): primarily manual scheduling, relying on Visual Flight Rules (VFR), supporting only small-scale, low-density scenarios. The second stage (2015-2020): based on static airspace division (such as NASA's UTM project) and preset routes, achieving initial automated scheduling, but with poor dynamic adaptability. The third stage (2020 to present): introducing artificial intelligence (such as reinforcement learning) and edge computing, supporting real-time path replanning.

[0004] While current drone traffic management technology has evolved from manual scheduling to intelligent collaboration, it still faces many technical challenges. The dynamic scheduling and conflict avoidance of massive drones place extremely high demands on computing power. Traditional centralized scheduling architectures are unable to meet real-time requirements and are subject to single-point failure risks. Summary of the Invention

[0005] To overcome the aforementioned problems of difficulty in meeting real-time requirements and the risk of single point of failure, the present invention provides a traffic management system for unmanned aerial vehicles (UAVs), including a central scheduler and multiple edge nodes connected in communication; the central scheduler and each edge node are connected in communication with the UAV.

[0006] The central scheduler is used to acquire the current pose data of the UAV; generate dynamic scheduling requirements based on the current pose data, combined with the preset flight mission and target area; divide the preset flight mission into multiple sub-tasks according to the dynamic scheduling requirements using task decomposition rules; and allocate each sub-task to the corresponding edge node based on a load balancing strategy.

[0007] The edge node is used to generate a conflict avoidance scheme based on the target sub-task assigned to the edge node, using a two-layer conflict detection mechanism and a path replanning algorithm, and send it to the UAV.

[0008] Optionally, the central scheduler is specifically used to predict the demand density index of each airspace that the UAV passes through during its flight to the target area based on the current pose data and the target area, using a time series prediction model; and to generate the dynamic scheduling requirements of the UAV in each airspace based on the demand density index of each airspace and the timeliness of the preset flight mission.

[0009] Optionally, the central scheduler is specifically used to divide the target area into multiple sub-regions based on the dynamic scheduling requirements using a Voronoi diagram spatial segmentation algorithm; and to divide the preset flight mission into multiple sub-tasks based on each sub-region using task chain sharding technology.

[0010] Optionally, the central scheduler is specifically used to dynamically adjust the allocation strategy of multiple sub-tasks based on the resource utilization reported by each edge node, using an improved Hungarian algorithm with the goal of minimizing the maximum load.

[0011] Optionally, the edge node is specifically used to calculate the minimum safe distance between UAVs based on the speed obstacle method; and to generate a conflict avoidance scheme by adopting a fast exploratory random tree algorithm that introduces dynamic constraints and the lowest risk entropy evaluation standard based on the obtained global optimization strategy model and the minimum safe distance between UAVs.

[0012] Optionally, the edge node is also used to acquire and store the current pose data of the UAV in a local spatiotemporal database; the local spatiotemporal database supports querying using a hybrid index structure combining R-trees and timestamp segments.

[0013] On the other hand, the present invention also provides a method for managing the traffic of a drone, comprising:

[0014] The current pose data of the UAV is obtained using a central scheduler;

[0015] Based on the current pose data, combined with the preset flight mission and target area, dynamic scheduling requirements are generated;

[0016] Based on the dynamic scheduling requirements, the preset flight mission is divided into multiple sub-tasks using task decomposition rules.

[0017] Based on the load balancing strategy, each subtask is assigned to a corresponding edge node. The edge node then generates a conflict avoidance scheme based on the target subtask assigned to it, using a two-layer conflict detection mechanism and a path replanning algorithm, and sends it to the UAV.

[0018] Optionally, generating dynamic scheduling requirements based on the current pose data, combined with preset flight missions and target areas, includes: predicting the demand density index of each airspace the UAV passes through during its flight to the target area based on the current pose data and target area, using a time series prediction model; and generating dynamic scheduling requirements for the UAV in each airspace based on the demand density index of each airspace and the timeliness of the preset flight mission.

[0019] Optionally, the step of dividing the preset flight mission into multiple sub-tasks according to the dynamic scheduling requirements and using task decomposition rules includes: dividing the target area into multiple sub-regions using a Voronoi diagram airspace segmentation algorithm based on the dynamic scheduling requirements; and dividing the preset flight mission into multiple sub-tasks using task chain fragmentation technology based on each sub-region.

[0020] Optionally, the step of using task decomposition rules to divide the preset flight mission into multiple sub-tasks includes: based on the resource utilization rate reported by each edge node, using an improved Hungarian algorithm to dynamically adjust the allocation strategy of the multiple sub-tasks with the goal of minimizing the maximum load.

[0021] On the other hand, the present invention also provides a method for managing the traffic of a drone, comprising:

[0022] The target subtasks assigned to the edge nodes are obtained using the edge nodes. The target subtasks are: the central scheduler obtains the current pose data of the UAV, generates dynamic scheduling requirements based on the current pose data, combined with the preset flight mission and target area, and divides the preset flight mission into multiple subtasks based on the dynamic scheduling requirements using task decomposition rules and allocates them based on a load balancing strategy.

[0023] Based on the target sub-task, a two-layer conflict detection mechanism and a path replanning algorithm are used to generate a conflict avoidance scheme and send it to the UAV.

[0024] Optionally, the method of generating conflict avoidance schemes by employing a two-layer conflict detection mechanism and path replanning algorithm includes: calculating the minimum safe distance between UAVs based on the speed obstacle method; and generating conflict avoidance schemes by using a fast exploratory random tree algorithm that incorporates dynamic constraints and the lowest risk entropy evaluation criterion, based on the obtained global optimization strategy model and the minimum safe distance between UAVs.

[0025] Optionally, it also includes: acquiring and storing the current pose data of the UAV in a local spatiotemporal database; the local spatiotemporal database supports querying using a hybrid index structure combining R-trees and timestamp segments.

[0026] On the other hand, the present invention also provides a computer device, characterized in that it includes: one or more processors;

[0027] The processor is used to store one or more programs;

[0028] When the one or more programs are executed by the one or more processors, the traffic management method for the drone described in any one of the above descriptions is implemented.

[0029] On the other hand, the present invention also provides a computer-readable storage medium, characterized in that it stores a computer program thereon, which, when executed, implements the traffic management method for unmanned aerial vehicles described in any one of the above.

[0030] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0031] This invention provides a traffic management system, method, electronic device, and medium for unmanned aerial vehicles (UAVs). The system includes: a central scheduler and multiple edge nodes connected in communication; the central scheduler and each edge node are connected in communication with the UAV; the central scheduler acquires the current pose data of the UAV; based on the current pose data, combined with a preset flight mission and target area, it generates dynamic scheduling requirements; based on the dynamic scheduling requirements, it divides the preset flight mission into multiple sub-tasks using task decomposition rules; based on a load balancing strategy, it assigns each sub-task to a corresponding edge node; the edge nodes, based on the target sub-tasks assigned to them, generate conflict avoidance schemes using a two-layer conflict detection mechanism and a path replanning algorithm, and send them to the UAVs. The central scheduler decomposes the scheduling task into multiple sub-tasks and assigns them to the edge nodes for processing through a distributed computing architecture, and then the edge nodes generate conflict avoidance schemes for each sub-task, realizing dynamic scheduling and conflict avoidance of UAVs, thereby improving the real-time performance of processing and avoiding the risk of single points of failure. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the traffic management system for the drone of the present invention;

[0033] Figure 2 This is a flowchart illustrating the traffic management method for the unmanned aerial vehicle (UAV) of the present invention.

[0034] Figure 3 This is a flowchart illustrating another method for traffic management of a drone according to the present invention;

[0035] Figure 4 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0036] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0037] Example 1:

[0038] This invention provides a traffic management system for unmanned aerial vehicles (UAVs), with the following structure: Figure 1 As shown, it includes a central scheduler 1 and multiple edge nodes 2 with communication connections; the central scheduler 1 and each edge node 2 are connected to the UAV.

[0039] The central scheduler is used to acquire the current pose data of the UAV; based on the current pose data, combined with the preset flight mission and target area, it generates dynamic scheduling requirements; based on the dynamic scheduling requirements, it divides the preset flight mission into multiple sub-tasks using task decomposition rules; and based on the load balancing strategy, it assigns each sub-task to the corresponding edge node.

[0040] Edge nodes are used to generate conflict avoidance schemes based on the target subtasks assigned to the edge nodes, employing a two-layer conflict detection mechanism and path replanning algorithm, and then send them to the UAV.

[0041] To overcome the challenges of traditional centralized scheduling architectures, which struggle to meet real-time requirements and suffer from single-point-of-failure risks, thus hindering the dynamic scheduling and conflict avoidance of massive numbers of drones, this invention employs a central scheduler that uses a distributed computing architecture to decompose scheduling tasks into multiple sub-tasks and distribute them to edge nodes for processing. The edge nodes then generate conflict avoidance schemes for each sub-task, enabling dynamic scheduling and conflict avoidance of drones. This improves real-time processing performance and avoids single-point-of-failure risks.

[0042] To accurately and effectively generate conflict avoidance schemes for drones, the drone traffic management system includes a central scheduler and multiple edge nodes. The central scheduler is communicatively connected to the multiple edge nodes. In order for the drone to implement the conflict avoidance scheme, the central scheduler and each edge node are communicatively connected to the drone.

[0043] The central scheduler is responsible for acquiring the current pose data of each drone. The pose data includes position, velocity, and heading information. The heading information can refer to the yaw angle. It can be understood that each drone can send its own pose data to the central scheduler in real time, or it can send its own pose data to the central scheduler at preset time intervals.

[0044] Specifically, the UAV can be equipped with a lightweight embedded data acquisition module that integrates a high-precision Global Navigation Satellite System (GNSS), an Inertial Measurement Unit (IMU), and airborne sensors. The GNSS can provide real-time kinematic (RTK) positioning, while the airborne sensors can provide point clouds from a Light Detection and Ranging (LiDAR) system. The UAV uploads real-time pose data at a frequency of 20Hz, including high-precision position (±5cm), velocity (±0.1m / s), and heading angle (±0.5°) information.

[0045] The central scheduler generates dynamic scheduling requirements based on the current pose data of each UAV, combined with preset flight missions and target areas. The preset flight missions are defined using JSON structured instructions, including target coordinates, priority (urgent / regular), and mission timeliness (hard deadline / flexible time), and are linked in real-time to a dynamic airspace map (including temporary obstacles and weather data). The target area refers to the specific geographic space that the UAV needs to reach or cover when executing the preset flight mission. This can be a specific geographical location, such as a farm, a forest, or an urban area, or a broader geographic area. Dynamic scheduling requirements refer to adjustments made to the flight plan and task allocation based on real-time conditions during the execution of the preset flight mission and target area coverage.

[0046] The preset flight missions are defined using JSON structured instructions, including target coordinates, priority (urgent / normal), mission timeliness (hard deadline / flexible time), and are bound in real time to the dynamic airspace map (including temporary obstacles and meteorological data).

[0047] In one possible implementation, the central scheduler can input the UAV's current pose data, preset flight mission, and target area into a pre-saved scheduling model to obtain the dynamic scheduling requirements output by the scheduling model.

[0048] To further enhance the flexibility and efficiency of mission execution, the central scheduler can employ task decomposition rules to break down complex, pre-defined flight missions into a series of more manageable and executable sub-missions based on dynamic scheduling needs. This process ensures the rationality of mission allocation and also promotes the optimal allocation of resources. For example, if a pre-defined flight mission is from point A to point B, the decomposed sub-missions could be from point A to point C, and from point C to point B.

[0049] After identifying each subtask, the central scheduler can allocate each subtask to the corresponding edge node based on a load balancing strategy. In one possible implementation, the central scheduler can match the needs of each subtask with the capabilities of the edge nodes. For example, a subtask requiring rapid response can be assigned to an edge node with high real-time requirements.

[0050] After receiving the assigned target subtask, edge nodes can first perform preliminary conflict detection. Specifically, they can quickly scan the task path and timeline to check for obvious conflict points, such as time overlaps or spatial intersections. Then, they perform in-depth conflict analysis, considering more factors such as the drone's performance limitations, flight rules, and environmental obstacles. Upon detecting a conflict, the edge node uses a path replanning algorithm to generate a conflict avoidance solution. The core of the path replanning algorithm is to find a new, conflict-free flight path to meet the drone's mission requirements. The edge node sends the conflict avoidance solution to the drone, which then executes it. It's important to note that edge computing nodes are small data centers distributed at the network edge, used for rapid processing and analysis of local data.

[0051] This invention adopts a distributed computing architecture: the central scheduler is only responsible for global airspace partitioning and task classification, while the specific obstacle avoidance calculation is performed by edge nodes.

[0052] This invention provides a traffic management system for unmanned aerial vehicles (UAVs). The central scheduler decomposes the scheduling task into multiple sub-tasks and distributes them to edge nodes for processing through a distributed computing architecture. The edge nodes then generate conflict avoidance schemes for each sub-task, thereby realizing dynamic scheduling and conflict avoidance of UAVs, which improves the real-time performance of processing and avoids the risk of single point of failure.

[0053] In order to accurately and effectively generate dynamic scheduling requirements, based on the above embodiments, in this embodiment of the invention, the central scheduler is specifically used to predict the demand density index of each airspace that the UAV passes through during its flight to the target area based on the current pose data and the target area, using a time series prediction model; and to generate the dynamic scheduling requirements of the UAV in each airspace based on the demand density index of each airspace and the timeliness of the preset flight mission.

[0054] To accurately and effectively generate dynamic scheduling requirements, the central scheduler locally stores a time-series prediction model. The central scheduler can input the UAV's current pose data and the specific location of the target area into the time-series prediction model, which can be a Long Short-Term Memory (LSTM) network. Specifically, the time-series prediction model predicts the demand density index of the various airspaces the UAV will pass through as it flies from its current location to the target area over a future period. The demand density index refers to the intensity of existing flight activity, including the number of other aircraft, the intersection of flight paths, and potential air traffic control requirements.

[0055] In one possible implementation, based on a time series forecasting model, combined with historical traffic heatmaps and real-time airspace load, the demand density index of each airspace is predicted within the next 5 minutes (for example only).

[0056] The central scheduler generates dynamic scheduling requirements for UAVs in each airspace based on the predicted demand density index for each airspace and the pre-defined timeliness requirements of flight missions. Mission timeliness refers to the degree to which a flight mission is sensitive to time; for example, some missions need to be completed within a specific time period or have specific requirements for flight speed.

[0057] In one possible implementation, the central scheduler can dynamically classify scheduling levels (low / medium / high) based on the demand density index of each airspace, triggering differentiated response mechanisms (such as activating a distributed collaborative avoidance mode in high-density areas). By coupling task timeliness with airspace congestion status, the scheduling priority of urgent tasks in congested areas is automatically increased, avoiding the rigidity problem of the traditional "first-come, first-served" strategy.

[0058] It should be noted that if the demand density index of a certain airspace is high, it means that there may be a lot of flight activity in that area. Drones need to be more cautious when passing through it and may need to adjust their flight speed, altitude or flight path to avoid conflicts with other drones. At the same time, if the mission has strict time requirements, drones may need to prioritize passing through areas with lower demand density to ensure that the mission is completed on time.

[0059] In order to accurately divide the preset flight mission into multiple sub-tasks, based on the above embodiments, in this embodiment of the invention, the central scheduler is specifically used to divide the target area into multiple sub-regions using the Voronoi diagram airspace segmentation algorithm according to dynamic scheduling requirements; and to divide the preset flight mission into multiple sub-tasks using task chain fragmentation technology based on each sub-region.

[0060] After determining the dynamic scheduling requirements of the UAVs, the central scheduler further employs the Voronoi (Thieson polygon) graph spatial segmentation algorithm to divide the target area. Specifically, the target area is divided into multiple adjacent and non-overlapping polygonal sub-regions. Each sub-region contains a specific point called the generation point, and the distance from any position within the sub-region to the generation point is less than the distance to any other generation point.

[0061] In this invention, the central scheduler uses the Voronoi diagram airspace segmentation algorithm to divide the target airspace into multiple sub-regions according to the coverage of edge nodes, ensuring that the number of UAVs in each sub-region does not exceed a preset value, which can be 50 UAVs.

[0062] When applying the Voronoi diagram spatial segmentation algorithm, the central scheduler can select a series of suitable generation points based on the geographical features of the target area, air traffic conditions, flight restrictions, and the dynamic scheduling needs of UAVs. Subsequently, the Voronoi diagram spatial segmentation algorithm calculates the Voronoi polygons defined by these generation points, thereby dividing the target area into multiple sub-regions.

[0063] After acquiring each sub-region, the central scheduler uses task chaining fragmentation technology to divide the pre-set flight mission into multiple sub-tasks. Task chaining fragmentation technology is a task decomposition strategy that breaks down complex tasks into multiple sub-tasks based on factors such as the overall objective of the flight mission, flight path, required resources, and time constraints. For cross-regional flight missions, task chaining fragmentation technology is used to divide continuous flight segments into multiple sub-segments and distribute them to edge nodes along the route for relay processing.

[0064] In order to accurately and effectively allocate subtasks, based on the above embodiments, in this embodiment of the invention, the central scheduler is specifically used to dynamically adjust the allocation strategy of multiple subtasks based on the resource utilization reported by each edge node, using an improved Hungarian algorithm with the goal of minimizing the maximum load.

[0065] To accurately and effectively allocate subtasks, the central scheduler collects resource utilization data from each edge node, including metrics such as Central Processing Unit (CPU), memory, and bandwidth. Edge nodes then send their own resource utilization data to the central scheduler. The central scheduler uses an improved Hungarian algorithm, considering the current load and task requirements of each edge node, to determine the optimal allocation strategy.

[0066] The improved Hungarian algorithm not only considers the matching cost between tasks and edge nodes, but also dynamically adjusts weights to ensure that high-priority tasks are preferentially allocated to edge nodes with sufficient resources. Simultaneously, through iterative optimization, the improved Hungarian algorithm gradually approaches the goal of minimizing the maximum load, avoiding situations where some edge nodes are overloaded while others remain idle.

[0067] This invention reduces cross-node coordination overhead through a segmentation strategy based on flight segment continuity awareness, thereby reducing communication latency by more than 40% compared to traditional random segmentation.

[0068] In order to accurately and effectively generate conflict avoidance schemes, based on the above embodiments, in this embodiment of the invention, the edge nodes are specifically used to calculate the minimum safe distance between UAVs based on the speed obstacle method; according to the obtained global optimization strategy model and the minimum safe distance between UAVs, a fast exploratory random tree algorithm that introduces dynamic constraints and the lowest risk entropy evaluation standard is adopted to generate conflict avoidance schemes.

[0069] To accurately and effectively generate conflict avoidance schemes, in this embodiment of the invention, edge nodes calculate the minimum safe distance between drones based on the velocity obstacle method. Specifically, edge nodes can obtain the relative position and velocity information between drones, and calculate the minimum safe distance between drones using the velocity obstacle method based on the relative position and velocity information.

[0070] Specifically, the minimum safe distance for edge nodes can be calculated using the following formula:

[0071] D safe =v max ×t resp +ε

[0072] Among them, D safe For the minimum safe distance, v max For speed information, t resp For time, t resp The time can be 1.2s, where ε is the preset deviation, which can be 10m.

[0073] To accurately and effectively generate conflict avoidance schemes, edge nodes can construct a comprehensive flat state that describes the UAV's motion state, including but not limited to its position, velocity, acceleration, and possible attitude information. Furthermore, the edge nodes define the UAV's target state, which is the specific location the UAV aims to reach or the specific motion state it wants to achieve. The target state can be pre-saved. Subsequently, the edge nodes initialize a Rapidly-Exploring Random Tree (RRT), whose root node represents the UAV's initial state.

[0074] Edge nodes also create accurate dynamic models for the drone. This model not only reflects the dynamic relationship between the drone's position, velocity, and acceleration, but also reports on the drone's physical limitations, such as maximum speed and maximum acceleration.

[0075] To assess the collision risk of drones under specific conditions, a risk function is predefined. This function combines a global optimization strategy model and the minimum safe distance between drones, quantifying the probability of a drone colliding with other drones or obstacles during flight. Furthermore, this invention introduces the concept of risk entropy, which reflects the uncertainty of risk distribution. Lower risk entropy means a more certain risk distribution, i.e., a lower probability of collision.

[0076] During the expansion phase of the RRT, a state is first randomly sampled from the flat states as a candidate node. Then, the existing node closest to this candidate node is found in the RRT, and a new node is generated by expanding a certain distance from this node towards the candidate node. This new node, during its generation, must not only satisfy dynamic constraints but also undergo a risk function evaluation to ensure its risk entropy is within an acceptable range. If the risk entropy of the new node is lower than a preset threshold, or lower than the risk entropy of some nodes in the current RRT, it will be added to the RRT.

[0077] Once the RRT (Rapid Response Time) is extended sufficiently close to the target state, path searching can begin. This invention uses an efficient search algorithm, such as Dijkstra's algorithm, to backtrack from the target state to the starting state and generate an initial path. However, this path may not be perfect, as it may contain unnecessary detours or sudden turns, which increases the difficulty of controlling the UAV and its energy consumption. Therefore, this path can be smoothed to reduce changes in control input under dynamic constraints and improve the executability of the path.

[0078] After path smoothing, a collision check can be performed. This ensures that every point on the path meets the minimum safe distance requirement during the actual flight of the drone, thereby avoiding collisions with other drones or obstacles. If a potential collision risk is detected, local optimization algorithms, such as gradient descent or particle swarm optimization, can be used to adjust the path to ensure the drone can fly safely along the path.

[0079] This invention introduces dynamic constraints (such as maximum turning angle and acceleration limits) to ensure path feasibility. During the expansion tree growth process, the node with the lowest risk entropy (risk entropy = collision probability × severity) is selected first, replacing the traditional pure distance cost function. Furthermore, the local path can be updated every 200ms, dynamically adjusted in conjunction with real-time environmental changes.

[0080] In order to obtain the current pose data of the UAV, based on the above embodiments, in this embodiment of the invention, the edge node is also used to obtain and store the current pose data of the UAV in a local spatiotemporal database; the local spatiotemporal database supports querying using a hybrid index structure of R-tree combined with timestamp segmentation.

[0081] Edge nodes are responsible for acquiring real-time pose data from the UAV and storing it in a local spatiotemporal database. This database employs a hybrid index structure, combining R-trees and timestamp segmentation to support fast and accurate spatiotemporal queries. The spatial indexing capabilities of R-trees enable edge nodes to efficiently process related queries, while timestamp segmentation further optimizes retrieval along the time dimension, ensuring high query performance even in complex spatiotemporal scenarios.

[0082] Customized Edge Computing Units (ECUs) are deployed at edge nodes, integrating NVIDIA Jetson AGX Orin (32 TOPS computing power), 5G communication modules (supporting NR-U band), and local storage (≥512GB SSD). Lightweight container technology (such as Docker+K3s) is adopted to achieve second-level hot-swapping and resource isolation of algorithm modules (conflict detection, path planning).

[0083] Edge nodes can remove sensor noise through Kalman filtering and compress trajectory data using Delta encoding, reducing bandwidth usage to 15% of the original data. Furthermore, edge nodes store a snapshot of the airspace state over the past 10 minutes (such as UAV pose and obstacle coordinates), supporting millisecond-level spatiotemporal range queries (such as "state of all aircraft within a 500-meter radius"). Employing a hybrid index structure of R-tree and timestamp segments, the efficiency of neighborhood search in collision detection is improved to O(log n) complexity (compared to O(n) for traditional brute-force search).

[0084] Example 2:

[0085] Based on the same inventive concept, this invention also provides a traffic management method for unmanned aerial vehicles (UAVs), applied to a central scheduler, as illustrated in the flowchart below. Figure 2 As shown, it includes:

[0086] Step 201: Obtain the current pose data of the UAV using the central scheduler;

[0087] Step 202: Based on the current pose data, combined with the preset flight mission and target area, generate dynamic scheduling requirements;

[0088] Step 203: Based on the dynamic scheduling requirements, the preset flight mission is divided into multiple sub-tasks using task decomposition rules;

[0089] Step 204: Based on the load balancing strategy, each subtask is assigned to the corresponding edge node. The edge node then generates a conflict avoidance scheme based on the target subtask assigned to it, using a two-layer conflict detection mechanism and a path replanning algorithm, and sends it to the UAV.

[0090] In one specific implementation, step 201 above, based on the current pose data and the target area, predicts the demand density index of each airspace the UAV passes through during its flight to the target area using a time series prediction model; and generates the dynamic scheduling requirements of the UAV in each airspace based on the demand density index of each airspace and the timeliness of the preset flight mission.

[0091] In one specific implementation, step 203 above divides the target area into multiple sub-regions using a Voronoi diagram spatial segmentation algorithm based on dynamic scheduling requirements; and based on each sub-region, a task chain fragmentation technique is used to divide the preset flight mission into multiple sub-tasks.

[0092] In one specific implementation, step 204 above uses an improved Hungarian algorithm based on the resource utilization rate reported by each edge node to dynamically adjust the allocation strategy of multiple sub-tasks with the goal of minimizing the maximum load.

[0093] Based on the same inventive concept, this invention also provides a traffic management method for unmanned aerial vehicles (UAVs) applied to edge nodes, as illustrated in the flowchart below. Figure 3 As shown, it includes:

[0094] Step 301: Use edge nodes to obtain target subtasks assigned to edge nodes; the target subtask is for the central scheduler to obtain the current pose data of the UAV, generate dynamic scheduling requirements based on the current pose data, combined with the preset flight mission and target area, and divide the preset flight mission into multiple subtasks based on the dynamic scheduling requirements and the task decomposition rules, which are allocated based on the load balancing strategy.

[0095] Step 302: Based on the target sub-task, a two-layer conflict detection mechanism and path replanning algorithm are used to generate a conflict avoidance scheme and send it to the UAV.

[0096] In one specific implementation, step 302 above calculates the minimum safe distance between UAVs based on the speed barrier method; and based on the obtained global optimization strategy model and the minimum safe distance between UAVs, a fast exploratory random tree algorithm that introduces dynamic constraints and the lowest risk entropy evaluation standard is used to generate a conflict avoidance scheme.

[0097] One specific implementation also includes: acquiring and storing the current pose data of the UAV in a local spatiotemporal database; the local spatiotemporal database supports querying using a hybrid index structure combining R-trees and timestamp segments.

[0098] Example 3:

[0099] like Figure 4 As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0100] The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and it is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of the UAV traffic management method in the above embodiments.

[0101] Example 4:

[0102] Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). An electronic device readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both built-in storage media within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of a UAV traffic management method described in the above embodiments.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] 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 its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.

Claims

1. A traffic management system for unmanned aerial vehicles (UAVs), characterized in that, It includes a central scheduler with communication connections and multiple edge nodes; the central scheduler and each of the edge nodes are communicatively connected to the UAV. The central scheduler is used to acquire the current pose data of the UAV; Based on the current pose data and the target area, and using a time series prediction model, the demand density index of each airspace the UAV passes through during its flight to the target area is predicted. Based on the demand density index of each airspace and the timeliness of the preset flight mission, the dynamic scheduling requirements of the UAV in each airspace are generated. Based on the dynamic scheduling requirements, the target area is divided into multiple sub-regions using a Voronoi diagram airspace segmentation algorithm. Based on each sub-region, the preset flight mission is divided into multiple sub-tasks using a task chain fragmentation technique. Based on the load balancing strategy, each subtask is assigned to a corresponding edge node; The edge node is used to generate a conflict avoidance scheme based on the target sub-task assigned to the edge node, using a two-layer conflict detection mechanism and a path replanning algorithm, and send it to the UAV. The edge nodes are used to calculate the minimum safe distance between UAVs based on the velocity obstacle method; based on the obtained global optimization strategy model and the minimum safe distance between UAVs, the Fast Exploratory Random Tree (RRT) algorithm, which introduces dynamic constraints and the lowest risk entropy evaluation standard, is used to generate conflict avoidance schemes. The global optimization strategy model and the minimum safe distance between the UAV are used to assess the collision risk of the UAV in a specific state. The specific state corresponds to the node generated in the RRT extension stage, and the node is located on the path of the UAV during actual flight. The lower the risk entropy, the lower the probability of a collision.

2. The system as described in claim 1, characterized in that, The central scheduler is used to dynamically adjust the allocation strategy of multiple sub-tasks based on the resource utilization reported by each edge node, using an improved Hungarian algorithm with the goal of minimizing the maximum load.

3. The system as described in claim 1, characterized in that, The edge node is also used to acquire and store the current pose data of the UAV in a local spatiotemporal database; the local spatiotemporal database supports querying using a hybrid index structure that combines R-trees with timestamp segments.

4. A method for managing traffic flow in unmanned aerial vehicles (UAVs), characterized in that, include: The current pose data of the UAV is obtained using a central scheduler; Based on the current pose data and the target area, and using a time series prediction model, the demand density index of each airspace the UAV passes through during its flight to the target area is predicted. Based on the demand density index of each airspace and the timeliness of the preset flight mission, the dynamic scheduling requirements of the UAV in each airspace are generated. Based on the dynamic scheduling requirements, the target area is divided into multiple sub-regions using a Voronoi diagram airspace segmentation algorithm. Based on each sub-region, the preset flight mission is divided into multiple sub-tasks using a task chain fragmentation technique. Based on the load balancing strategy, each subtask is assigned to a corresponding edge node; Utilize the edge nodes to obtain the target subtasks assigned to the edge nodes; Based on the target sub-task, a conflict avoidance scheme is generated and sent to the UAV using a two-layer conflict detection mechanism and path replanning algorithm. This includes: calculating the minimum safe distance between UAVs based on the speed obstacle method; and generating a conflict avoidance scheme using the Fast Exploratory Random Tree (RRT) algorithm, which incorporates dynamic constraints and the lowest risk entropy evaluation criterion, based on the obtained global optimization strategy model and the minimum safe distance between UAVs. The global optimization strategy model and the minimum safe distance between the UAV are used to assess the collision risk of the UAV in a specific state. The specific state corresponds to the node generated in the RRT extension stage, and the node is located on the path of the UAV during actual flight. The lower the risk entropy, the lower the probability of a collision.

5. An electronic device, characterized in that, include: At least one processor and memory; The memory and processor are connected via a bus; The memory is used to store one or more programs; When the one or more programs are executed by the at least one processor, the traffic management method for the drone as described in claim 4 is implemented.

6. A readable storage medium, characterized in that, It contains an executable program, which, when executed, implements the UAV traffic management method as described in claim 4.

Images