Multi-target unmanned aerial vehicle scheduling method, device, equipment and medium

Abstract

The invention provides a multi-target unmanned aerial vehicle scheduling method and device, equipment and a medium, relates to the technical field of unmanned aerial vehicle navigation, and is used for solving the technical problem that an existing unmanned aerial vehicle scheduling method is difficult to meet real-time and efficient path planning requirements for a multi-target task. The method comprises the following steps: acquiring space environment characteristics corresponding to a current airspace of an unmanned aerial vehicle; according to the space environment characteristics, utilizing a pre-constructed path searching model to identify an optimal path of each unmanned aerial vehicle in each height layer, which can reach the target position by avoiding the no-fly zone from the initial position; according to the optimal path, each unmanned aerial vehicle is controlled to execute a flight task in each height layer according to a specified flight path; in response to the fact that the flight distance between any two unmanned aerial vehicles located in the same height layer is smaller than a safety distance threshold value, the flight state of one unmanned aerial vehicle is switched and the flight height of the other unmanned aerial vehicle is adjusted, so that any two unmanned aerial vehicles are located in different height layers for flight scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle navigation, and more specifically, to a multi-target unmanned aerial vehicle scheduling method, device, equipment and medium. Background Art

[0002] With the development of unmanned aerial vehicle (UAV) technology, UAVs have shown good application prospects in various fields. Currently, UAVs are combined with many industries in the low-altitude environment to perform tasks that are difficult for humans to operate and achieve, such as bridge and tunnel damage detection, high-altitude litter identification, security patrol, aerial photography, etc. Currently, the flight altitude of UAVs for industrial applications is in the low-altitude environment below 400 m. The complex low-altitude environment poses new requirements for the UAV path planning algorithm. UAV path planning is the basis for UAVs to perform tasks, and its purpose is to plan the optimal path between the starting position and the target position in a specific environment. In recent years, more and more researchers have studied this by combining the low-altitude environment and using various algorithms. Commonly used algorithms include graph search algorithms, linear programming methods, traditional / improved intelligent optimization algorithms, and machine learning algorithms, etc.

[0003] However, for the existing UAV path planning algorithms, on the one hand, the environmental settings are single, ignoring the practicability of the algorithms and the constraints of obstacles in different scenarios, and it is difficult to solve the problem of UAV collisions caused by route conflicts; on the other hand, due to their own different natures, the existing UAV path planning algorithms have certain limitations. It can be seen that the existing UAV scheduling methods are difficult to meet the path planning requirements for the real-time and high-efficiency of multi-target tasks. Summary of the Invention

[0004] In view of this, the present invention provides a multi-target unmanned aerial vehicle scheduling method, device, equipment and medium to solve the technical problem that the existing UAV scheduling methods are difficult to meet the path planning requirements for the real-time and high-efficiency of multi-target tasks.

[0005] An aspect of the present invention provides a multi-target UAV scheduling method, including: obtaining the spatial environment characteristics corresponding to the current airspace of the UAV, where the spatial environment characteristics are divided into multiple altitude layers; according to the spatial environment characteristics, using a pre-constructed path search model, identifying the optimal path for each UAV in each altitude layer to reach the target position while avoiding no-fly zones from the starting position, where the optimal path represents the least resource consumption required for the UAV to reach the target position from the starting position; controlling each UAV to perform flight tasks according to the specified flight route in each altitude layer according to the optimal path; in response to the flight distance between any two UAVs in the same altitude layer being less than the safety distance threshold, by switching the flight state of one of the UAVs and adjusting the flight altitude of the other UAV, making any two UAVs fly in different altitude layers for flight scheduling.

[0006] According to an embodiment of the present invention, the path search model is constructed based on the A* search algorithm; wherein, according to the spatial environment characteristics, using a pre-constructed path search model, identifying the optimal path for each UAV in each altitude layer to reach the target position while avoiding no-fly zones from the starting position includes: extracting the resource consumption parameters for the UAV to reach the next node from the current arbitrary position, where the resource consumption parameters include the first resource consumption parameters for the UAV to reach all adjacent nodes from the current arbitrary position, and the second resource consumption parameters for predicting to reach the target position from each adjacent node; selecting the node with the smallest resource consumption parameter in the next nodes as the starting node, and continuing to search for the node with the smallest resource consumption parameter from the starting node to the next nodes; in response to the node with the smallest resource consumption parameter reaching the target position in the next step, starting from the target position and backtracking to the starting position to obtain the optimal path of the UAV.

[0007] According to an embodiment of the present invention, the path search model is configured with: an open list, where the open list is used to store the nodes to be searched during the process of the path search model searching for the optimal path; a closed list, where the closed list is used to store the nodes that have been searched during the process of the path search model searching for the optimal path.

[0008] According to an embodiment of the present invention, before controlling each UAV to perform flight tasks according to the specified flight route in each altitude layer according to the optimal path, it further includes: detecting whether the optimal path passes through a no-fly zone; in response to the optimal path passing through a no-fly zone, re-identifying a new optimal path.

[0009] According to an embodiment of the present invention, detecting whether an optimal path passes through a no-fly zone includes: establishing a feature model of the no-fly zone, where the feature model is configured to be constructed by a polygon defined by a set of vertices; emitting a ray along the X-axis direction from any node in the optimal path, and counting the number of intersection points between the ray and the sides of the polygon; in response to the number of intersection points being odd, the optimal path does not pass through the no-fly zone; in response to the number of intersection points being even, the optimal path passes through the no-fly zone.

[0010] According to an embodiment of the present invention, flight scheduling for any two drones to fly at different altitude levels by switching the flight state of one of the drones and adjusting the flight altitude of the other drone includes: in response to the flight distance between any two drones at the same altitude level being less than the safety distance threshold, switching the flight state of one of the drones to the waiting state, where the drone remains stationary in the waiting state; based on the waiting state, adjusting the flight altitude of the other drone to a different altitude level.

[0011] According to an embodiment of the present invention, the multi-target drone scheduling method further includes: configuring a path list, where the path list is used to record the path information of each drone, and each node in the path information includes the three-dimensional coordinate value of the corresponding drone at that node; in response to a change in the flight position and flight altitude of any one drone, updating the path list in real time to record the latest position information and altitude information of the corresponding drone.

[0012] Another aspect of the present invention provides a multi-target drone scheduling device, including: an acquisition module, configured to acquire the spatial environment characteristics corresponding to the current airspace of the drones, where the spatial environment characteristics are divided into multiple altitude levels; an identification module, configured to identify, according to the spatial environment characteristics and using a pre-constructed path search model, the optimal path for each drone in each altitude level to reach the target position while avoiding the no-fly zone from the starting position, where the optimal path represents the least resource consumption required for the drone to reach the target position from the starting position; an execution module, configured to control each drone to execute a flight task according to the specified flight route in each altitude level according to the optimal path; a scheduling module, configured to, in response to the flight distance between any two drones at the same altitude level being less than the safety distance threshold, perform flight scheduling for any two drones to fly at different altitude levels by switching the flight state of one of the drones and adjusting the flight altitude of the other drone.

[0013] Another aspect of the present invention provides an electronic device, including: one or more processors; a memory, configured to store one or more programs, where when the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0014] Another aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method as described above.

[0015] Another aspect of the present invention provides a computer program product that includes computer-executable instructions that, when executed, are used to implement the method as described above.

[0016] Compared with the prior art, the multi-target UAV scheduling method, device, equipment, and medium provided by the present invention have at least the following beneficial effects:

[0017] (1) The multi-target UAV scheduling method, device, equipment, and medium provided by the present invention divide the airspace into multiple altitude layers, search for the optimal paths of each UAV according to the path search model in each altitude layer, and then perform task scheduling according to the optimal paths. When conflicts occur in the paths of UAVs in the same altitude layer, the conflicts are resolved by adjusting the flight states and flight altitudes of the UAVs, enabling the UAVs to achieve optimal scheduling at low altitudes and avoid collisions, and being applicable to fields such as future low-altitude UAV logistics and urban flying car commuting.

[0018] (2) The multi-target UAV scheduling method, device, equipment, and medium provided by the present invention generate the optimal path based on the A* search algorithm. Since the A* search algorithm has high flexibility and customizability and can combine the actual cost of reaching a node from the starting position (i.e., the first resource consumption parameter) and the predicted cost of reaching the target position from the node (i.e., the second resource consumption parameter), it preferentially selects nodes for expansion. Therefore, it can quickly generate the optimal path in the shortest time and avoid unnecessary computational overhead. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Through the following description of the embodiments of the present invention with reference to the drawings, the above and other objects, features, and advantages of the present invention will become clearer. In the drawings:

[0020] Figure 1 Schematically shows a flowchart of the multi-target UAV scheduling method according to an embodiment of the present invention;

[0021] Figure 2 Schematically shows a flowchart of generating the optimal path of a UAV using the A* search algorithm according to an embodiment of the present invention;

[0022] Figure 3 Schematically shows a structural block diagram of the multi-target UAV scheduling device according to an embodiment of the present invention;

[0023] Figure 4 Schematically shows a structural block diagram of an electronic device suitable for implementing the multi-target UAV scheduling method according to an embodiment of the present invention. Detailed implementation manners

[0024] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In the following detailed description, for the sake of explanation, numerous specific details are set forth in order to provide a comprehensive understanding of the embodiments of the present invention. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts of the present invention.

[0025] The terms used herein are merely for describing specific embodiments and are not intended to limit the present invention. The terms "including", "comprising" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0027] In the case of using expressions such as "at least one of A, B, and C, etc.", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but is not limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0028] In the embodiments of the present invention, in terms of the collection, update, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the involved data (for example, including but not limited to user personal information), they all comply with the provisions of relevant laws and regulations, are used for legal purposes, and do not violate public order and good customs. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and to safeguard the security of user personal information, network security, and national security.

[0029] With the development of Unmanned Aerial Vehicle (UAV) technology, UAVs have shown good application prospects in various fields. Currently, UAVs are combined with many industries in the low-altitude environment to perform tasks that are difficult for humans to operate and achieve, such as bridge and tunnel damage detection, high-altitude litter identification, security patrol, aerial photography, etc. Currently, the flight altitude of UAVs for industrial applications is in the low-altitude environment below 400 m. The complex low-altitude environment has put forward new requirements for UAV path planning algorithms. UAV path planning is the basis for UAVs to perform tasks, and its purpose is to plan the optimal path between the starting position and the target position in a specific environment. In recent years, more and more researchers have studied this by combining the low-altitude environment and using various algorithms. Commonly used algorithms include graph search algorithms, linear programming methods, traditional / improved intelligent optimization algorithms, and machine learning algorithms, etc.

[0030] Graph search algorithms are the most widely used algorithms in graph theory. Among them, Dijkstra (Dijkstra's algorithm), as a classic graph search algorithm, shows higher search efficiency than depth-first search and breadth-first search in solving the shortest path problem. However, with the in-depth study of problems, the irregularity of obstacles in the actual scenario makes it impossible to simply describe them with nodes and line segments. Moreover, as the search map increases and the number of nodes increases, the execution efficiency of the algorithm for solving the shortest path is too low.

[0031] Linear programming algorithms are a mathematical theory and method for studying the extreme values of linear objective functions under linear constraint conditions, and are widely used in the fields of military, engineering technology, computer, etc. Compared with other algorithms, linear programming algorithms have the characteristics of simple calculation, high efficiency, and can be solved in real time, and are also widely used in UAV path planning. However, linear programming algorithms cannot handle problems with more decision variables within a limited calculation time.

[0032] Intelligent optimization algorithms are developed by simulating or revealing certain natural phenomena or the intelligent behaviors of biological populations. They generally have the advantages of simplicity, generality, and convenience for parallel processing. In terms of UAV path planning, genetic algorithms, particle swarm algorithms, ant colony algorithms, etc. are applied more. However, genetic algorithms have a slow search speed, are easy to fall into local optima, and the parameter settings are too dependent on experience. The calculation amount of the algorithm is large and the time cost is high.

[0033] Reinforcement Learning (RL), an important branch of machine learning, is currently widely used in the fields of traffic control and robotics, such as autonomous / assisted driving, ground traffic path optimization, UAV obstacle avoidance and path planning. Reinforcement learning is an artificial intelligence algorithm that optimizes decisions by continuously interacting with the environment, making trial and error, and obtaining feedback information. Although it has strong generality and can generate a large number of samples for supervised learning, it can only handle problems that require short-term memory, may not converge, and requires fine-tuning of parameters.

[0034] However, on the one hand, the existing UAV path planning algorithms have a single environmental setting, ignoring the practicality of the algorithms and the constraints of obstacles in different scenarios, and it is difficult to solve the problem of UAV collisions caused by route conflicts. On the other hand, due to their own different natures, the existing UAV path planning algorithms have certain limitations. It can be seen that the existing UAV scheduling methods are difficult to meet the path planning requirements for the real-time and efficiency of multi-objective tasks.

[0035] Based on this, the embodiments of the present invention provide a multi-objective UAV scheduling method to solve the technical problem that the existing UAV scheduling methods are difficult to meet the path planning requirements for the real-time and efficiency of multi-objective tasks.

[0036] The method includes: obtaining the spatial environmental characteristics corresponding to the current airspace of the UAV, where the spatial environmental characteristics are divided into multiple altitude layers; according to the spatial environmental characteristics, using a pre-constructed path search model to identify the optimal path for each UAV in each altitude layer to reach the target position while avoiding the no-fly zone from the starting position, where the optimal path represents the least resource consumption required for the UAV to reach the target position from the starting position; controlling each UAV to execute the flight task according to the specified flight route in each altitude layer; in response to the flight distance between any two UAVs in the same altitude layer being less than the safety distance threshold, by switching the flight state of one of the UAVs and adjusting the flight altitude of the other UAV, so that any two UAVs fly in different altitude layers for flight scheduling.

[0037] The multi-objective UAV scheduling method provided by the embodiments of the present invention divides the airspace into multiple altitude layers, searches for the optimal paths of each UAV according to the path search model in each altitude layer, and then performs task scheduling according to the optimal paths. When conflicts occur in the paths of UAVs in the same altitude layer, the conflicts are resolved by adjusting the flight states and flight altitudes of the UAVs, enabling the UAVs to achieve optimal scheduling at low altitude and avoid collisions, and is applicable to fields such as future low-altitude UAV logistics and urban flying car commuting.

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following provides a further detailed description of the present invention in conjunction with specific embodiments and with reference to the accompanying drawings.

[0039] Figure 1 The flowchart of the multi-objective UAV scheduling method according to an embodiment of the present invention is schematically shown.

[0040] As Figure 1 shown, the multi-objective UAV scheduling method of this embodiment may include operations S1 to S4, for example.

[0041] In operation S1, obtain the spatial environmental characteristics corresponding to the current airspace of the UAV, where the spatial environmental characteristics are divided into multiple altitude layers.

[0042] In operation S2, according to the spatial environmental characteristics, use the pre-constructed path search model to identify the optimal path for each UAV in each altitude layer to reach the target position while avoiding no-fly zones from the starting position. Here, the optimal path represents the least resource consumption required for the UAV to reach the target position from the starting position.

[0043] In operation S3, control each UAV to perform flight tasks according to the specified flight route in each altitude layer according to the optimal path.

[0044] In operation S4, in response to the flight distance between any two UAVs in the same altitude layer being less than the safety distance threshold, by switching the flight state of one of the UAVs and adjusting the flight altitude of the other UAV, the two UAVs are made to fly in different altitude layers for flight scheduling.

[0045] In this embodiment, the multi-objective UAV scheduling method may be implemented based on a UAV simulation model, and the relevant attribute configurations of this UAV simulation model are as follows:

[0046] (1) UAV coordinates:

[0047] The UAV coordinates are conventional three-axis coordinates, that is, the X, Y, and Z axes, which are used to complete the simulation of the movement in the three-dimensional world.

[0048] (2) UAV speed:

[0049] The UAV speed is constant, and in each simulation cycle, only a fixed unit length displacement movement in one direction of the horizontal direction (X-axis, Y-axis) and the vertical direction (Z-axis) can be completed.

[0050] (3) UAV state:

[0051] There are three basic states of the UAV during the simulation process:

[0052] Waiting state (waiting): When the drone needs to resolve conflicts or wait for optimal flight conditions, it is in the waiting state, and the drone remains stationary in the waiting state.

[0053] Flying state (flying): When the drone has no conflicts and can fly normally, it is in the flying state.

[0054] Arrival state (end): When the drone reaches the destination, it is in the arrival state, and the altitude drops to 0.

[0055] (4) Drone movement rules:

[0056] The movement rules of the drone within each simulation cycle are as follows:

[0057] Single-direction movement: The drone can only choose one direction for each movement, either moving in the horizontal direction (X-axis or Y-axis) or in the vertical direction (Z-axis).

[0058] Fixed unit length: The distance of each movement is a fixed unit length. In this embodiment, the unit length is set to 300 units to ensure the consistency of the simulation step size.

[0059] Altitude adjustment: When conflicts need to be resolved, the drone can adjust its altitude, but the new altitude must be recorded in the path list after each adjustment.

[0060] In this embodiment, after obtaining the spatial environmental characteristics of the airspace, the path search model is used to search for the path with the minimum cost (resource consumption) for each drone in each altitude layer to reach the target position while avoiding the no-fly zone from the starting position as the optimal path. Then, this optimal path is passed to the drone for flight scheduling and task execution. When conflicts occur between any two drones in the same altitude layer, for example, one drone can be kept stationary, and the flight altitude of the other drone can be adjusted to avoid collisions.

[0061] The multi-objective drone scheduling method provided by the embodiment of the present invention divides the airspace into multiple altitude layers, searches for the optimal paths of each drone according to the path search model in each altitude layer, and then performs task scheduling according to this optimal path. When conflicts occur in the drone paths in the same altitude layer, the conflicts are resolved by adjusting the flight state and flight altitude of the drone, enabling the drone to achieve optimal scheduling at low altitude and avoid collisions, and is applicable to fields such as future low-altitude drone logistics and urban flying car commuting.

[0062] According to the embodiment of the present invention, in operation S1, the spatial environmental characteristics corresponding to the current airspace of the drone are obtained. For example, the spatial environmental characteristics can be generated by constructing an airspace model.

[0063] In this embodiment, the airspace model is configured as a three-dimensional space, which includes the following parameters:

[0064] Width: The range of the airspace in the X-axis direction.

[0065] Height: The range of the airspace in the Y-axis direction.

[0066] Maximum height: The range of the airspace in the Z-axis direction.

[0067] No-fly zone: The area in the airspace where drones are prohibited from entering.

[0068] In this embodiment, the airspace is divided into multiple altitude layers, and the flight altitudes of drones within each layer are similar. For example, vertical stratification can be defined, with each 200 meters as a layer.

[0069] According to an embodiment of the present invention, the path search model is constructed based on the A* search algorithm.

[0070] The A* search algorithm, also known as the A-star algorithm, as one of the heuristic search algorithms, is an algorithm that finds the lowest passing cost for a path with multiple nodes on a graphical plane.

[0071] In this embodiment, operation S2, according to the spatial environment characteristics, uses the pre-constructed path search model to identify the optimal path for each drone in each altitude layer to reach the target position while avoiding the no-fly zone. For example, it may include operations S21 to S23.

[0072] In operation S21: Extract the resource consumption parameters for the drone to reach the next node from the current arbitrary position, where the resource consumption parameters include the first resource consumption parameters for the drone to reach all adjacent nodes from the current arbitrary position, and the second resource consumption parameters for predicting to reach the target position from each adjacent node.

[0073] In operation S22: Select the node with the smallest resource consumption parameter in the next nodes as the starting node, and continue to search for the node with the smallest resource consumption parameter from the starting node to the next nodes.

[0074] In operation S23: In response to the node with the smallest resource consumption parameter reaching the target position in the next step, starting from the target position, backtrack to the starting position to obtain the optimal path of the drone.

[0075] According to an embodiment of the present invention, the path search model is configured with an open list and a closed list.

[0076] Among them, the open list is used to store the nodes to be searched during the process of the path search model searching for the optimal path. The closed list is used to store the nodes that have been searched during the process of the path search model searching for the optimal path.

[0077] In this embodiment, the optimal path of the drone is generated by the A* search algorithm. Among them, the process of generating the optimal path of the drone using the A* search algorithm is as Figure 2 shown.

[0078] Figure 2 FIG. schematically shows a flowchart of generating an optimal path of a drone using the A* search algorithm according to an embodiment of the present invention.

[0079] As Figure 2 shown, this embodiment uses the A* search algorithm for autonomous path planning of the drone to ensure finding the optimal path considering no-fly zones. This algorithm uses a heuristic function to estimate the minimum cost from the current node to the target node, and at the same time maintains an open list and a closed list to store the nodes to be explored and the nodes that have been explored respectively, ensuring the efficiency of the algorithm.

[0080] The process of generating the optimal path of the drone using the A* search algorithm according to the embodiment of the present invention is specifically as follows:

[0081] (1) Initialization:

[0082] First, set the starting node (starting position) and the target node (target position) of the drone, and pass in a heuristic function and a neighbors function for the A* search algorithm. The heuristic function is used to estimate the minimum cost from the current node to the target node, and the neighbors function is used to determine all the neighbor nodes of the current node (i.e., the possible next moving directions). These functions help the algorithm evaluate the advantages and disadvantages of each path as efficiently as possible. When the algorithm is initialized, the initial state of the drone is stored in the open list, and its initial path cost is set to 0.

[0083] (2) Search process:

[0084] The A* search algorithm selects the node with the minimum estimated cost f (resource consumption) in the open list as the current node. The calculation method is:

[0085] f = g + h

[0086] where g represents the path cost from the starting point to the current node, and h represents the heuristic cost (i.e., the predicted cost) from the current node to the target node.

[0087] Specifically:

[0088] Search all adjacent nodes of the current node, calculate the cost g of each adjacent node, and use the heuristic function h to estimate the minimum cost from this node to the target node.

[0089] If the adjacent node is not in the closed list, add it to the open list and record the path cost from the start node to this node and its parent node (for path backtracking).

[0090] If the adjacent node is already in the open list but the current path has a lower cost than the previously recorded path cost, update the path and cost of this node.

[0091] This process continues until the target node is found or the open list is empty. When the open list is empty, it means there is no feasible path to the target node.

[0092] (3)Path backtracking:

[0093] When the A* search algorithm finds the target node, reconstruct the optimal path of the UAV by backtracking the parent nodes of the nodes in the closed list.

[0094] This path backtracking process starts from the target node, gradually backtracks to the start node, and finally forms a complete path to obtain the optimal path.

[0095] The multi-target UAV scheduling method provided by the embodiments of the present invention generates an optimal path based on the A* search algorithm. Since the A* search algorithm has high flexibility and customizability and can combine the actual cost of reaching a node from the starting position (i.e., the first resource consumption parameter) and the predicted cost of reaching the target position from the node (i.e., the second resource consumption parameter) to preferentially select nodes for expansion, it can quickly generate the optimal path in the shortest time and avoid unnecessary computational overhead.

[0096] In addition, since the no-fly zone has a great impact on the UAV during the subsequent flight mission execution, before executing the flight mission, it is necessary to ensure that the flight path of the UAV bypasses the no-fly zone. That is, before executing the flight mission, it is necessary to detect whether the optimal path of the UAV passes through the no-fly zone. If the optimal path passes through the no-fly zone, a new optimal path needs to be re-identified.

[0097] According to an embodiment of the present invention, detecting whether the optimal path passes through the no-fly zone may include, for example:

[0098] Establish a feature model of the no-fly zone, where the feature model is configured to be constructed by a polygon defined by a set of vertices;

[0099] Starting from any node in the optimal path, emit a ray along the X-axis direction and count the number of intersections of the ray with the polygon edges;

[0100] In response to the number of intersections being odd, the optimal path does not pass through the no-fly zone;

[0101] In response to the number of intersections being even, the optimal path passes through the no-fly zone.

[0102] In this embodiment, detecting whether the optimal path passes through a no-fly zone can be achieved by establishing a feature model of the no-fly zone (i.e., the no-fly zone model), and the no-fly zone model defines a specific area in the airspace where drones cannot enter.

[0103] The no-fly zone consists of a polygon or multiple polygons, and each polygon is defined by a set of vertices. The design of the no-fly zone model takes into account how to effectively determine whether a point is within the no-fly zone and how to apply these no-fly zones in airspace management. Specifically:

[0104] In this embodiment, the no-fly zone is represented as a polygon composed of a set of ordered vertices. The polygon can be a simple convex polygon or a complex non-convex polygon. To determine whether a point is within the no-fly zone, this embodiment adopts the ray method determination algorithm. Its basic idea is to emit a ray along the X-axis direction from the point to be determined and count the number of intersections between the ray and the sides of the polygon. If the number of intersections is odd, the point is inside the polygon; if it is even, the point is outside the polygon.

[0105] After checking each point in the path to ensure that the drones avoid all no-fly zones and select the optimal path, then perform operation S3 to control each drone to execute the flight mission according to the specified flight route at each altitude layer.

[0106] The multi-objective drone scheduling method provided by the embodiment of the present invention, after the backtracking ends, transmits the optimal path to the drones for their actual flight use. At the same time, the no-fly zone model ensures that the drones avoid all no-fly zones and select the shortest path by checking each point in the path, greatly improving the accuracy of task scheduling.

[0107] According to an embodiment of the present invention, in operation S4, by switching the flight state of one of the drones and adjusting the flight altitude of another drone, so that any two drones fly at different altitude layers for flight scheduling. For example, it may include operations S41~S42.

[0108] In operation S41, in response to the flight distance between any two drones located at the same altitude layer being less than the safety distance threshold, switch the flight state of one of the drones to the waiting state, where the drone remains stationary in the waiting state.

[0109] In operation S42, based on the waiting state, adjust the flight altitude of the other drone to a different altitude layer.

[0110] In this embodiment, in order to effectively manage multiple drones and avoid conflicts, in drone airspace management, strategies such as hierarchical management, priority allocation, conflict detection and resolution are adopted. Specifically:

[0111] Regarding the hierarchical management strategy: Referring to the description of the above airspace model, the airspace is divided into multiple altitude layers, and the flight altitudes of the unmanned aerial vehicles (UAVs) within each layer are similar. For example, vertical stratification can be defined, with each 200 meters as a layer.

[0112] Regarding the priority assignment strategy: Each UAV is assigned to a specific altitude layer during registration. Generally, UAVs in the lower layers have higher priorities to support emergency missions or low-altitude flights.

[0113] Regarding the conflict detection strategy: Potential conflicts are identified by checking the distances between UAVs within each altitude layer. If the distance between any two UAVs is less than the set safety distance threshold (e.g., 300 meters), a conflict may occur.

[0114] Regarding the conflict resolution strategy: When a conflict is detected, the status of the affected UAVs is switched from "flying state" to "waiting state", and then one or more of the UAVs are adjusted to another altitude layer until the conflict is resolved or a safe flight altitude is found. The specific altitude adjustment is dynamically determined during each conflict resolution to avoid re - conflicts.

[0115] According to an embodiment of the present invention, the multi - target UAV scheduling method may further include operations S5 - S6.

[0116] In operation S5, a path list is configured, where the path list is used to record the path information of each UAV, and each node in the path information includes the three - dimensional coordinate values of the corresponding UAV at that node.

[0117] In operation S6, in response to a change in the flight position and flight altitude of any one UAV, the path list is updated in real time to record the latest position information and altitude information of the corresponding UAV.

[0118] In this embodiment, in order to better track the flight path of the UAV, the path information of each UAV is recorded in the form of a list. Each path point contains the X, Y, Z coordinate values of the UAV at that point. Each time the UAV moves or its altitude is adjusted, the path list is updated to record the latest position information and altitude information.

[0119] Figure 3 Schematically shows a structural block diagram of a multi - target UAV scheduling device according to an embodiment of the present invention.

[0120] As Figure 3 shown, the multi - target UAV scheduling device 300 according to an embodiment of the present invention includes: an acquisition module 310, an identification module 320, an execution module 330, and a scheduling module 340.

[0121] Among them, the acquisition module 310 is used to acquire the spatial environment characteristics corresponding to the current airspace of the UAV, where the spatial environment characteristics are divided into multiple altitude layers.

[0122] The recognition module 320 is used to utilize the pre-constructed path search model according to the spatial environment characteristics to recognize the optimal path for each UAV in each altitude layer to reach the target position while avoiding the no-fly zone from the starting position. The optimal path represents the least resource consumption required for the UAV to reach the target position from the starting position.

[0123] The execution module 330 is used to control each UAV to execute the flight mission according to the specified flight route in each altitude layer according to the optimal path.

[0124] The scheduling module 340 is used to respond to the flight distance between any two UAVs in the same altitude layer being less than the safety distance threshold, and by switching the flight state of one of the UAVs and adjusting the flight altitude of the other UAV, to make any two UAVs fly in different altitude layers for flight scheduling.

[0125] Any number of, or at least part of the functions of, the modules, sub-modules, units, and sub-units according to the embodiments of the present invention can be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present invention can be split into multiple modules for implementation. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present invention can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by any other reasonable way of integrating or packaging the circuit in hardware or firmware, or implemented in any one of the three implementation ways of software, hardware, and firmware or in an appropriate combination of any several of them. Alternatively, one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present invention can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding functions can be executed.

[0126] For example, any number of the obtaining module 310, the identifying module 320, the executing module 330, and the scheduling module 340 may be combined and implemented in one module / cell / sub-cell, or any one of the modules / cells / sub-cells may be split into multiple modules / cells / sub-cells. Alternatively, at least part of the functions of one or more of these modules / cells / sub-cells may be combined with at least part of the functions of other modules / cells / sub-cells and implemented in one module / cell / sub-cell. According to an embodiment of the present invention, at least one of the obtaining module 310, the identifying module 320, the executing module 330, and the scheduling module 340 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or may be implemented by any other reasonable means such as hardware or firmware through circuit integration or packaging, or may be implemented in any one of the three implementation manners of software, hardware, and firmware, or in an appropriate combination of any several of them. Alternatively, at least one of the obtaining module 310, the identifying module 320, the executing module 330, and the scheduling module 340 may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding functions may be executed.

[0127] It should be noted that the part of the track association device based on parameter space conversion in the embodiments of the present invention corresponds to the part of the track association method based on parameter space conversion in the embodiments of the present invention. For the description of the part of the track association device based on parameter space conversion, reference may be specifically made to the part of the track association method based on parameter space conversion, and details are not described herein again.

[0128] Figure 4 A structural block diagram of an electronic device suitable for implementing the multi-target UAV scheduling method according to an embodiment of the present invention is schematically shown. Figure 4 The shown electronic device is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0129] Such as Figure 4As shown, the electronic device 400 according to an embodiment of the present invention includes a processor 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage section 408 into a random access memory (RAM) 403. The processor 401 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application-specific integrated circuit (ASIC)), and so on. The processor 401 may also include on-board memory for caching purposes. The processor 401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0130] In the RAM 408, various programs and data required for the operation of the electronic device 400 are stored. The processor 401, the ROM 402, and the RAM 408 are connected to each other via a bus 404. The processor 401 performs various operations of the method flow according to an embodiment of the present invention by executing the programs in the ROM 402 and / or the RAM 408. It should be noted that the programs may also be stored in one or more memories other than the ROM 402 and the RAM 408. The processor 401 may also perform various operations of the method flow according to an embodiment of the present invention by executing the programs stored in the one or more memories.

[0131] According to an embodiment of the present invention, the electronic device 400 may further include an input / output (I / O) interface 405, and the input / output (I / O) interface 405 is also connected to the bus 404. The electronic device 400 may further include one or more of the following components connected to the input / output (I / O) interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output (I / O) interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed.

[0132] According to an embodiment of the present invention, the method flow according to the embodiment of the present invention can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the processor 401, the above functions defined in the system of the embodiment of the present invention are executed. According to an embodiment of the present invention, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0133] The present invention also provides a computer-readable storage medium, which can be included in the device / device / system described in the above embodiment; or can exist separately without being assembled into the device / device / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0134] According to an embodiment of the present invention, the computer-readable storage medium can be a non-volatile computer-readable storage medium. For example, it can include but is not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, device, or device.

[0135] For example, according to an embodiment of the present invention, the computer-readable storage medium can include the above-described ROM 402 and / or RAM 408 and / or one or more memories other than ROM 402 and RAM 408.

[0136] An embodiment of the present invention also includes a computer program product, which includes a computer program that contains program codes for executing the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program codes are used to enable the electronic device to implement the method provided by the embodiment of the present invention.

[0137] When the computer program is executed by the processor 401, the above functions defined in the system / device of the embodiment of the present invention are executed. According to an embodiment of the present invention, the above-described systems, devices, modules, units, etc. can be implemented by computer program modules.

[0138] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication section 409, and / or installed from the removable medium 411. The program code included in the computer program may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0139] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiments of the present invention may be written in any combination of one or more programming languages. Specifically, these computing programs may be implemented using high-level procedures and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions. Those skilled in the art can understand that the features described in the various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present invention.

[0141] The embodiments of the present invention have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present invention, those skilled in the art can make various substitutions and modifications, and these substitutions and modifications should fall within the scope of the present invention.

Claims

1. A multi-target UAV scheduling method, characterized in that: The method comprises: Obtaining the space environment characteristics corresponding to the current airspace of the UAV, wherein the space environment characteristics are divided into multiple altitude layers; According to the spatial environment characteristics, using a pre-built path search model, identify the optimal path for each UAV in each altitude layer to reach the target location from the starting position avoiding the no-fly zone, wherein the optimal path represents the minimum resource consumption required for the UAV to reach the target location from the starting position; Control each UAV to perform a flight mission according to a specified flight route in each altitude layer according to the optimal path; In response to the flight distance between any two UAVs located in the same altitude layer being less than a safety distance threshold, the flight state of one of the UAVs is switched and the flight altitude of another UAV is adjusted so that the two UAVs are located in different altitude layers for flight scheduling.

2. The method according to claim 1, characterized in that The path search model is constructed based on the A* search algorithm; Wherein, the method of identifying the optimal path for each UAV in each altitude layer to reach the target location from the starting position avoiding the no-fly zone by using a pre-built path search model according to the spatial environment characteristics includes: Extracting resource consumption parameters for the drone to reach the next node from the current arbitrary position, wherein the resource consumption parameters include a first resource consumption parameter for the drone to reach all adjacent nodes from the current arbitrary position, and a second resource consumption parameter predicted from each adjacent node to reach the target position; Selecting a node with the smallest resource consumption parameter in the next node as the starting node, and continuing to search from the starting node to the node with the smallest resource consumption parameter in the next node; In response to the node with the smallest resource consumption parameter reaching the target position in the next step, starting from the target position and tracing back to the starting position, the optimal path of the drone is obtained.

3. The method according to claim 2, characterized in that The path finding model is configured with: An open list, wherein the open list is used to store nodes to be searched in the process of searching for an optimal path by the path search model; A closed list, wherein the closed list is used to store nodes that have been searched by the path search model during the process of searching for the optimal path.

4. The method according to claim 2, characterized in that: Before controlling each UAV to perform a flight mission according to a specified flight route in each altitude layer according to the optimal path, the method further includes: Detecting whether the optimal path passes through the no-fly zone; In response to the optimal path crossing the no-fly zone, a new optimal path is re-identified.

5. The method according to claim 4, characterized in that The detecting whether the optimal path passes through the no-fly zone comprises: Establishing a feature model of the no-fly zone, wherein the feature model is configured to be constructed by a polygon defined by a set of vertices; Starting from any node in the optimal path, a ray is emitted along the X-axis direction, and the number of intersections between the ray and the polygon edge is counted; In response to the number of intersection points being an odd number, the optimal path does not pass through the no-fly zone; In response to the number of intersection points being an even number, the optimal path passes through the no-fly zone.

6. The method according to claim 1, characterized in that The method of switching the flight state of one of the UAVs and adjusting the flight altitude of another UAV so that the two UAVs are located at different altitudes for flight scheduling includes: In response to a flight distance between any two UAVs located in the same altitude layer being less than a safety distance threshold, switching the flight state of one of the UAVs to a waiting state, wherein the UAV remains stationary in the waiting state; Based on the waiting state, the flight altitude of another UAV is adjusted to a different altitude layer.

7. The method according to claim 6, characterized in that Also includes: Configure a path list, wherein the path list is used to record the path information of each drone, and each node in the path information includes the three-dimensional coordinate value of the corresponding drone at the node; In response to changes in the flight position and flight altitude of any UAV, the path list is updated in real time to record the latest position information and altitude information of the corresponding UAV.

8. A multi-target UAV dispatching device, characterized in that: The device comprises: An acquisition module is used to acquire the space environment characteristics corresponding to the current airspace of the UAV, wherein the space environment characteristics are divided into multiple altitude layers; An identification module is used to identify, according to the spatial environment characteristics, an optimal path for each UAV in each altitude layer to reach a target location from a starting position avoiding a no-fly zone using a pre-built path search model, wherein the optimal path represents the minimum resource consumption required for the UAV to reach the target location from the starting position; An execution module, used to control each UAV to perform a flight mission according to a specified flight route in each altitude layer according to the optimal path; The scheduling module is used to respond to the flight distance between any two UAVs located in the same altitude layer being less than a safety distance threshold, by switching the flight state of one of the UAVs and adjusting the flight altitude of the other UAV, so that the two UAVs are located in different altitude layers for flight scheduling.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor executes the method according to any one of claims 1 to 7.

Images