A method and apparatus for drone trajectory planning for edge data recovery

Abstract

This invention discloses a drone trajectory planning method and apparatus for edge data retrieval, relating to the navigation field, to improve the reliability of data retrieval tasks while ensuring data retrieval efficiency. The invention obtains edge node information for all target edge nodes; acquires basic drone parameters and initial state information, thereby obtaining the drone's unit energy consumption; calculates the drone's flight energy consumption between each pair of nodes, constructing an edge node geographic information model; then iterates through the following steps until all edge nodes have been visited, obtaining the drone's flight trajectory: based on the edge node geographic information model and the drone's state information, a greedy strategy is used to plan the access trajectory corresponding to the maximum number of visited nodes; the drone visits nodes sequentially along this access trajectory and updates its state information. This invention can effectively improve the reliability of data retrieval, ensuring both data retrieval efficiency and energy efficiency of the system.

Description

Technical Field

[0001] This invention relates to the field of navigation, and in particular to a method and apparatus for unmanned aerial vehicle (UAV) trajectory planning for edge data recovery. Background Technology

[0002] With the rapid development of edge computing, more and more tasks are shifting from traditional cloud computing centers to edge nodes. However, this process also generates a large amount of edge data, which often needs to be collected and processed in a timely manner to meet the needs of various application scenarios. In many real-world scenarios, network latency is a significant issue, especially in harsh environments such as remote areas, natural disaster sites, or industrial parks, where wireless network coverage is limited or even impossible to establish a reliable connection, posing a major challenge to data transmission. Therefore, how to efficiently collect data generated by edge nodes has become an urgent problem to be solved.

[0003] Considering these issues, drones, as a flexible and efficient data retrieval tool, have attracted widespread attention. Drones are highly maneuverable, enabling them to perform data collection and retrieval tasks in various complex environments. Deploying drones for data retrieval can overcome the limitations of traditional wireless network transmission, ensuring that data can be delivered to the processing center in a timely and secure manner. However, in the process of using drones to retrieve data from multiple edge nodes, how to plan a path that minimizes overall data collection time and energy consumption has become a hot research topic.

[0004] Existing drone trajectory optimization algorithms typically focus on minimizing the shortest distance or time of a path. For example, the "Path Planning Method for a Drone in Data Collection Process" proposed in Chinese Patent Document CN112902969A aims to minimize the drone's flight path to construct a global path planning problem model for the drone. These planning methods neglect the objective condition that, in real-world scenarios, battery power may not meet the energy consumption requirements of a single data collection session. This neglect may lead to insufficient power on the drone's return journey, preventing it from completing the mission or even causing it to crash, resulting in equipment damage and safety hazards. Therefore, in the trajectory planning process, the drone's battery status needs to be used as a constraint on trajectory decisions to improve the drone's availability and safety. Summary of the Invention

[0005] The purpose of this invention is to provide a drone trajectory planning method and apparatus for edge data recovery, addressing all or part of the problems mentioned above, so as to improve the reliability of data recovery tasks while ensuring data recovery efficiency.

[0006] The technical solution adopted in this invention is as follows:

[0007] A drone trajectory planning method for edge data retrieval includes the following steps:

[0008] S1. Obtain edge node information for all target edge nodes;

[0009] S2. Obtain the basic parameters and initial state information of the UAV, and obtain the operating power based on the basic parameters of the UAV;

[0010] S3. Based on the edge node information, basic parameters and working power of each edge node, calculate the flight energy consumption of the UAV between each pair of nodes, and construct the edge node geographic information model.

[0011] Iterate through steps S4 and S5 until all edge nodes have been visited:

[0012] S4. Based on the edge node geographic information model and the UAV status information, and on the premise that the UAV can return to the starting point, a greedy strategy is used to plan the access trajectory corresponding to the maximum number of access nodes.

[0013] S5. The UAV visits nodes sequentially according to the access trajectory and updates the UAV's status information according to the edge node geographic information model.

[0014] Furthermore, step S3 includes:

[0015] S3.1 Calculate the flight time of the UAV between each pair of nodes based on the edge node information and the basic parameters of the UAV.

[0016] S3.2 Calculate the flight energy consumption of the UAV between each pair of nodes based on the unit energy consumption of the UAV;

[0017] S3.3 Construct an energy consumption relationship library that expresses the energy consumption of UAV flight between any two nodes, and initialize the set of edge nodes visited by the UAV.

[0018] Furthermore, step S4 includes:

[0019] Under the constraints of the UAV's state information, based on the edge node geographic information model, the maximum number of edge nodes that the UAV can continue to visit and eventually return to the starting point from each of the current selectable edge nodes is obtained. The edge node with the maximum number of visited edge nodes among the traversed selectable edge nodes is selected as the next node, and the path with the maximum number of visited edge nodes corresponding to this node is combined with the path back to the starting point as the planned access trajectory; if there is no selectable edge node, the path back to the starting point is used as the planned access trajectory.

[0020] Furthermore, methods for determining optional edge nodes include:

[0021] Filter out unvisited edge nodes from all target edge nodes;

[0022] Traverse unvisited edge nodes. If the drone's state information supports the drone starting from the current node, reaching the currently traversed edge node, and then returning to the starting point from that edge node, then the currently traversed edge node is determined to be an optional edge node.

[0023] Furthermore, methods for obtaining the maximum number of accessed edge nodes include:

[0024] Iterate through each optional edge node, and obtain all remaining optional edge nodes that can be accessed from the currently traversed edge node and can return to the starting point as the next node. Then, iterate through each next node and update the drone's status information and the optional edge nodes when traversing that next node. Obtain all remaining optional edge nodes that can be accessed from the current edge node and can return to the starting point as the next node after that. Continue in this manner until there are no more optional edge nodes. Count the number of edge nodes in all paths traversed from the currently traversed edge node, select the maximum value, and record the corresponding node access order.

[0025] Furthermore, when traversing each selectable edge node, the remaining battery power of the drone after visiting the maximum number of edge nodes is calculated; if there is more than one selectable edge node with the maximum number of edge nodes visited, the edge node with the least remaining battery power of the drone is selected as the next node.

[0026] Furthermore, when there is more than one selectable edge node with the least remaining power for the drone, the next node is determined from these edge nodes with the least remaining power based on uniformly distributed sampling.

[0027] Furthermore, step S5 includes:

[0028] The drone visits each node in the planned access trajectory sequentially. For each subsequent node:

[0029] If the next node is the starting point, then update the drone's state information to the optimal state;

[0030] If the next node is an edge node, then based on the current node's drone status information, the flight energy consumption from the current node to the next node is deducted, and the next node is updated to the set of visited edge nodes.

[0031] The present invention also provides a drone trajectory planning device for edge data recovery, comprising a processor and a storage medium, wherein the processor runs a computer program in the storage medium to execute the above-described drone trajectory planning method for edge data recovery.

[0032] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0033] This invention considers the starting point (rechargeable point) during trajectory planning and employs a greedy algorithm for trajectory point decision-making under the constraints of UAV state information, effectively optimizing the trajectory path length and energy consumption. This method not only ensures that the UAV has sufficient battery power to return to the charging station after completing the data retrieval task, effectively avoiding battery depletion, but also ensures that each flight can access as many edge nodes as possible, balancing data retrieval efficiency and task execution reliability. Furthermore, by simultaneously deciding on trajectories for multiple access nodes, it reduces algorithm execution time and enhances the UAV's adaptability in complex environments. Attached Figure Description

[0034] The present invention will be described by way of example and with reference to the accompanying drawings, wherein:

[0035] Figure 1 This is a flowchart of a drone trajectory planning method for edge data recovery in an embodiment of this application.

[0036] Figure 2 This is a node jump tree diagram when planning the access path to the node in the embodiments of this application.

[0037] Figure 3 , Figure 4 These are comparative experimental results of the completion rate and execution time of UAV access nodes under different algorithms provided in the embodiments of the present invention, wherein the algorithm of this application is named EnerDrontic. Detailed Implementation

[0038] All features disclosed in this specification, or all steps in all disclosed methods or processes, may be combined in any way, except for mutually exclusive features and / or steps.

[0039] Any feature disclosed in this specification (including any appended claims and abstract) may be replaced by other equivalent or similar features, unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is merely one example of a series of equivalent or similar features.

[0040] Current drone trajectory planning algorithms typically focus on the shortest path or the shortest time, neglecting the potential risks caused by whether the drone's battery power can sustain the planned path. This application provides a drone trajectory planning method for edge data recovery, aiming to ensure the reliability of the data recovery task while recovering data as efficiently as possible.

[0041] like Figure 1 As shown in the embodiments of this application, the UAV trajectory planning method for edge data recovery includes the following process:

[0042] S1. Obtain edge node information for all target edge nodes.

[0043] The so-called target edge nodes are the edge nodes that the drone will visit. These edge nodes typically contain data to be retrieved. Of course, they can also be edge nodes that do not have data to be retrieved but are designated for inspection. These target edge nodes must be specified before the drone's trajectory is planned. Usually, a drone is responsible for data retrieval within a given geographic area, and all target edge nodes within that geographic area can be identified using technologies such as electronic fences.

[0044] In some embodiments, edge node information includes geographic information and status information of the edge node. The geographic information indicates the geographical location of the edge node, including its latitude, longitude, and altitude. The status information indicates the amount of data to be recovered by the edge node. The geographic information is used to calculate the flight energy consumption between nodes, and the status information can be used to evaluate the recovery efficiency of the planned path.

[0045] In some possible implementations, P0 represents the charging point and is set as the starting point for the drone's flight. For edge nodes P within a given geographical location range... i ,1≤i≤n, establish a relationship with P i Edge node information representation S i ={G i H i D i}, where i is the edge node identifier, n represents the target number of edge nodes, and G i H represents the latitude and longitude of the edge node i. i D represents the altitude of edge node i. i This represents the amount of data to be reclaimed at edge node i (this data can be ignored for access trajectory planning).

[0046] S2. Obtain the basic parameters and initial state information of the UAV, and obtain the operating power based on the basic parameters of the UAV.

[0047] The basic parameters of a drone are its configuration attributes, including its flight speed and maximum battery capacity. Flight speed allows us to calculate the drone's energy consumption per unit, while the maximum battery capacity gives us the drone's remaining power in optimal condition. The drone's initial state information includes its current remaining battery power and the set of edge nodes it has visited. The remaining battery power constrains path planning, ensuring the drone has enough power to return to the starting point, while recording the set of visited edge nodes allows us to consider only unvisited edge nodes when planning the flight path.

[0048] In some possible implementations, the parameters of the UAV substrate are expressed as U = {v, B} *}, where v represents the drone's flight speed, B * This represents the maximum battery capacity of the drone. The set of edge nodes visited by the drone is represented here as set V. The drone's current remaining battery power can be represented using B. i This indicates that the distance to edge node P is... i The remaining battery power at that time.

[0049] S3. Based on the edge node information, basic parameters and operating power of each edge node, calculate the flight energy consumption of the UAV between each pair of nodes, and construct the edge node geographic information model.

[0050] The nodes of drone flight include the starting point and edge nodes. By constructing a geographic information model of the edge nodes, we can provide decision support data for drone trajectory planning.

[0051] In some embodiments, step S3 includes the following sub-steps:

[0052] S3.1 Calculate the flight time of the UAV between each pair of nodes based on the edge node information and the basic parameters of the UAV.

[0053] Since the edge node information of each edge node can determine the position of each edge node, the optimal flight trajectory q between every two nodes i and j can be obtained by combining the position and the UAV flight dynamics. i,j ,0≤i,j≤n,i≠j,n represents the number of edge nodes; then, the flight time of the drone between each pair of nodes can be calculated from the flight speed given by the basic parameters of the drone.

[0054] S3.2 Calculate the flight energy consumption of the UAV between each pair of nodes based on the unit energy consumption of the UAV.

[0055] The flight time between each pair of nodes calculated in sub-step S3.1 can be multiplied by the operating power of the UAV to calculate the flight energy consumption of the UAV between each pair of nodes.

[0056] S3.3 Construct an energy consumption relationship library that expresses the energy consumption of UAV flight between any two nodes, and initialize the set of edge nodes visited by the UAV.

[0057] In some possible implementations, the energy consumption relation database is represented using a two-dimensional matrix. For example, a two-dimensional matrix X can be used to represent the energy consumption relation database:

[0058]

[0059] Among them, X i,j This represents the energy consumption of the drone flying from node i to node j.

[0060] Initialize set V as an empty set.

[0061] After obtaining the data calculated or constructed in the above embodiments, drone trajectory planning can be performed. By iterating through steps S4-S5 until all edge nodes have been visited, the drone flight trajectory is obtained.

[0062] S4. Based on the edge node geographic information model and the UAV status information, and on the premise that the UAV can return to the starting point, a greedy strategy is used to plan the access trajectory corresponding to the maximum number of nodes accessed in the current round.

[0063] The flight energy consumption between each pair of nodes described by the edge node geographic information model, combined with the remaining power represented by the drone's status information, can be used to analyze whether the drone can return to the starting point after visiting the edge node.

[0064] In some embodiments, step S4 includes the following process:

[0065] Under the constraints of the UAV's state information, based on the edge node geographic information model, the maximum number of edge nodes that the UAV can continue to visit and eventually return to the starting point from each of the current selectable edge nodes is obtained. The edge node with the maximum number of visited edge nodes among the traversed selectable edge nodes is selected as the next node, and the path with the maximum number of visited edge nodes corresponding to this node is combined with the path back to the starting point as the planned access trajectory; if there is no selectable edge node, the path back to the starting point is used as the planned access trajectory.

[0066] This step involves filtering the available edge nodes, calculating the maximum number of edge nodes that can be accessed for each available edge node, and filtering the final access trajectory.

[0067] In some possible implementations, methods for determining optional edge nodes include:

[0068] Filter out unvisited edge nodes from all target edge nodes;

[0069] Traverse unvisited edge nodes. If the drone's state information supports the drone starting from the current node, reaching the currently traversed edge node, and then returning to the starting point from that edge node, then the currently traversed edge node is determined to be an optional edge node.

[0070] In this implementation, it is assumed that the k-th decision is currently being executed, using P k k∈{0,1,2,...,n} represents the current node, and Q is used. k,available Indicates starting from the current point P k The set of optional edge nodes for starting.

[0071] Based on the flight energy consumption relationship matrix X of the UAVs between nodes, all UAVs from the current point P are... k The optional edge nodes that originate are placed into set Q. k,available In this context, the optional edge node indicates the amount of battery power the drone currently has that can support the power of node P. k Start by visiting the edge node and returning to the starting point P0.

[0072] As a feasible implementation, first obtain the edge nodes that the drone has not visited. After leaving each edge node, the drone adds the left-away edge node to the set V of visited edge nodes, using set Q. k,screen Let Q be the set of visited edge nodes, then: k,screen =P * -P k -V, meaning from the target edge node set P * In the middle, remove the current edge node and the set of visited edge nodes V.

[0073] Then iterate through set Q k,screen edge node P in s If the drone's remaining battery power meets B k -X k,s -X s,0 If ≥0, then the edge node P will be... s Put into set Q k,available middle.

[0074] In some possible implementations, methods for obtaining the maximum number of accessed edge nodes include:

[0075] Iterate through each optional edge node, and obtain all remaining optional edge nodes that can be accessed from the currently traversed edge node and can return to the starting point as the next node. Then, iterate through each next node and update the drone's status information and the optional edge nodes when traversing that next node. Obtain all remaining optional edge nodes that can be accessed and can return to the starting point as the next node after that. Continue in this way until there are no more optional edge nodes. Count the number of edge nodes in all paths traversed from the currently traversed edge node, select the maximum value, and record the corresponding node access order.

[0076] As a feasible implementation, the algorithm optPath for obtaining the maximum number of accessed edge nodes is executed as follows:

[0077]

[0078] When traversing each optional edge node to plan the starting node for the current node's access path, such as Figure 2 As shown, the currently traversed optional edge node is taken as the root node. Starting from this root node, the optional edge nodes at this root node are taken as first-level child nodes. These first-level child nodes can all be the next nodes starting from the currently traversed optional edge node. The flight energy consumption to reach different next nodes is different, so the drone's state information needs to be updated at each first-level child node. The update of the drone's state information will cause changes in the optional edge nodes, so after updating the drone's state information, the set of optional edge nodes at each first-level child node also needs to be updated. Similarly, each first-level child node is taken as the parent node, and its optional edge nodes are taken as its second-level child nodes. These second-level child nodes can be the next nodes starting from the first-level child node. At each second-level child node, the drone's state information and optional edge nodes also need to be updated. This process is repeated until the drone's state information no longer supports accessing optional edge nodes and only supports returning to the starting point, that is, there are no more optional edge nodes at a certain level of child node. At this point, the edge node becomes a leaf node. The maximum number of edge nodes visited by the current optional edge node (i.e., the root node) is the longest path from the currently traversed optional edge node to all leaf nodes that it can reach.

[0079] As a feasible implementation method, by traversing set Q k,available For edge nodes, a recursive approach is used to repeatedly plan the next node, update the drone's state information and available edge nodes, until the drone's state information no longer supports accessing any edge nodes, at which point the process returns to the starting point. The maximum number of edge nodes visited starting from the traversed edge nodes is calculated, and the corresponding remaining battery power of the drone after the visit is completed is saved.

[0080] Define "farthest uncharged node number" as the maximum number of edge nodes reachable from the current node without needing to recharge, given a certain amount of remaining battery power. The set Q... k,available Each edge node in the set has a maximum number of visited edge nodes, and the node with the maximum number of visited edge nodes is the furthest node without filling. When traversing set Q... k,available After each edge node, from set Q k,available Then select the edge node with the largest number of unfilled nodes as the next node.

[0081] If multiple edge nodes have the same number of furthest nodes without charging, the edge node with the least remaining battery power for the drone will be selected as the next node.

[0082] If multiple edge nodes have the same number of furthest uncharged nodes and the same remaining battery power for the drones, then the next node is determined from the edge nodes with the least remaining battery power for these drones based on uniformly distributed sampling.

[0083] If the current state information of the drone does not support visiting any unvisited edge nodes before returning to the starting point, i.e., set Q k,available If the value is empty, the starting point will be used as the next node.

[0084] As a feasible approach, the EnerDrontic algorithm for planning the access trajectory in this application embodiment is executed as follows:

[0085]

[0086] S5. The drone visits nodes sequentially according to its access trajectory and updates its status information based on the edge node geographic information model.

[0087] After step S4, each node that the drone needs to reach in sequence can be determined. After the drone reaches each node, the remaining battery power will change, and the edge nodes visited may also change, so both need to be updated.

[0088] In some embodiments, step S5 includes:

[0089] The drone visits each node in the planned access trajectory sequentially. For each subsequent node:

[0090] If the next node is the starting point P0, then update the drone's state information to the optimal state, i.e., B. k =B * The set V remains unchanged;

[0091] If the next node is an edge node P j(Assume the current node is P) i The drone has a remaining battery power of B. k-1 Then, based on the current node's drone status information (especially remaining battery power), subtract the distance from the current node to the next node P. j Flight energy consumption: B k =B k-1 -X i,j and the visited node P j Update the visited edge node set V.

[0092] This application also proposes a drone trajectory planning device for edge data recovery. The device includes a processor and a storage medium. The storage medium stores a computer program, which, when executed, performs the drone trajectory planning method for edge data recovery described in the above embodiments. The processor runs the computer program in the storage medium to execute the aforementioned drone trajectory planning method for edge data recovery.

[0093] Because real-world experiments related to UAV trajectory planning are time-consuming, this application embodiment constructs a UAV trajectory planning simulation environment and conducts comparative experiments on four methods within this simulation environment. The experimental results are then compared, as shown below. Figure 3 As shown.

[0094] This application demonstrates a comparison of the proposed algorithm with three other commonly used methods when applied to the current scenario. The three common methods are:

[0095] (1) A* method: This method evaluates the cost of each node by defining a heuristic function and selects the path with the minimum cost. According to this method, the algorithm prioritizes the path most likely to lead to the target during the search process, ensuring that the optimal trajectory is found quickly in complex environments.

[0096] (2) GGA method: In each generation, the best trajectory is selected for reproduction based on the fitness of the path. According to this method, individuals with higher path quality are more likely to be selected to pass on their genes, thereby gradually optimizing the flight trajectory of the UAV.

[0097] (3) ACO method: This method guides the selection of subsequent ants by releasing pheromones along the path. According to this method, the concentration of pheromones on higher-quality paths will increase, thereby attracting more ants to choose that path, ultimately forming the optimal flight trajectory of the drone.

[0098] See Figure 3The results show that, compared with methods A*, GGA, and ACO, the method proposed in this application can consistently maintain a 100% node access completion rate, while the other methods have very low node access completion rates when battery capacity is small. This demonstrates that the method provided in this application not only has sufficient reliability but also exhibits superior performance in data recovery efficiency.

[0099] See Figure 4 The results show that, compared with methods A*, GGA, and ACO, the method proposed in this application has the shortest execution time, while the other methods, especially GGA and ACO, are very time-consuming. This demonstrates that the method provided in this application also has superior performance in terms of execution efficiency.

[0100] This invention is not limited to the specific embodiments described above. The invention extends to any new feature or combination disclosed in this specification, as well as any new method or process step or combination disclosed herein.

Claims

1. A drone trajectory planning method for edge data retrieval, characterized in that, Includes the following steps: S1. Obtain edge node information for all target edge nodes; S2. Obtain the basic parameters and initial state information of the UAV, and obtain the operating power based on the basic parameters of the UAV; S3. Based on the edge node information, basic parameters and working power of each edge node, calculate the flight energy consumption of the UAV between each pair of nodes, and construct the edge node geographic information model. Iterate through steps S4 and S5 until all edge nodes have been visited. S4. Based on the edge node geographic information model and the UAV's state information, and ensuring that the UAV can return to the starting point, a greedy strategy is used to plan the access trajectory corresponding to the maximum number of accessed nodes. This includes: under the constraint of the UAV's state information, based on the edge node geographic information model, obtaining the maximum number of edge nodes that the UAV can continue to access from each currently available edge node and eventually return to the starting point; selecting the edge node with the maximum number of accessed edge nodes among the traversed available edge nodes as the next node; and combining the path with the maximum number of accessed edge nodes corresponding to the next node with the path returning to the starting point as the planned access trajectory; if there are no available edge nodes, then the path returning to the starting point is used as the planned access trajectory. S5. The UAV visits nodes sequentially according to the access trajectory and updates the UAV's status information according to the edge node geographic information model.

2. The UAV trajectory planning method for edge data recovery as described in claim 1, characterized in that, Step S3 includes: S3.1 Calculate the flight time of the UAV between each pair of nodes based on the edge node information and the basic parameters of the UAV. S3.2 Calculate the flight energy consumption of the UAV between each pair of nodes based on the unit energy consumption of the UAV; S3.3 Construct an energy consumption relationship library that expresses the energy consumption of UAV flight between any two nodes, and initialize the set of edge nodes visited by the UAV.

3. The UAV trajectory planning method for edge data recovery as described in claim 1, characterized in that, Methods for determining optional edge nodes include: Filter out unvisited edge nodes from all target edge nodes; Traverse unvisited edge nodes. If the drone's state information supports the drone starting from the current node, reaching the currently traversed edge node, and then returning to the starting point from the currently traversed edge node, then the currently traversed edge node is determined to be an optional edge node.

4. The UAV trajectory planning method for edge data retrieval as described in claim 3, characterized in that, Methods for obtaining the maximum number of accessed edge nodes include: Iterate through each optional edge node, and obtain all remaining optional edge nodes that can be accessed from the currently traversed edge node and can return to the starting point as the next node. Then, iterate through each next node and update the drone's status information and the optional edge nodes when traversing that next node. Obtain all remaining optional edge nodes that can be accessed from the current edge node and can return to the starting point as the next node after that. Continue in this manner until there are no more optional edge nodes. Count the number of edge nodes in all paths traversed from the currently traversed edge node, select the maximum value, and record the corresponding node access order.

5. The UAV trajectory planning method for edge data recovery as described in claim 4, characterized in that, When traversing each optional edge node, the remaining battery power of the drone after visiting the maximum number of edge nodes is also calculated. If there is more than one optional edge node with the maximum number of edge nodes visited, the edge node with the least remaining battery power of the drone is selected as the next node.

6. The UAV trajectory planning method for edge data recovery as described in claim 5, characterized in that, When there is more than one selectable edge node with the least remaining power for the drone, the next node is determined from these edge nodes with the least remaining power based on uniformly distributed sampling.

7. The UAV trajectory planning method for edge data recovery as described in claim 2, characterized in that, Step S5 includes: The drone visits each node in the planned access trajectory sequentially. For each subsequent node: If the next node is the starting point, then update the drone's state information to the optimal state; If the next node is an edge node, then based on the current node's drone status information, the flight energy consumption from the current node to the next node is deducted, and the next node is updated to the set of visited edge nodes.

8. A drone trajectory planning device for edge data retrieval, comprising a processor and a storage medium, characterized in that, The processor runs a computer program in the storage medium to perform the UAV trajectory planning method for edge data recovery as described in any one of claims 1-7.

Images