An unmanned aerial vehicle path planning and segment speed joint optimization method and system

Abstract

Embodiments of the present application provide a method and system for unmanned aerial vehicle path planning and joint optimization of flight segment speed, the method comprising: obtaining a logistics task and a space environment of an unmanned aerial vehicle; wherein the logistics task contains one take-off and landing point and multiple sets of pick-up and delivery node pairs; generating a task node distance matrix based on the space environment and the multiple sets of pick-up and delivery node pairs; generating a communication interruption probability graph based on an unmanned aerial vehicle flight area of the space environment; performing path planning based on the task node distance matrix and the communication interruption probability graph to obtain an initial feasible path; performing path search on the initial feasible path to determine a candidate path set; and performing speed optimization based on the candidate path set to determine an optimal path. The above scheme can improve the feasibility and flight efficiency of the logistics unmanned aerial vehicle task execution, and reduce the risk of disconnection.

Description

Technical Field

[0001] This application relates to the field of UAV logistics scheduling and path planning technology, specifically to a method and system for joint optimization of UAV path planning and segment speed. Background Technology

[0002] With the rapid development of urban instant delivery and low-altitude logistics, drones are widely used in multi-order pickup and delivery scenarios due to their high mobility and flexible deployment, which puts forward higher requirements for drone path planning and task scheduling.

[0003] However, logistics drones are limited by battery capacity and payload capacity, and their flight energy consumption is strongly coupled with flight distance, flight speed, and payload status. Existing studies often simplify battery constraints to maximum range or maximum flight time, or perform path optimization under fixed speed conditions, making it difficult to achieve synergistic optimization between path selection, speed allocation, and energy consumption constraints. This can easily lead to energy consumption exceeding limits or mission infeasibility under complex task conditions.

[0004] On the other hand, multi-order pickup and delivery tasks usually have strict constraints on the order of picking up and delivering points (Pickup and Delivery Problem, PDP), which significantly increases the difficulty of feasibility determination and combinatorial complexity of path planning problems. Traditional path search algorithms are prone to getting trapped in local optima or generating infeasible solutions under such constraints.

[0005] In addition, in urban low-altitude operating environments, the execution of drone missions usually relies on wireless communication links between ground base stations, control centers, or relay nodes to achieve mission scheduling, status feedback, and safety monitoring.

[0006] However, existing path planning and speed optimization methods generally ignore communication constraints such as discontinuous communication coverage and link quality variations with location and speed. This can lead to communication interruptions, communication quality degradation, or loss of connection during actual execution of the planned path, further affecting mission security and execution reliability. Summary of the Invention

[0007] This application aims to provide a method and system for joint optimization of UAV path planning and segment speed, which can improve the feasibility and flight efficiency of logistics UAV missions and reduce the risk of losing contact.

[0008] The technical solution of this application is implemented as follows: In a first aspect, embodiments of this application provide a method for joint optimization of UAV path planning and segment speed, the method comprising: Acquire the logistics task and spatial environment of the drone; wherein, the logistics task includes a take-off and landing point and multiple sets of pick-up and delivery node pairs; Based on the spatial environment and the multiple sets of pickup and delivery node pairs, a task node distance matrix is ​​generated; Based on the UAV flight area of ​​the aforementioned space environment, a communication interruption probability map is generated; Based on the task node distance matrix and the communication interruption probability map, path planning is performed to obtain an initial feasible path; and a path search is performed on the initial feasible path to determine a set of candidate paths. Based on the candidate path set, speed optimization is performed to determine the optimal path.

[0009] In the above scheme, generating the task node distance matrix based on the spatial environment and the multiple sets of pickup and delivery node pairs includes: Based on the aforementioned space environment, a flight map is established; wherein, the flight map includes a set of spatial nodes in the flight environment and a set of flight segments of the UAV. Based on the multiple sets of fetch and send node pairs, multiple task nodes are determined; For each pair of task nodes among the plurality of task nodes, a shortest path search is performed on the flight map to determine the minimum cumulative flight cost between the pair of task nodes. The distance matrix between the task nodes is determined based on the minimum cumulative flight cost between each pair of task nodes.

[0010] In the above scheme, generating a communication interruption probability map based on the UAV flight area of ​​the space environment includes: Based on the UAV flight area of ​​the aforementioned spatial environment, multiple base stations corresponding to the UAV are determined. Based on the terrain and building information of the spatial environment, path loss images corresponding to each of the multiple base stations are generated; Spatial alignment and consistency verification are performed on the path loss images corresponding to the multiple base stations to determine the three-dimensional received power stack. Based on each received power in the three-dimensional received power stack, the maximum instantaneous signal-to-interference-plus-noise ratio corresponding to each of the plurality of base stations is determined; The communication interruption probability is determined by using a communication reliability threshold and the maximum instantaneous signal-to-interference-plus-noise ratio corresponding to each of the multiple base stations; and the communication interruption probability map is generated based on the communication interruption probability.

[0011] In the above scheme, the step of performing path planning based on the task node distance matrix and the communication interruption probability map to obtain an initial feasible path includes: Based on the task node distance matrix and the communication interruption probability map, multiple random paths are generated. Based on the aforementioned order of pickup and delivery constraints, a path search is performed on the multiple random paths to determine infeasible random paths; From the plurality of random paths, the infeasible random paths are removed to obtain the initial feasible paths.

[0012] In the above scheme, the step of performing path search on the initial feasible path to determine the candidate path set includes: The initial feasible path is transformed by the candidate generation operator to generate a new path; By using the order of pickup and delivery constraints and the maximum load constraint, a path search is performed on the initial feasible path and the new path to determine the infeasible path and the feasible path. The infeasible paths are rearranged and flight segments are modified to determine the updated paths; The updated paths and feasible paths are filtered by using communication reliability constraints and battery power consumption constraints to determine the candidate path set.

[0013] In the above scheme, the candidate generation operator may include a neighborhood transformation operator and / or a population evolution operator; the neighborhood transformation operator includes an inversion operator, a swap operator, and an insertion operator; The step of transforming the initial feasible path using a candidate generation operator to generate a new path includes: The new path is generated by performing inversion, exchange, and insertion operations on the initial feasible path using the inversion operator, the exchange operator, and the insertion operator; and / or, The population evolution operator is used to select, cross over, mutate, and recombine the initial feasible paths to generate the new paths.

[0014] In the above scheme, the step of optimizing speed and determining the optimal path based on the candidate path set includes: Obtain the actual load corresponding to each candidate path in the candidate path set; wherein the actual load is greater than 0 and less than or equal to the maximum load; For each candidate path in the candidate path set, the optimal flight time for each candidate path is determined by optimizing the speed of each segment within each candidate path. Based on the actual payload corresponding to each candidate path and the optimal flight time of each candidate path, the candidate paths are speed optimized to determine the optimal path.

[0015] Secondly, embodiments of this application provide a joint optimization system for UAV path planning and segment speed, the joint optimization system for UAV path planning and segment speed comprising: an acquisition module, a generation module, and a determination module, wherein, The acquisition module is used to acquire the logistics task and spatial environment of the UAV; wherein, the logistics task includes a take-off and landing point and multiple sets of pick-up and delivery node pairs; The generation module is used to generate a task node distance matrix based on the spatial environment and the multiple sets of pickup and delivery node pairs; and to generate a communication interruption probability map based on the UAV flight area of ​​the spatial environment. The determining module is used to perform path planning based on the task node distance matrix and the communication interruption probability map to obtain an initial feasible path; and to perform path search on the initial feasible path to determine a candidate path set; and to perform speed optimization based on the candidate path set to determine the optimal path.

[0016] Thirdly, embodiments of this application provide a device for joint optimization of UAV path planning and segment speed, comprising: a processor and a memory; wherein, The memory is used to store computer programs; The processor is configured to call and run the computer program from the memory to perform the method as described in the first aspect.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing executable instructions for causing a processor to perform the method described in the first aspect.

[0018] This application provides a method and system for joint optimization of UAV path planning and segment speed. The method includes: acquiring the UAV's logistics task and spatial environment; wherein the logistics task includes a take-off and landing point and multiple sets of pickup and delivery node pairs; generating a task node distance matrix based on the spatial environment and the multiple sets of pickup and delivery node pairs; generating a communication interruption probability map based on the UAV's flight area in the spatial environment; performing path planning based on the task node distance matrix and the communication interruption probability map to obtain an initial feasible path; performing path search on the initial feasible path to determine a candidate path set; and performing speed optimization based on the candidate path set to determine the optimal path. In the above scheme, acquiring the UAV's logistics task and spatial environment, generating a task node distance matrix based on the spatial environment and multiple sets of pickup and delivery node pairs, generating a communication interruption probability map based on the UAV's flight area in the spatial environment, and jointly optimizing the flight path and segment speed of the UAV when performing multiple order pickup and delivery tasks, can achieve coordinated optimization of path and flight speed, improve the feasibility and flight efficiency of logistics UAV tasks, and reduce the risk of loss of communication. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application. Obviously, the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0020] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0021] Figure 1 This is an optional flowchart illustrating a method for joint optimization of UAV path planning and segment speed provided in an embodiment of this application. Figure 2 An optional flowchart illustrating another method for joint optimization of UAV path planning and segment speed provided in an embodiment of this application; Figure 3 A schematic diagram of the structure of a UAV path planning and segment speed joint optimization system provided in this application embodiment; Figure 4 This is a schematic diagram of the structure of a device for joint optimization of UAV path planning and segment speed provided in an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0023] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this application is for the purpose of describing embodiments of this application only and is not intended to be limiting of this application.

[0024] In the following description, references to "some embodiments," "this embodiment," "this application embodiment," and examples, etc., describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subset of all possible embodiments and may be combined with each other without conflict.

[0025] If the application documents contain similar descriptions such as "first / second", the following explanation shall be added: In the following description, the terms "first / second / third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0026] This application provides a method for joint optimization of UAV path planning and segment speed. Figure 1 This is an optional flowchart illustrating a method for joint optimization of UAV path planning and segment speed provided in an embodiment of this application, which will combine... Figure 1 The steps shown are explained.

[0027] S101. Obtain the logistics mission and spatial environment of the UAV; wherein, the logistics mission includes a take-off and landing point and multiple sets of pick-up and delivery node pairs.

[0028] In some embodiments of this application, the logistics task includes a take-off and landing point and multiple sets of pick-up and delivery node pairs.

[0029] In some embodiments of this application, a method for joint optimization of UAV path planning and segment speed is adapted to UAV logistics transportation scenarios.

[0030] In some embodiments of this application, a method for joint optimization of UAV path planning and segment speed is adapted to a system for joint optimization of UAV path planning and segment speed.

[0031] In some embodiments of this application, the logistics tasks and spatial environment of the UAV are obtained; wherein, the spatial environment includes the UAV flight area, terrain information and building information.

[0032] For example, suppose a logistics task performed by a drone includes a take-off and landing point and several sets of pick-up and delivery nodes. Define the node set as: Node 0 represents the takeoff and return positions of the drone; Indicates the set of pickup points; This represents a set of delivery points.

[0033] Each pickup node p i With the only delivery node d i A set of pick-up and send-down pairs is formed, and the set of pick-up and send-down pairs is defined as follows: During mission execution, drones must meet the following pick-up and delivery sequence constraints: This means that any delivery node can only be accessed after the corresponding pickup node has been accessed.

[0034] It should be noted that multiple sets of fetch and send node pairs are called fetch and send pairing sets.

[0035] To characterize the dynamic changes in payload during the delivery and retrieval missions of the UAV, a nodal load variation function is introduced: in, This represents the weight of the goods at the i-th vertex.

[0036] When the drone visits the node sequence along the path At that time, the actual load of the j-th segment was: It must also meet the maximum payload constraints of the drone: in, This indicates the maximum payload constraint for the drone.

[0037] S102. Based on the spatial environment and multiple sets of pick-up and delivery node pairs, generate a task node distance matrix.

[0038] In some embodiments of this application, a flight map is established based on the space environment; wherein, the flight map includes a set of spatial nodes in the flight environment and a set of flight segments flown by the UAV; multiple task nodes are determined based on multiple sets of pick-up and drop-off node pairs; for each pair of task nodes, a shortest path search is performed on the flight map to determine the minimum cumulative flight cost between each pair of task nodes; and a task node distance matrix is ​​determined based on the minimum cumulative flight cost between each pair of task nodes.

[0039] S103. Based on the UAV flight area in the space environment, generate a communication interruption probability map.

[0040] In some embodiments of this application, multiple base stations corresponding to the UAV are determined based on the UAV flight area of ​​the spatial environment; path loss images corresponding to each of the multiple base stations are generated based on the terrain information and building information of the spatial environment; spatial alignment and consistency verification are performed on the path loss images corresponding to each of the multiple base stations to determine the three-dimensional received power stack; based on each received power in the three-dimensional received power stack, the maximum instantaneous signal-to-interference-plus-noise ratio (SIR) corresponding to each of the multiple base stations is determined; the communication interruption probability is determined by the communication reliability threshold and the maximum instantaneous SIR corresponding to each of the multiple base stations; and a communication interruption probability map is generated based on the communication interruption probability.

[0041] S104. Based on the task node distance matrix and communication interruption probability map, perform path planning to obtain an initial feasible path; and perform path search on the initial feasible path to determine the candidate path set.

[0042] In some embodiments of this application, multiple random paths are generated based on the task node distance matrix and the communication interruption probability map. Based on the pick-up / delivery order constraint, a path search is performed on these multiple random paths to determine infeasible random paths. From these multiple random paths, infeasible random paths are removed to obtain initial feasible paths. The initial feasible paths are transformed using a candidate generation operator to generate new paths. A path search is performed on the initial feasible paths and new paths using the pick-up / delivery order constraint and load constraint to determine infeasible and feasible paths. Infeasible paths are rearranged and their segments modified to determine updated paths. Finally, the updated paths and feasible paths are filtered using communication reliability constraints and energy consumption constraints to determine a candidate path set.

[0043] For example, multiple random paths are generated based on heuristic strategies, including but not limited to: path generation prioritizing pickup points, random path generation and repair, and generating multiple random paths based on a greedy strategy. Multiple random paths may not satisfy the pickup / delivery order; infeasible random paths are removed to obtain initial feasible paths. The initial feasible paths are transformed using candidate generation operators to generate new paths. A path search is performed between the initial feasible paths and the new paths to determine infeasible and feasible paths. Infeasible paths are rearranged and their segments modified to determine updated paths. Finally, communication reliability constraints and energy consumption constraints are used to filter the updated and feasible paths to determine a candidate path set.

[0044] S105. Based on the candidate path set, optimize the speed and determine the optimal path.

[0045] In some embodiments of this application, the actual payload corresponding to each candidate path in the candidate path set is obtained; wherein the actual payload is greater than 0 and less than or equal to the maximum payload; for each candidate path in the candidate path set, the optimal flight time of each candidate path is determined by speed optimization of each segment in each candidate path; based on the actual payload corresponding to each candidate path and the optimal flight time of each candidate path, the speed of the candidate path is optimized to determine the optimal path.

[0046] It is understood that the embodiments of this application obtain the logistics task and spatial environment of the UAV, generate a task node distance matrix based on the spatial environment and multiple sets of pickup and delivery node pairs, generate a communication interruption probability map based on the UAV flight area of ​​the spatial environment, and jointly optimize the flight path and segment speed of the UAV when performing multiple order pickup and delivery tasks to achieve coordinated optimization of path and flight speed, which can improve the feasibility and flight efficiency of logistics UAV task execution and reduce the risk of loss of connection.

[0047] In some embodiments of this application, S102 can be implemented by S201-S204, as follows: S201. Based on the space environment, establish a flight map; wherein, the flight map includes a set of spatial nodes in the flight environment and a set of flight segments of the UAV.

[0048] S202. Based on multiple sets of fetch and send node pairs, determine multiple task nodes.

[0049] S203. For each pair of task nodes among multiple task nodes, perform a shortest path search on the flight map to determine the minimum cumulative flight cost between each pair of task nodes.

[0050] S204. Determine the distance matrix between task nodes based on the minimum cumulative flight cost between each pair of task nodes.

[0051] For example, a flight map can be constructed based on the space environment or airway network in which the drone can fly: in, It represents a set of spatial nodes in the flight environment, which can be waypoints, road network nodes, or grid center points; This represents the set of flight segments where drones are permitted to fly.

[0052] For any flight segment Its basic flight cost is defined as: The basic flight cost can represent the geometric distance of a flight segment, the equivalent flight length, or the flight cost after proportional conversion.

[0053] After completing the task node mapping, for any two task nodes In flight map Perform a shortest path search on the top, and calculate from arrive Minimum cumulative flight cost: in, Indicates from arrive A feasible flight path is found. The above shortest path search can be performed using Dijkstra's algorithm, A* algorithm, or other equivalent shortest path search methods.

[0054] By repeating the above calculation for all task nodes (i, j), the complete task node distance matrix is ​​generated as follows: In some embodiments of this application, S103 can be implemented by S301-S305, as follows: S301. Based on the space environment, determine the flight area of ​​the UAV and identify multiple base stations corresponding to the UAV.

[0055] S302. Based on the terrain and building information of the spatial environment, generate path loss images corresponding to each of the multiple base stations.

[0056] S303. Perform spatial alignment and consistency verification on the path loss images corresponding to multiple base stations to determine the three-dimensional received power stack.

[0057] S304. Based on each received power in the three-dimensional received power stack, determine the maximum instantaneous signal-to-interference-plus-noise ratio corresponding to each of the multiple base stations.

[0058] S305. Determine the communication interruption probability by using the communication reliability threshold and the maximum instantaneous signal-to-interference-plus-noise ratio corresponding to each of the multiple base stations; and generate a communication interruption probability map based on the communication interruption probability.

[0059] For example, the communication interruption probability map is used to characterize the probabilistic characteristics of the UAV establishing a reliable communication link with the ground communication system at different spatial locations, and serves as an important constraint input for the subsequent path planning and optimization module.

[0060] For the wireless propagation environment within the planning area, a wireless propagation simulation tool is used to model the terrestrial communication system, taking into account factors such as terrain, buildings, and electromagnetic propagation characteristics, to generate path loss (PL) raster images corresponding to different base stations.

[0061] For the k-th communication base station, its path loss graph is defined as: The path loss map is in the form of a discrete grid, covering all spatial locations within the planning area.

[0062] At a given base station transmit power Under these conditions, the path loss map is transformed into a received power map: in, This represents the average received power at spatial location (x, y) received by the k-th base station; if a location is unreachable or has an invalid simulation result, it is marked as an invalid value (NODATA).

[0063] Through the above transformation, a set of received power raster maps corresponding to multiple base stations can be obtained.

[0064] Suppose there are K communication base stations within the planned area, corresponding to K received power raster maps. Perform spatial alignment and consistency checks on all raster maps to ensure they remain consistent in raster resolution, spatial range, and coordinate reference.

[0065] After alignment, a three-dimensional received power stack is formed: This power stack serves as the basis for subsequent calculations of the probability of communication interruption.

[0066] To facilitate probabilistic modeling, the received power is converted from the logarithmic domain (dBm) to linear power (mW): Let the noise power be N0 (dBm), and the corresponding linear power be: To characterize the uncertainty of fast fading in a wireless channel, we assume that small-scale fading follows a Rayleigh distribution, and its power gain follows an exponential distribution: Then, under the m-th random channel implementation, the instantaneous received power of the k-th base station at location (x, y) is: Considering co-channel interference from multiple base stations, if a UAV connects to the kth base station at location (x,y), its instantaneous signal-to-interference-plus-noise ratio (SIR) is defined as: Considering the dynamic selection of the optimal communication link by the UAV, the maximum instantaneous signal-to-interference-plus-noise ratio is defined as: Set communication reliability threshold (Linear domain) When the maximum instantaneous signal-to-interference-plus-noise ratio (SIR) falls below this threshold, a communication interruption event is determined to have occurred. The probability of communication interruption is defined as: Monte Carlo simulation is used to numerically estimate the probability of communication interruption by repeatedly generating random channels. Let M be the number of simulations; then the estimated probability of communication interruption is: in, This is an indicator function.

[0067] Through the above process, a communication interruption probability map can be generated across the entire planning area: In some embodiments of this application, the path search for the initial feasible path and the determination of the candidate path set in S104 can be implemented through S401-S305, as follows: S401. Transform the initial feasible path using the candidate generation operator to generate a new path.

[0068] In some embodiments of this application, the candidate generation operator may include a neighborhood transformation operator and / or a population evolution operator; the neighborhood transformation operator includes an inversion operator, a swap operator, and an insertion operator.

[0069] In some embodiments of this application, new paths are generated by reversing, exchanging, and inserting operations on the initial feasible paths through inversion operators, exchange operators, and insertion operators; and / or, new paths are generated by selecting, crossing, mutating, and recombining the initial feasible paths through population evolution operators.

[0070] S402. By using the order of pickup and delivery constraints and the maximum load constraint, perform path search on the initial feasible path and the new path to determine the infeasible path and the feasible path.

[0071] S403. Rearrange the routes and modify the segments for infeasible routes to determine the updated routes.

[0072] S404. Based on communication reliability constraints and battery power consumption constraints, the updated paths and feasible paths are filtered to determine the candidate path set.

[0073] For example, let the path for the drone to access the task node be represented as a sequence of nodes: The corresponding segment velocity vector is: Wherein, the k-th velocity variable corresponds to node v k to v k+1 The flight segment.

[0074] Based on application requirements, establish optimization goals: Minimum flight time target: Minimum energy consumption target: in, Let wk be the segment length determined by the distance matrix, and wk be the payload for the corresponding segment. Meanwhile, the optimization objective includes, but is not limited to, any trade-off between flight time and energy consumption.

[0075] Joint optimization must satisfy the following constraints in addition to the aforementioned extracted delivery order constraints and maximum load constraints: Speed ​​constraints: Battery energy consumption constraints: Communication reliability constraints (explicit or implicit): Where Φ(·) represents the communication interruption risk measurement function on the path.

[0076] During path optimization, the current path or path set is transformed using candidate generation operators to generate a candidate path set. In each iteration, the current solution or elite solution set is updated based on evaluation metrics. The candidate generation operators may include neighborhood transformation operators and / or population evolution operators, wherein neighborhood operators include, but are not limited to: Reversal operator: Reverses the order of nodes in a subsequence of a path.

[0077] Swap operator: Swaps the positions of any two nodes in the path.

[0078] Insertion operator: Selects a node in the path and inserts it between other nodes.

[0079] When using population evolution operators, a path set (population) consisting of multiple feasible paths is maintained, and new candidate paths are generated through selection, crossover, mutation and / or recombination operators. Among them, crossover and mutation can rearrange the access order while satisfying the pick-and-go pairing constraints, or restore feasibility by repairing infeasible paths when they are generated. Furthermore, local improvement operators (such as the neighborhood operators mentioned above) can be applied to individuals in the population to form hybrid genetic or meme algorithms.

[0080] During the path search process, a path pool / elite solution set can be maintained to store multiple candidate paths generated in the current iteration stage. The path pool is filtered according to the evaluation function to retain paths with greater potential. When the path pool reaches its capacity limit, some paths are removed based on the evaluation value, crowding degree, or diversity index to maintain search diversity.

[0081] To avoid the search getting stuck in local optima, a search control strategy can be optionally introduced. The search control strategy includes, but is not limited to: a memory structure (e.g., a tabu list), an acceptance criterion (e.g., a pardon criterion or a probability acceptance criterion), an elite retention strategy, and a dynamic neighborhood switching or restart strategy. Among these strategies, when a candidate path is better than the current optimal path in terms of evaluation metrics, the current optimal path or the elite solution set can be updated according to the acceptance criterion.

[0082] For each candidate path If communication interruption occurs in any segment of the route... If the path is deemed infeasible, it will be classified as infeasible. For infeasible paths, the following remediation strategy will be adopted: 1. Route rearrangement: For flight segments that cannot meet communication requirements, try to make the route feasible for communication by swapping the order of path nodes or adjusting the order of flight segments.

[0083] 2. Avoid infeasible areas: Divert certain segments of the route to avoid crossing areas with a high probability of communication disruption, and search for other more reliable alternative routes.

[0084] During the path repair process, battery power consumption constraints also need to be considered. If the power consumption of a certain path... Exceeding the battery's maximum energy If the path is deemed infeasible, then the path is also deemed infeasible. In this case, the energy consumption of the path can be reduced by appropriately decreasing the segment speed v(k) or by replacing the high-energy-consumption segments in the infeasible path with shorter or more energy-efficient paths, until the path energy consumption meets the constraints.

[0085] The path search and repair mechanism will ensure that the path meets various constraints such as pick-up and delivery constraints, communication reliability constraints, and energy consumption constraints in each iteration, until the optimal solution is found or the maximum number of iterations is reached.

[0086] In some embodiments of this application, S105 can be implemented by S501-S503, as follows: S501. Obtain the actual load corresponding to each candidate path in the candidate path set; wherein the actual load is greater than 0 and less than or equal to the maximum load.

[0087] S502. For each candidate path in the candidate path set, the optimal flight time for each candidate path is determined by optimizing the speed of each segment of each candidate path.

[0088] S503. Based on the actual payload corresponding to each candidate path and the optimal flight time of each candidate path, optimize the speed of the candidate paths and determine the optimal path.

[0089] For example, to improve search efficiency, the evaluation of path candidate solutions will be performed through a surrogate evaluation function, which takes into account the following factors: 1. Total path length or time; 2. Battery energy consumption and speed distribution; 3. Violations of task constraints and communication constraints; 4. Other user-defined optimization goals.

[0090] The speed allocation for each segment of the path is optimized using the Lagrange relaxation method. Assuming the objective is to minimize flight time or energy consumption, Lagrange multipliers are introduced. To ensure that energy consumption constraints are met: With the path π fixed, the problem degenerates into: In fixed Under these conditions, the speed of each flight segment can be solved independently: By adjusting λ through a one-dimensional search, the energy consumption constraint is brought to the feasible boundary.

[0091] During the outer path search process, the optimal flight time after velocity optimization for a given path in the inner layer is used. As a path evaluation indicator.

[0092] By analyzing the path Perform local transformation operations to generate a set of candidate paths, and repair paths that do not meet the pick-up and send-out constraints to form new feasible paths.

[0093] Path updates follow: in, Represents the set of path neighborhoods.

[0094] Based on the actual payload and optimal flight time of each candidate path, the candidate paths are speed optimized, and the candidate path that satisfies at least one of the following conditions is selected as the optimal path: shortest optimal flight time and least actual payload.

[0095] Figure 2 An optional flowchart illustrating another method for joint optimization of UAV path planning and segment speed provided in this application embodiment is shown below. Figure 2As shown, the UAV path planning and segment speed joint optimization method includes task and environment inputs, distance matrix generation and interruption probability map generation to obtain task node distance matrix and communication interruption probability map; based on task node distance matrix and communication interruption probability map, feasible solution generation and metaheuristic search are performed to determine whether the obtained solution is feasible. If the solution is feasible, speed optimization is performed, and the optimized solution is checked to see if it meets energy consumption constraints. If it does, the optimal path is output; if the solution is infeasible, feasibility repair is performed, and the steps of feasible solution generation and metaheuristic search are continued.

[0096] Based on the above embodiments, this application also provides a joint optimization system for UAV path planning and segment speed, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of a UAV path planning and segment speed joint optimization system provided in an embodiment of this application. The UAV path planning and segment speed joint optimization system 3 includes: an acquisition module 301, a generation module 302, and a determination module 303, wherein... The acquisition module 301 is used to acquire the logistics task and spatial environment of the UAV; wherein, the logistics task includes a take-off and landing point and multiple sets of pick-up and delivery node pairs; The generation module 302 is used to generate a task node distance matrix based on the spatial environment and the multiple sets of pickup and delivery node pairs; The determining module 303 is used to determine a radio environment model based on the UAV flight area of ​​the space environment. The generation module 302 is also used to generate a communication interruption probability map based on the radio environment model; The determining module 303 is further configured to perform path planning based on the task node distance matrix and the communication interruption probability map to obtain an initial feasible path; and to perform path search on the initial feasible path to determine a candidate path set; and to perform speed optimization based on the candidate path set to determine the optimal path.

[0097] Based on the above embodiments, this application also provides a device for joint optimization of UAV path planning and segment speed. Figure 4 As shown, Figure 4 This is a schematic diagram of the structure of a UAV path planning and segment speed joint optimization device provided in an embodiment of this application. The UAV path planning and segment speed joint optimization device 4 includes a processor 401 and a memory 402. The memory 402 is used to store computer programs; the processor 401 is used to call and run the computer programs from the memory to execute a UAV path planning and segment speed joint optimization method as described in the above embodiment.

[0098] In the embodiments of this application, the processor 401 described above can be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field-Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that for different devices, the electronic device used to implement the above processor function can also be other types, and the embodiments of this application do not specifically limit it.

[0099] This application provides a computer-readable storage medium storing a computer program for implementing, when executed by a processor, a method for joint optimization of UAV path planning and segment speed as described in any of the above embodiments.

[0100] For example, the program instructions corresponding to the UAV path planning and segment speed joint optimization method in this embodiment can be stored on storage media such as optical discs, hard disks, and USB flash drives. When the program instructions corresponding to the UAV path planning and segment speed joint optimization method in the storage medium are read or executed by an electronic device, the UAV path planning and segment speed joint optimization method as described in any of the above embodiments can be implemented.

[0101] Furthermore, in the embodiments of this application, the functional modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional module.

[0102] If the integrated unit is implemented as a software functional module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the method of this embodiment. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0103] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the embodiments in this application are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, these will not be repeated here.

[0104] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0105] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.

[0106] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0107] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0108] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0109] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0110] The above description is merely an embodiment of this application, but the protection scope of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for joint optimization of UAV path planning and segment speed, characterized in that, The method includes: Acquire the logistics task and spatial environment of the drone; wherein, the logistics task includes a take-off and landing point and multiple sets of pick-up and delivery node pairs; Based on the spatial environment and the multiple sets of pickup and delivery node pairs, a task node distance matrix is ​​generated; Based on the UAV flight area of ​​the aforementioned space environment, a communication interruption probability map is generated; Based on the task node distance matrix and the communication interruption probability map, path planning is performed to obtain an initial feasible path; and a path search is performed on the initial feasible path to determine a set of candidate paths. Based on the candidate path set, speed optimization is performed to determine the optimal path.

2. The method according to claim 1, characterized in that, The step of generating a task node distance matrix based on the spatial environment and the multiple sets of pickup and delivery node pairs includes: Based on the aforementioned space environment, a flight map is established; wherein, the flight map includes a set of spatial nodes in the flight environment and a set of flight segments of the UAV. Based on the multiple sets of fetch and send node pairs, multiple task nodes are determined; For each pair of task nodes among the plurality of task nodes, a shortest path search is performed on the flight map to determine the minimum cumulative flight cost between the pair of task nodes. The distance matrix between the task nodes is determined based on the minimum cumulative flight cost between each pair of task nodes.

3. The method according to claim 1, characterized in that, The UAV flight area based on the aforementioned spatial environment generates a communication interruption probability map, including: Based on the UAV flight area of ​​the aforementioned spatial environment, multiple base stations corresponding to the UAV are determined. Based on the terrain and building information of the spatial environment, path loss images corresponding to each of the multiple base stations are generated; Spatial alignment and consistency verification are performed on the path loss images corresponding to the multiple base stations to determine the three-dimensional received power stack. Based on each received power in the three-dimensional received power stack, the maximum instantaneous signal-to-interference-plus-noise ratio corresponding to each of the plurality of base stations is determined; The communication interruption probability is determined by using a communication reliability threshold and the maximum instantaneous signal-to-interference-plus-noise ratio corresponding to each of the multiple base stations; and the communication interruption probability map is generated based on the communication interruption probability.

4. The method according to claim 1, characterized in that, The step of performing path planning based on the task node distance matrix and the communication interruption probability map to obtain an initial feasible path includes: Based on the task node distance matrix and the communication interruption probability map, multiple random paths are generated. Based on the aforementioned order of pickup and delivery constraints, a path search is performed on the multiple random paths to determine infeasible random paths; From the plurality of random paths, the infeasible random paths are removed to obtain the initial feasible paths.

5. The method according to claim 1, characterized in that, The step of performing path search on the initial feasible path to determine the candidate path set includes: The initial feasible path is transformed by the candidate generation operator to generate a new path; By using the order of pickup and delivery constraints and the maximum load constraint, a path search is performed on the initial feasible path and the new path to determine the infeasible path and the feasible path. The infeasible paths are rearranged and flight segments are modified to determine the updated paths; The updated paths and feasible paths are filtered by using communication reliability constraints and battery power consumption constraints to determine the candidate path set.

6. The method according to claim 5, characterized in that, The candidate generation operator may include a neighborhood transformation operator and / or a population evolution operator; the neighborhood transformation operator includes an inversion operator, a swap operator, and an insertion operator; The step of transforming the initial feasible path using a candidate generation operator to generate a new path includes: The initial feasible path is reversed, swapped, and inserted using the inversion operator, the exchange operator, and the insertion operator to generate the new path. And / or, The population evolution operator is used to select, cross over, mutate, and recombine the initial feasible paths to generate the new paths.

7. The method according to claim 1, characterized in that, The step of optimizing speed based on the candidate path set to determine the optimal path includes: Obtain the actual load corresponding to each candidate path in the candidate path set; wherein the actual load is greater than 0 and less than or equal to the maximum load; For each candidate path in the candidate path set, the optimal flight time for each candidate path is determined by optimizing the speed of each segment within each candidate path. Based on the actual payload corresponding to each candidate path and the optimal flight time of each candidate path, the candidate paths are speed optimized to determine the optimal path.

8. A joint optimization system for UAV path planning and segment speed, characterized in that, The UAV path planning and segment speed joint optimization system includes: an acquisition module, a generation module, and a determination module, wherein... The acquisition module is used to acquire the logistics task and spatial environment of the UAV; wherein, the logistics task includes a take-off and landing point and multiple sets of pick-up and delivery node pairs; The generation module is used to generate a task node distance matrix based on the spatial environment and the multiple sets of pickup and delivery node pairs; and to generate a communication interruption probability map based on the UAV flight area of ​​the spatial environment. The determining module is used to perform path planning based on the task node distance matrix and the communication interruption probability map to obtain an initial feasible path; and to perform path search on the initial feasible path to determine a candidate path set; and to perform speed optimization based on the candidate path set to determine the optimal path.

9. A device for joint optimization of UAV path planning and segment speed, characterized in that, include: Processor and memory, of which, The memory is used to store computer programs; The processor is configured to call and run the computer program from the memory to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores executable instructions for causing a processor to execute, thereby implementing the method of any one of claims 1 to 7.

Images