Logistics management method based on low-altitude flight

Abstract

The invention discloses a logistics management method based on low-altitude flight, and provides a multi-dimensional optimization scheme for the problems of poor adaptability of complex scenes, low resource utilization rate and formation collaboration. An anti-interference path is generated by constructing a dynamic-static cooperative impedance model and combining robust optimization, a learning prediction dynamic adjustment strategy is reinforced, and adaptive optimization of the path is realized; an energy consumption and task density coupled composite impedance model is introduced, the influence of regional loads on energy consumption is quantified, and the high-density regional distribution efficiency is optimized; a space-time clustering algorithm is adopted to layer tasks according to geographical proximity and time urgency, and emergency tasks are preferentially processed and area coverage is optimized through fast response and standard and elastic formation cooperative scheduling; a core area and an edge area are divided, a long-endurance unmanned aerial vehicle is used for covering a remote area, high-load formation batch distribution is performed on the core area, and dynamic balance coverage and repeated distribution impedance are performed. And the response speed, the energy utilization rate and the global distribution efficiency in a complex scene are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle task allocation, and more particularly to a low-altitude flight-based logistics management method. Background Art

[0002] With the rapid development of e-commerce, the rapid growth of e-commerce has given rise to a surge in the demand for logistics and distribution. In particular, the "last mile" distribution link faces challenges such as low efficiency, traffic congestion, and rising labor costs. Against this background, logistics unmanned aerial vehicles have become a cutting-edge technology for breaking through the bottleneck of terminal distribution due to their advantages such as strong flexibility, fast response speed, and the ability to avoid ground traffic restrictions. Globally, major companies have carried out unmanned aerial vehicle logistics pilots to verify their application potential in remote areas, emergency material transportation, and high-timeliness scenarios.

[0003] The Chinese invention patent with the publication number CN117634818B provides a logistics unmanned aerial vehicle task allocation method with priority division. Based on the natural geographical environment, low-altitude airspace structure, and the performance of logistics unmanned aerial vehicles, the three-dimensional operation space information of logistics unmanned aerial vehicles is extracted to obtain the performance parameters of logistics unmanned aerial vehicles; combined with the needs of logistics companies and customers, the transportation type, flow, flow direction, and flow time data of logistics unmanned aerial vehicles are obtained to construct the operation scenario of logistics unmanned aerial vehicles; combined with task priority and the fairness of logistics companies, a service satisfaction index for logistics unmanned aerial vehicles is established; with the goal of minimizing flight impedance and maximizing service satisfaction, a logistics unmanned aerial vehicle task allocation model is constructed; the NSGA-II algorithm is used to solve the model, and the optimal resource allocation plan for logistics unmanned aerial vehicles is output.

[0004] However, most of them are based on single-machine independent optimization, with the goal of minimizing flight impedance and maximizing service satisfaction, and a multi-objective optimization model is constructed. Although such methods can solve the basic task allocation problem, they do not consider the adaptability to complex environmental scenarios, resource utilization rate, and formation coordination problems. Summary of the Invention

[0005] The present application solves the problems of poor adaptability to complex environmental scenarios, low resource utilization rate, and poor formation coordination of logistics unmanned aerial vehicles in the prior art by providing a low-altitude flight-based logistics management method.

[0006] The present application provides a low-altitude flight-based logistics management method, and the method includes: S1. Associating the dynamic task impedance and the static planning impedance through a collaborative weight factor to form a dynamic-static collaborative impedance; using a robust optimization model to generate multiple candidate static paths, with each path considering the maximum anti-interference ability; based on a prediction model of reinforcement learning, predicting the dynamic adjustment probability and cost; S2. Based on the dynamic-static collaborative impedance, introduce the energy management impedance and task density impedance to construct a composite impedance model; conduct task density-energy coupling modeling; adopt a composite impedance minimization decision combination to achieve dynamic adaptive-energy density collaborative optimization; S3. Through the collaborative operation of UAV formations, combined with spatio-temporal coupling clustering and formation collaborative path planning, achieve global task allocation optimization, and improve the emergency task response speed and regional coverage efficiency; S4. Balance the regional coverage impedance and repeated delivery impedance through the grouping strategy, further optimize the regional coverage and repeated delivery efficiency, and achieve efficient delivery across the region.

[0007] Furthermore, associate the dynamic task impedance and the static planning impedance through a collaborative weight factor, and define it as: ; where: is the static planning weight, , reflecting the degree of dependence on the basic path; is the dynamic adjustment penalty factor, , the higher the proportion of the dynamic impedance, the greater the total collaborative impedance; is the dynamic task impedance; is the static planning impedance; represents the ratio of the dynamic adjustment cost to the static planning cost, measuring the robustness of the static planning; ; where, is the static planning impedance, is the flight time, is the takeoff and landing time, is the charging time; ; where, is the dynamic task impedance, is the weather, is the congestion, is the emergency task.

[0008] Furthermore, adopt a robust optimization model. By inputting geographical environment data, UAV performance parameters, and historical task data, generate multiple candidate static paths. Each path considers the maximum anti-interference ability (such as reserving a detour margin and charging node redundancy) to obtain a set of static paths , represents the nth static path, and each path is accompanied by a robustness score.

[0009] Furthermore, based on the prediction model of reinforcement learning, predict and dynamically adjust the probability and cost, and select adjustment strategies according to real-time environmental data, sudden task requests, and the robustness score of the current static path: Strategy 1: Fine-tune the path, such as local obstacle avoidance and dynamic impedance is relatively low; Strategy 2: Switch to the standby static path, and the dynamic impedance is relatively high but task interruption is avoided; Output the dynamically adjusted path and the corresponding , is the optimal feasible path generated by the system through the adjustment strategy. Formulate a collaborative impedance minimization decision, and the constraint conditions are: task completion rate ≥ 99%; service satisfaction ≥ 0.95; The objective function is: .

[0010] Furthermore, on the basis of the original dynamic-static collaborative impedance, introduce energy management impedance and task density impedance to construct a composite impedance model: ; where: represents the composite impedance; is the energy management impedance; is the task density impedance; is the weight of the dynamic-static collaborative impedance, , inheriting the balance of path robustness and flexibility in the original scheme; is the energy-density coupling weight, , reflecting the amplification effect of task density on energy consumption; represents the energy consumption efficiency in high task density areas. The higher the density, the greater the energy consumption per unit static path.

[0011] Furthermore, quantify the task density: Divide the area levels according to the density; The calculation formula for the energy management impedance is: ; where: is the energy management impedance; is the power consumption of the UAV; is the full charge; represents a single UAV u in the UAV set U; represents the task density in area s, and the calculation formula is: , N is the number of demand points, A is the area of the area, is the density-energy consumption coefficient, low density = 1, medium density = 1.2, high density = 1.5; ; Wherein: is the task density impedance, RT is the path congestion time, and ST is the standard flight time represents a single area s in the area set S; Make a decision to minimize the composite impedance, and the objective function is: ; Wherein, the value of minimizing the composite impedance.

[0012] Furthermore, classify the formations: a rapid response formation composed of high-endurance and high-speed drones, dedicated to emergency time window tasks; a standard formation composed of ordinary drones, dealing with standard time window tasks; an elastic formation composed of rechargeable drones, responsible for loose time window tasks and supporting dynamic task insertion; emergency tasks are preferentially assigned to the rapid response formation to ensure the shortest path and the least interference; standard tasks are assigned to the standard formation according to the area clustering results, and a single formation covers multiple demand points within the same cluster; the elastic formation is dynamically adjusted according to the real-time task density to fill high-load areas or replace low-battery drones.

[0013] Furthermore, on the basis of traditional K-means spatial clustering, fuse the time window urgency and introduce spatio-temporal coupling clustering: ; Wherein, CW is the spatio-temporal coupling clustering weight, is the spatial and temporal weight, defaulting to 0.7, with a value range of [0,1], SD is the spatial distance; WU is the time window urgency, which is defined as , RT is the remaining time, ST is the total time window, and the larger the time window urgency value, the more urgent it is.

[0014] Furthermore, set the long-endurance drones as the coverage formation, equip them with large-capacity batteries, and be responsible for the distribution in remote and low-density areas, mainly covering scattered demand points to minimize the area coverage impedance; set the high-load drones as the efficient formation, support batch task packaging, reduce repeated deliveries, mainly serve high-density core areas, and reduce the repeated impedance through single-time multi-task deliveries; retain the original formations: rapid response formation, standard formation, elastic formation.

[0015] Furthermore, according to the task density, divide the area into: core area, edge area, buffer area; matching rule: the coverage formation is only assigned to the edge area, and the efficient formation is only assigned to the core area to avoid cross-regional task intersections; The elastic formation monitors the task density in the buffer area in real time and dynamically switches the formation type (such as switching from the standard formation to the coverage formation).

[0016] Furthermore, introduce two new types of impedance, and The impedance jointly constitutes the global optimization objective; ; Among them, is the weight of the repeated delivery impedance; is the weight of the repeated delivery impedance, is the weight of the composite impedance, The sum is equal to 1 and is dynamically adjusted according to the regional load; Regional coverage impedance: Measuring the delivery timeliness in the edge area, which is positively correlated with the distance. Introduce the distance penalty coefficient: ; Among them, is the regional coverage impedance; represents a single area s within the edge area; WH is the straight-line distance between the demand point and the warehouse, in kilometers; is the distance penalty coefficient in the edge area, used to amplify the time cost of delivery in the edge area, and preferentially allocate long-endurance unmanned aerial vehicles, such as = 1.2; ; Among them, is the repeated delivery impedance; represents a single area s within the core area; AC represents the number of repeated deliveries; represents the cost coefficient of a single repeated delivery, such as = 0.5, used to quantify the resource consumption of a single repeated delivery.

[0017] One or more technical solutions provided in this application have at least the following technical effects or advantages: By providing a low-altitude flight-based logistics management method, the problems of poor adaptability to complex environmental scenarios, low resource utilization rate, and poor formation coordination of logistics unmanned aerial vehicles in the prior art are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of a low-altitude flight-based logistics management method in an embodiment of the present invention.

[0019] Figure 2 It is a flowchart of robust path generation in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] For ease of understanding the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs; the terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] Embodiment 1: A low-altitude flight logistics management method of the present application, the method includes: When a logistics drone is performing delivery, it will encounter a static planning impedance generated by a benchmark cost calculated based on a preset route network, drone performance, and historical mission data; the defined formula is: ; Wherein, is the flight time, is the takeoff and landing time, is the charging time; correspondingly, the additional cost caused by real-time environmental interference and sudden tasks is called dynamic task impedance; the defined formula is: ; Wherein, is the weather, is the congestion, is the sudden task.

[0023] The weighted combination of the static planning impedance and the dynamic task impedance is the dynamic-static collaborative impedance, aiming to balance the basic path efficiency and the real-time environment adaptation ability, and its definition is: ; Wherein: is the static planning weight , reflecting the degree of dependence on the basic path; is the dynamic adjustment penalty factor , the higher the proportion of the dynamic impedance, the greater the total collaborative impedance; is the dynamic task impedance; is the static planning impedance; represents the ratio of the dynamic adjustment cost to the static planning cost, measuring the robustness of the static planning.

[0024] Robust static planning pre-optimization, such as Figure 2Shown: By inputting geographical environment data, UAV performance parameters, and historical mission data, multiple candidate static paths are generated. Each path considers the maximum anti-interference ability to obtain a set of static paths. , Denote the nth static path, and attach a robustness score to each path.

[0025] Generate redundant paths through Monte Carlo simulation, and reserve a detour margin and a robustness score to screen high anti-interference paths, reducing the need for dynamic adjustment.

[0026] Based on a prediction model of reinforcement learning, predict the probability and cost of dynamic adjustment. According to real-time environmental data, sudden mission requests, and the robustness score of the current static path, select adjustment strategies: Strategy 1: Fine-tune the path, such as local obstacle avoidance and dynamic impedance is relatively low; Strategy 2: Switch to a standby static path, with a relatively high dynamic impedance but avoiding mission interruption; Output the path after dynamic adjustment and the corresponding , which is the optimal feasible path generated by the system through the adjustment strategy.

[0027] The RL model can predict the path congestion probability in the next 30 minutes, preferentially select local adjustment strategies, reduce the path switching frequency, and can reduce the dynamic adjustment cost , the mission interruption rate is reduced, and the emergency mission response time is shortened.

[0028] Formulate a collaborative impedance minimization decision, with the constraint conditions: mission completion rate ≥ 99%; service satisfaction ≥ 0.95; the objective function is: ; Improve the NSGA-II algorithm, encode the UAV path as an integer sequence; the weight , is encoded as a floating point number, with a dynamic range of [0,1]×[0,10]; adjust according to the real-time environmental risk level , : ; where L is the risk level, with a value range of [0,10]; Map the risk level to , : Peak period: =0.2, =16; Off-peak period (risk level 2): =0.8, =4.

[0029] Through collaborative weight dynamic optimization, the proportion during peak periods is dynamically adjusted, and the on-time rate of tasks is improved; during off-peak periods, the static path utilization rate is increased, and energy consumption is reduced.

[0030] The technical solutions in the above embodiments of the present application at least have the following technical effects or advantages: Through a dynamic-static impedance coupling model, robust path pre-optimization, and data-driven weight adjustment, the present application has achieved triple breakthroughs in the efficiency, robustness, and satisfaction of logistics UAV task allocation, while improving service satisfaction and task reliability. It can achieve seamless connection from static planning to dynamic response. Static planning pre-optimization reduces the need for dynamic adjustment, and dynamic prediction and strategy selection improve response efficiency; multiple strategies cooperate to cope with sudden interferences; more efficient and stable logistics UAV task allocation is achieved while improving satisfaction.

[0031] However, the existing technology only focuses on static path optimization and does not consider real-time dynamic interferences such as weather changes and sudden tasks, which may lead to order delays. For example, in the daily distribution in the city center, the basic order volume is stable, such as 200 orders per day, the weather is clear, and the airspace is unobstructed. However, due to temporary traffic control during the morning rush hour in a certain residential area, order delays may occur. By adopting the above technical solution, the pre-generated robust static path is directly called, and through the RL model, the controlled area is detected, and Strategy 1 is triggered, so that the sudden detour distance is shortened by 68%, and the average detour time is shortened from 15 minutes to 4 minutes; by dynamically adjusting the weight = 0.6, = 8, the probability of task interruption is reduced by 73%.

[0032] Embodiment 2: In the above embodiment, although the coordination between the dynamic path and the static planning is optimized, the amplification effect of task space density on energy efficiency is not fully considered. For example, when the distribution points in the same area are highly concentrated, the frequent takeoff, landing, obstacle avoidance, and charging waiting of UAVs will cause non-linear increase in energy consumption, which will in turn affect the overall distribution efficiency. This embodiment further improves the above embodiment.

[0033] On the basis of the original dynamic-static collaborative impedance, an energy management impedance and a task density impedance are introduced to construct a composite impedance model: ; Where: represents the composite impedance; is the energy management impedance; is the task density impedance; is the weight of the dynamic-static collaborative impedance, , inheriting the balance of path robustness and flexibility of the original scheme; is the energy-density coupling weight, , reflecting the amplification effect of task density on energy consumption; Indicates the energy consumption efficiency of high task density areas (the higher the density, the greater the energy consumption per unit of static path).

[0034] Identify high-density grids and automatically trigger the following strategies: assign fully charged drones or pre-deployed mobile charging stations; adjust the flight altitude to the low-turbulence layer to reduce headwind energy consumption; reduce the unit task energy consumption in high-density areas and increase the daily average endurance time.

[0035] Optimize the dynamic-static collaborative impedance. Use the static pre-generated robust path set and real-time environmental data (weather, airspace status) as input data. Based on reinforcement learning, predict high-probability interference events (such as sudden congestion), and select local detours or switch to alternative paths for dynamic path adjustment; dynamically adjust the γ value according to the time period (peak / low). For example, reduce γ during peak periods to focus on dynamic adjustment, and increase γ during low periods to prioritize the stability of static paths as a weight adaptability to optimize the output dynamic path And the corresponding value.

[0036] The composite impedance model is defined as: ; Where: Represents the composite impedance; Is the energy management impedance; Is the task density impedance; Is the weight of the dynamic-static collaborative impedance, , inheriting the balance of path robustness and flexibility in the original scheme; Is the energy-density coupling weight, , reflecting the amplification effect of task density on energy consumption; Indicates the energy consumption efficiency of high task density areas. The higher the density, the greater the energy consumption per unit of static path; ; Where: Is the energy management impedance, Is the power consumption of the drone, Is the full charge; Represents a single drone u in the drone set U; Represents the task density in area s, and the calculation formula is: , N is the number of demand points, A is the area of the region, Is the density-energy consumption coefficient, low density = 1, medium density = 1.2, high density = 1.5; ; Where: The task density impedance is \(Z_{TD}\), the path congestion time is \(RT\), and the standard flight time is \(ST\). Represents a single area \(s\) in the area set \(S\); ; Wherein, The value that minimizes the composite impedance.

[0037] And add constraint conditions, regional load balancing: a single UAV serves at most 3 tasks in a high-density area to avoid concentrated power consumption; energy safety threshold: the remaining power of the UAV shall not be lower than 20% to prevent emergency landing. Through collaborative optimization, the combination of "low-energy consumption path + balanced load" is preferentially selected; in low-density areas: straight flight routes are adopted to maximize the static path efficiency. In high-density areas: the snake-shaped inspection mode is enabled to complete multi-point distribution in batches, achieving the effect of reducing the composite impedance.

[0038] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: By introducing the energy management-task density coupling relationship, the DA-EDCO scheme further optimizes the energy consumption and task allocation balance in high-density areas on the basis of dynamic adaptive path planning. Its core lies in: accurately quantifying the impact of density on energy consumption: through Coefficients, dynamically adjust the energy distribution strategy; load balancing and minimizing the composite impedance; for example, during the "Double Eleven" period, the order volume surges, and there is a dense distribution demand in the core business district. The traditional scheme has a battery life crisis, and the UAVs land and take off frequently, resulting in power exhaustion and forced landing; adopting the above technical solutions can activate the composite impedance model, identify high-density areas, automatically deploy mobile charging stations, adjust the flight altitude to the low-turbulence layer, enable the snake-shaped inspection mode, complete multi-point distribution in batches, and the density-aware energy distribution increases the single UAV task volume by 40% in high-density areas and the battery life by 2.3 hours. Thus, the composite impedance is reduced, the task volume is increased, and more efficient and stable collaborative distribution of logistics UAVs is achieved.

[0039] Embodiment 3: In the above embodiment, although the energy consumption and task allocation are optimized, in the scenario of large-scale deployment of logistics UAVs, the single UAV task allocation mode faces bottlenecks such as lag in emergency task response, low regional coverage efficiency, and poor dynamic environment adaptability. This embodiment further improves the above embodiment.

[0040] Classify the formations: A rapid response formation composed of high-endurance and high-speed drones is dedicated to emergency time window tasks; a standard formation composed of ordinary drones handles standard time window tasks; a flexible formation composed of rechargeable drones is responsible for loose time window tasks and supports dynamic task insertion; emergency tasks are preferentially assigned to the rapid response formation to ensure the shortest path and the least interference; standard tasks are assigned to the standard formation according to the regional clustering results, and a single formation covers multiple demand points within the same cluster; the flexible formation is dynamically adjusted according to the real-time task density to fill high-load areas or replace low-battery drones.

[0041] Based on the traditional K-means spatial clustering, fuse the time window urgency and introduce spatio-temporal coupled clustering: ; Among them, CW is the spatio-temporal coupled clustering weight, is the spatial and temporal weight, defaulting to 0.7, with a value range of [0,1], and SD is the spatial distance; WU is the time window urgency, which is defined as , RT is the remaining time, ST is the total time window, and the larger the time window urgency value, the more urgent it is.

[0042] Adopt different cluster matching strategies for different formations; rapid response formation: high-urgency cluster, time window urgency ≥ 0.8, and use a straight-line path to reach the target directly; standard formation: medium-low urgency cluster, time window urgency < 0.8, and serve all points within the cluster in the order of the closed path; flexible formation: dynamically fill the uncovered cluster or take over the overflow tasks.

[0043] Formation collaborative path planning: Use the ant colony algorithm to generate the shortest closed path for each formation to cover all demand points within the cluster, and the objective function: ; Among them, is the flight time; is the takeoff and landing time consumption; is the time window delay penalty coefficient, which is used to amplify the cost of emergency task timeout and ensure the delivery timeliness. For example, =2; is the maximum time window delay value of all tasks within the formation, in minutes, and the calculation method is: ; Among them, TT is the actual arrival time, and TM is the time window upper limit; for example, if a task time window is [09:00, 10:00] and the actual arrival time is 10:15, then the delay is It is 15 minutes. 0 represents the lower limit of the delay time. That is, when the actual arrival time does not exceed the upper limit of the time window, the delay time is forced to be set to 0. Formulate the collaborative rules between formations: The rapid response formation enjoys airspace priority, and the standard formation needs to detour at least 500 meters from its path; The drones in the flexible formation can provide emergency charging support to other formations, and through the wireless charging module, extend the mission cycle; Based on real-time position sharing, automatically adjust the formation altitude layer. The rapid formation flies at 100 - 150 meters, and the standard formation flies at 50 - 100 meters.

[0044] Dynamic task reallocation and formation reconstruction; Triggered in the following situations, sudden task insertion: such as a temporary urgent order; Equipment failure: insufficient drone battery power or communication interruption; Environmental interference: bad weather causes flight bans in some areas. When encountering the above situations, adopt the following reallocation strategies: Emergency task takeover: The rapid response formation gives priority to handling. If it is full, trigger the expansion of the flexible formation, temporarily adding 2 - 3 drones; Standard task delay processing: Re-cluster and allocate to the flexible formation, and reduce its time window weight to below 0.5; Formation reconstruction algorithm: A dynamic adjustment model based on deep reinforcement learning, aiming to minimize the global impedance as the goal, and optimize the formation structure and path in real time.

[0045] The technical solutions in the above embodiments of the present application at least have the following technical effects or advantages: The present application improves the emergency task response ability and resource utilization rate by introducing formation collaborative priority clustering optimization; optimizes the spatio-temporal matching of tasks within the formation to reduce conflicts; reduces the global impedance through priority passage and energy sharing; for example, it is necessary to deliver materials to 8 locations, and the time window is compressed to 45 minutes. At the same time, a thunderstorm weather is encountered, and 3 main flight routes are closed. Adopt the above technical solutions for formation collaborative emergency response. The rapid response formation breaks through directly, and spatio-temporal clustering combines 8 points into 2 emergency clusters. At the same time, the flexible formation provides in-air charging support, extending the mission radius by 35%. Spatio-temporal coupling clustering improves the emergency task response speed by 112%, and formation collaboration avoids 62% of route conflicts. Finally, the formation plan is significantly improved in terms of response speed, task volume and stability, enabling more efficient and stable collaborative distribution of logistics drones.

[0046] Embodiment 4: In the above embodiment, although the response speed, task volume and stability are improved, the regional coverage is uneven. In remote areas, due to low task density and long distances, drones make repeated round trips, resulting in high energy consumption and poor timeliness. In high-density areas, due to scattered orders, a single drone needs to make multiple round trips to the same area, causing path redundancy. In view of the problems of coverage and repeated distribution, this embodiment further improves the above embodiment.

[0047] Set the long-endurance UAV as the coverage formation, equip it with a large-capacity battery, and be responsible for distribution in remote and low-density areas, mainly covering scattered demand points to minimize the regional coverage impedance; set the high-load UAV as the efficient formation, support batch task packaging, reduce repeated deliveries, mainly serve high-density core areas, and reduce the repeated impedance through single-time multi-task deliveries; retain the original formations: the rapid response formation, the standard formation, and the flexible formation.

[0048] According to the task density, divide the area into: the core area, the edge area, and the buffer area; matching rule: the coverage formation is only assigned to the edge area, and the efficient formation is only assigned to the core area to avoid cross-regional task intersections; The flexible formation monitors the task density in the buffer area in real time and dynamically switches the formation type (such as from the standard formation to the coverage formation).

[0049] Introduce two new types of impedance, which together with the impedance constitute the global optimization objective; ; Among them, is the weight of the repeated delivery impedance; is the weight of the repeated delivery impedance, is the weight of the composite impedance, The sum is equal to 1 and is dynamically adjusted according to the regional load; ; Among them, is the regional coverage impedance; represents a single area s in the edge area; WH is the straight-line distance between the demand point and the warehouse, in kilometers; is the edge area distance penalty coefficient, such as = 1.2; ; Among them, is the repeated delivery impedance; represents a single area s in the core area; AC represents the number of repeated deliveries; represents the single repeated delivery cost coefficient, such as = 0.5, which is used to quantify the resource consumption of a single repeated delivery.

[0050] Match the formations according to the regional clustering. In the core area, generate high-density task clusters based on the K-means++ algorithm, and each cluster is served by 1 efficient formation; in the edge area, divide the grid according to the administrative boundary or natural terrain, and each grid is assigned 1 coverage formation; in the buffer area, monitor the task density in real time and trigger the flexible formation mode switch, such as from the standard formation to the coverage formation.

[0051] Among them, the coverage formation adopts a "radiating straight-line path" to directly reach the edge demand points from the warehouse, and can pick up sporadic orders on the return journey; the efficient formation generates a "closed-loop path" based on an improved ant colony algorithm to cover all demand points within the cluster; the flexible formation enables a "dynamic patrol mode" in the buffer zone to scan unassigned tasks along the main roads.

[0052] When the tasks in the core area are overloaded, the cluster is automatically split and the flexible formation is called for support to achieve overload warning; when the task volume of the coverage formation exceeds the threshold, the flexible formation switches to the coverage mode to take over the excess tasks for reinforcement in the edge area.

[0053] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: Through the formation grouping and regional exclusive service strategy in the present application, the problems of repeated distribution in the core area and coverage in the edge area are solved simultaneously, and the global total impedance is reduced; the utilization rate of the formation is improved, and the flexible resource pool reduces redundant investment; the dynamic balance covers, repeats and the original trade-off goals; for example, there have long been pain points in distribution in remote mountainous areas: 5 villages are scattered in a mountainous area of 80 km², with only 8 orders per day on average, but the traditional solution requires drones to make round trips every day, resulting in high costs. By adopting the above technical solutions, through the deployment of exclusive formations and the radiating straight-line distribution of the coverage formation, the 80 km² is divided into 3 exclusive grids, and the distance penalty coefficient =1.2 is used to optimize the path, increasing the edge coverage efficiency by 217% and shortening the distribution time in the mountainous area from 48 hours to 8 hours. Global optimality is achieved, and more efficient and stable collaborative distribution of logistics drones is realized.

Claims

1. A low-altitude flight logistics management method, characterized in that: The following steps are involved: S1. Associate the dynamic task impedance and the static planning impedance into dynamic-static collaborative impedance through the collaborative weight factor; use the robust optimization model to generate multiple candidate static paths, each path considering the maximum anti-interference ability; based on the prediction model of reinforcement learning, predict the probability and cost of dynamic adjustment; S2. Based on the dynamic-static synergistic impedance, energy management impedance and task density impedance are introduced to construct a composite impedance model; task energy-density coupling modeling is performed; composite impedance minimization decisions are taken to improve delivery efficiency; S3. Through UAV formation collaboration, combined with spatiotemporal coupling clustering and formation collaborative path planning, global task allocation optimization is achieved to improve emergency task response speed and regional coverage efficiency; S4. The regional coverage impedance and repeated delivery impedance are balanced through grouping strategy, which further optimizes the regional coverage and repeated delivery efficiency and realizes efficient delivery across the entire region.

2. A low-altitude flight logistics management method according to claim 1, characterized in that: The dynamic-static cooperative impedance model is defined as: ； in: For static planning weights , reflecting the degree of dependence on the basic path; To dynamically adjust the penalty factor, ,The higher the proportion of dynamic impedance, the greater the total cooperative impedance; is the dynamic task impedance; Impedance for static planning; It represents the ratio of dynamic adjustment cost to static planning cost, and measures the robustness of static planning; ； in, is the static planning impedance, is the flight time, is the take-off and landing time, For charging time; ， in, is the dynamic task impedance, For the weather, For congestion, For emergency tasks.

3. The low-altitude flight logistics management method according to claim 1 is characterized in that: The robust optimization model is defined as: By inputting geographic environment data, UAV performance parameters, and historical mission data, multiple candidate static paths are generated. Each path considers the maximum anti-interference capability to obtain a static path set. , represents the nth static path, with a robustness score attached to each path.

4. The low-altitude flight logistics management method according to claim 1 is characterized in that: The composite impedance model is defined as: ； in: represents the composite impedance; Impedance management for energy; is the task density impedance; is the dynamic-static synergistic impedance weight, ,Inherit the original solution’s balance between path robustness and flexibility; is the energy-density coupling weight, , reflecting the amplifying effect of task density on energy consumption; It represents the energy consumption efficiency in the high task density area. The higher the density, the greater the unit static path energy consumption. ； in: Impedance for energy management, Power consumption for drones, Fully charged; Represents a single drone u in the drone set U; represents the task density in area s, and the calculation formula is: , N is the number of demand points, A is the area of ​​the region, is the density-energy consumption coefficient, low density =1, medium density =1.2, high density =1.5; ； in: is the task density impedance, RT is the path congestion time, and ST is the standard flight time represents a single region s in the region set S; ； in, The value at which the composite impedance is minimized.

5. The low-altitude flight logistics management method according to claim 1 is characterized in that: The spatiotemporal coupled clustering is defined as: , where CW is the spatiotemporal coupling clustering weight, is the spatial and temporal weight, with a default value of 0.7 and a range of [0,1]; SD is the spatial distance; WU is the time window urgency, which is defined as , RT is the remaining time, ST is the total time window, and the larger the time window urgency value is, the more urgent it is; When the formation collaborative path planning generates the optimal path, the objective function is: ； in, is the flight time; It takes time for take-off and landing; is the time window delay penalty coefficient, which is used to amplify the cost of urgent task overtime, such as =2; It is the maximum time window delay value of all tasks in the formation, in minutes, calculated as follows: ； Among them, TT is the actual arrival time, and TM is the upper limit of the time window; if the time window of a task is [09:00,10:00], and the actual arrival time is 10:15, then the delay The delay time is 15 minutes, and 0 indicates the lower limit of the delay time. That is, when the actual arrival time does not exceed the upper limit of the time window, the delay time is forcibly set to 0.

6. The low-altitude flight logistics management method according to claim 1 is characterized in that: The formations include: rapid response formation, standard formation and flexible formation; The rapid response formation refers to a formation composed of high-endurance, high-speed drones, which are dedicated to emergency tasks within 1 hour, among which, high endurance refers to a full-load flight distance of ≥ 50 kilometers after a single charge, and high speed refers to a cruising speed of ≥ 90 km / h and a maximum speed of ≥ 120km / h; the standard formation refers to a formation that can complete a standard task within 3 hours and is allocated according to the results of spatiotemporal clustering; the flexible formation refers to a formation composed of rechargeable drones that dynamically fill high-load areas and take over overflow tasks.

7. The low-altitude flight logistics management method according to claim 1 is characterized in that: The global objective function is defined as: ； in, is the impedance weight for repeated delivery; is the repeated distribution impedance weight, is the composite impedance weight, The sum is equal to 1, and it is adjusted dynamically according to the regional load; ； in, is the regional coverage impedance; represents a single area s in the marginal area; WH is the straight-line distance between the demand point and the warehouse, in kilometers; is the edge area distance penalty coefficient, such as =1.2; ； in, Impedance for repeated delivery; represents a single area s within the core area; AC represents the number of repeated deliveries; Represents the cost coefficient of a single repeated delivery, such as =0.5, which is used to quantify the resource consumption of a single repeated delivery.

8. A low-altitude flight logistics management method according to claim 7, characterized in that: When the core area is overloaded with tasks, the elastic formation is triggered to expand or split the cluster; when the task volume exceeds the threshold, the elastic formation switches to overlay mode to take over the tasks.

9. The low-altitude flight logistics management method according to claim 3 is characterized in that: The robustness score of the candidate static path is calculated based on the detour margin, charging node redundancy and historical anti-interference data, and the dynamic adjustment strategy includes local path fine-tuning or switching to an alternative path.

10. A low-altitude flight logistics management method according to claim 6, characterized in that: Formation coordination includes: the rapid response formation enjoys airspace priority, and the standard formation must detour its path by at least 500 meters; the flexible formation provides cross-formation emergency charging support.

Images