Truck and heterogeneous unmanned aerial vehicle collaborative distribution path planning system based on dynamic requirements

Abstract

The invention relates to the technical field of logistics distribution, and discloses a truck and heterogeneous unmanned aerial vehicle cooperative distribution path planning system based on dynamic demands, and the system comprises a data collection module which collects order information, traffic conditions, weather conditions, and vehicle and unmanned aerial vehicle states; the data acquisition module is connected with a dynamic demand analysis module, and the dynamic demand analysis module performs updating according to order changes and environment changes and predicts subsequent order demands and distribution demands; the dynamic demand analysis module is connected with a collaborative path planning module, and the collaborative path planning module sets a constraint threshold. The advantages of the truck and the unmanned aerial vehicle are integrated, the cooperative path planning system is utilized to integrate multiple factors to optimize the path, the plan is adjusted in real time in combination with the dynamic demand analysis module, task allocation is optimized through the adjustment strategy module, the defects of a traditional mode are overcome, hysteresis is avoided, delay is reduced, and the distribution efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics distribution, and particularly to a collaborative distribution path planning system for trucks and heterogeneous drones based on dynamic demand. Background Art

[0002] In today's logistics distribution field, with the rapid development of e-commerce, people's demand for logistics distribution shows a trend of diversification and rapid growth. Traditional distribution methods mainly rely on ground transportation tools such as trucks, which have a large load capacity and transportation ability and can meet the distribution needs of most goods. However, with the expansion of cities and the increasing complexity of traffic conditions, ground traffic congestion has become an important factor restricting distribution efficiency. At the same time, customers' requirements for distribution time are also getting higher and higher. Especially in the distribution of some urgent or special items, it is very difficult to meet the requirements of fast and efficient delivery only by truck transportation. For example, in the central area of the city, traffic jams during peak hours will cause a significant extension of the truck distribution time, seriously affecting service quality and customer satisfaction. In addition, for some remote areas or areas with inconvenient transportation, truck transportation may be difficult to reach efficiently due to road conditions, which bring great challenges to traditional logistics distribution.

[0003] To address the above challenges, the application of heterogeneous drones in logistics distribution has begun to emerge. Heterogeneous drones have the advantages of being not restricted by ground traffic, fast speed, and strong accessibility, and are particularly suitable for short-distance fast distribution or areas that are difficult to access by trucks. In some scenarios, such as the emergency distribution of medical first-aid drugs and the fast transportation of high-value items, drones can play a unique advantage and greatly shorten the distribution time. However, drones also have their own limitations, such as limited load capacity, short endurance mileage, and their flight performance is seriously affected by factors such as weather and environment. For example, in bad weather conditions such as strong winds, heavy rains or fog, the flight safety and stability of drones will be threatened and they may even be unable to fly normally; and the weight and volume of goods they can carry are relatively small, which is not economical for the transportation of a large amount of goods. Therefore, relying solely on drones for distribution cannot fully meet the complex and diverse logistics needs.

[0004] However, there are still many deficiencies in the current path planning technology when dealing with this collaborative distribution. For example, in the actual use process, various different problems are likely to occur, such as insufficient battery power of drones and insufficient fuel of vehicles. Once this situation occurs, the drones may lose power on the way, resulting in the goods not being delivered on time, and even may crash and damage the goods. Insufficient fuel of the vehicle may be due to the driver's failure to refuel in time or unreasonable route planning, resulting in the vehicle needing to find a gas station during transportation, which will not only delay the distribution time, but also may cause the vehicle to deviate from the optimal route and increase the transportation cost. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a collaborative delivery path planning system for trucks and heterogeneous drones based on dynamic requirements. By using multimodal dynamic correction, integrating traffic, weather, and equipment status data, the path weights are corrected in real time, and a collaborative strategy for heterogeneous devices is used. Based on a multi-objective optimization model of energy-load-distance, the problem that in the existing collaborative delivery process of drones, when various different problems occur, the system cannot judge and adjust the plan in time, resulting in the crash of the drone and damage to the goods or the vehicle not being delivered in time is solved.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A collaborative delivery path planning system for trucks and heterogeneous drones based on dynamic requirements, including: a data acquisition module that collects order information, traffic conditions, weather conditions, and the status of vehicles and drones; a dynamic requirement analysis module is connected to the data acquisition module, and the dynamic requirement analysis module is updated according to order changes and environmental changes, and predicts subsequent order requirements and delivery requirements; a collaborative path planning module is connected to the dynamic requirement analysis module, and the collaborative path planning module sets constraint thresholds; a real-time monitoring and adjustment module is connected to the collaborative path planning module, and the real-time monitoring and adjustment module monitors various information in the delivery process in real time and timely reminds the staff to make adjustments; the dynamic requirement analysis module includes: a requirement change monitoring module that monitors order changes; an order update module is connected to the requirement change monitoring module, and the order update module adjusts and changes the order information according to the instructions and information of the requirement change monitoring module; the collaborative path planning module includes: a constraint condition setting module that sets constraint data, and a path planning algorithm module is connected to the constraint condition setting module, and the path planning algorithm module uses a genetic algorithm; the real-time monitoring and adjustment module includes: a real-time monitoring module that uses high-precision GPS positioning to obtain the real-time position coordinates of the truck and the real-time position coordinates of the drone, and an adjustment strategy module is connected to the real-time monitoring module, and the adjustment strategy module calculates according to the data of the real-time monitoring module using a calculation formula and makes corresponding strategy adjustments according to the results.

[0007] Preferably, the order information includes: the quantity, weight, volume, and delivery address of the order, and the weight of order i is denoted as w i , the volume is denoted as v i , and the longitude and latitude coordinates of the delivery address are (x i , y i ).

[0008] Preferably, the traffic conditions include: obtaining real-time road congestion conditions and average vehicle speeds by using traffic information APIs, in-vehicle GPS, and roadside sensors.

[0009] Preferably, the weather conditions include: wind speed, rainfall, and visibility under real-time weather.

[0010] Preferably, the vehicle and drone statuses include: collecting the real-time positions, battery levels (or fuel levels), and loads of the truck and the drone through in-vehicle sensors and the flight data recording devices carried by the drone itself.

[0011] Preferably, the constraint thresholds include load constraints, endurance constraints, and time constraints, and an algorithm is used to plan and calculate the delivery routes.

[0012] Preferably, the monitoring of order changes specifically includes: listening to the messages of the order system in real time, recording the relevant information of the order when a new order is generated; and updating the corresponding order status when the order is cancelled or modified.

[0013] Preferably, the constraint data specifically includes: load constraint: the load of the truck cannot exceed its maximum load, and the load of the drone cannot exceed its maximum load; endurance constraint: the flight distance of the drone cannot exceed its maximum endurance; time constraint: the entire delivery task needs to be completed within the specified time.

[0014] Preferably, the specific calculation formula in the adjustment strategy module is:

[0015]

[0016] Where:

[0017] S suitability represents the adaptability of the device to undertake new tasks. The higher this value, the more suitable the device is to undertake the tasks reallocated due to device failures or order demand changes under the comprehensive conditions of distance, load, and remaining battery or fuel. By comparing the S suitability values of different devices, the adjustment strategy module makes reasonable task allocation decisions to ensure delivery efficiency;

[0018] D distance-adjusted represents the distance from the device to the relevant task points after being corrected by traffic conditions and road condition factors;

[0019] W load-remaining represents the remaining load of the device;

[0020] Q energy-remaining-adjusted represents the remaining battery or fuel after being corrected for the energy consumption differences of the device under different working conditions;

[0021] The specific strategy adjustments include:

[0022] Device Selection and Task Allocation Strategy: According to the adaptability S of the device suitability , prioritize the allocation of tasks to devices with high adaptability, ensure that tasks can be completed by the device with the relatively shortest distance to the task point and the optimal comprehensive conditions of remaining load capacity and energy status, so as to improve the distribution efficiency;

[0023] Distance and Energy Adjustment Strategy:

[0024] For drones, if the corrected distance D from them to the task point distance-adjusted is relatively long and the remaining energy Q energy-remaining-adjusted is not enough to support the flight, transfer the task to a more suitable device or let it fly to a transfer point to wait for assistance or energy replenishment;

[0025] For trucks, if the remaining fuel quantity Q energy-remaining-adjusted is not enough to reach the task point, plan a route passing through a gas station to ensure that it can complete the subsequent tasks;

[0026] Load Capacity and Energy Balance Strategy:

[0027] Avoid allocating new tasks to devices that are fully loaded or nearly fully loaded W load-remaining close to 0 to ensure the performance and transportation safety of the devices; and when multiple devices are available for selection, prioritize the allocation of tasks to devices that have both sufficient remaining load capacity W load-remaining and sufficient energy Q energy-remaining-adjusted .

[0028] The present invention provides a collaborative distribution path planning system for trucks and heterogeneous drones based on dynamic demands.

[0029] It has the following beneficial effects:

[0030] 1. The present invention integrates the advantages of trucks and drones, uses the collaborative path planning system to optimize the path by synthesizing multiple factors, combines the dynamic demand analysis module to adjust the plan in real time, and optimizes the task allocation through the adjustment strategy module, overcomes the defects of the traditional method, avoids lag, reduces delays, and significantly improves the distribution efficiency.

[0031] 2. The present invention monitors the traffic and environment in real time, uses the genetic algorithm to plan the optimal path, avoids energy waste, and combines the load capacity and energy balance strategy to prevent device overload, reducing the operation cost.

[0032] 3. The real-time monitoring module of the present invention can cope with insufficient energy, adjust the flight plan, and the constraint conditions ensure the device performance, enhance the distribution reliability, and reduce the risk of task failure.

[0033] 4. The present invention can adapt to diverse demands, adjust the plan and task allocation through the dynamic demand analysis module and real-time data, cope with emergencies, and demonstrate the adaptability and flexibility of the system. Brief Description of the Drawings

[0034] Figure 1 This is a three-dimensional view of the present invention. Detailed Description of the Invention

[0035] Next, in combination with the accompanying drawings of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0036] Embodiment:

[0037] Please refer to the attached Figure 1 , the embodiment of the present invention provides a collaborative distribution path planning system for trucks and heterogeneous drones based on dynamic demand, including: a data acquisition module, which collects order information, traffic conditions, weather conditions, and vehicle and drone status. The order information includes: the number, weight, volume, and delivery address of the order, and the weight of order i is denoted as w i , the volume is denoted as v i , and the longitude and latitude coordinates of the delivery address are (x i , y i )

[0038] The traffic conditions include: using traffic information APIs, in-vehicle GPS, and roadside sensors, etc., to obtain real-time road congestion conditions and average vehicle speeds;

[0039] The weather conditions include: wind speed, rainfall, and visibility under real-time weather;

[0040] The vehicle and drone status includes: collecting the real-time positions, battery levels (or fuel levels), and load capacities of the trucks and drones through in-vehicle sensors and flight data recording devices carried by the drones;

[0041] The data acquisition module is connected to a dynamic demand analysis module, which is updated according to order changes and environmental changes, and predicts subsequent order demands and delivery demands; a dynamic demand analysis algorithm is set in the dynamic demand analysis module, and the dynamic demand analysis algorithm includes:

[0042]

[0043] It should be noted that, it is necessary to input the order change vector ΔO t = [Δo1,..., Δo n1. The environmental attenuation coefficient \(E\in[0,1]\), and the predicted value of the output demand is calculated through a formula.

[0044] The dynamic demand analysis module includes: a demand change monitoring module, which monitors the changes in orders. Specifically, it listens to the messages of the order system in real time. When a new order is generated, it records the relevant information of the order; when an order is cancelled or modified, it updates the corresponding order status. A demand change abnormal fluctuation algorithm is set in the demand change monitoring module, and the demand change abnormal fluctuation algorithm includes:

[0045]

[0046] It should be noted that by inputting a continuous order stream \(\{o1, o2,...\}\) and a time window \(T\), the abnormal fluctuation identifier Alert \(\in\{0,1\}\) is calculated through a formula; and the update rule of the parameter \(\eta\) in the above formula is:

[0047]

[0048] An order update module is connected to the demand change monitoring module. The order update module adjusts and changes the order information according to the instructions and information of the demand change monitoring module. An order update algorithm is set in the order update module, and the order update algorithm includes:

[0049]

[0050] It should be noted that by inputting the demand prediction 1. The alert status Alert, and the resource status \(R = [truck l oad, uav b attery]\), the updated priority \(P\) is calculated through a formula ′ .

[0051] A collaborative path planning module is connected to the dynamic demand analysis module. The collaborative path planning module sets constraint thresholds, including load constraint, endurance constraint, and time constraint, and uses the collaborative planning preprocessing equation algorithm to plan and calculate the distribution path. At the same time, the dynamic demand analysis module triggers path replanning through real-time order changes and sends update instructions to the collaborative path planning module. The collaborative planning preprocessing equation algorithm includes:

[0052]

[0053] Spatial-temporal allocation Vor k (O): Generate a Voronoi diagram to divide the service area based on the type of transportation tool

[0054]

[0055] Neighborhood traversal NN-Walk(seed): The unassigned order closest to the seed point is used as the next node to generate an initial path chain;

[0056] It should be noted that the input order set O = {o1, o2,..., o n}, the coordinates of the distribution center (x d , y d ) are required, so that the output initial path set Path (0) can be calculated through the formula;

[0057] The collaborative path planning module includes: a constraint condition setting module. The constraint condition setting module uses the constraint relaxation factor algorithm to calculate constraint data. The constraint data is: load constraint: the load of the truck cannot exceed its maximum load, and the load of the drone cannot exceed its maximum load; endurance constraint: the flight distance of the drone cannot exceed its maximum endurance; time constraint: the entire distribution task needs to be completed within the specified time. The constraint relaxation factor algorithm includes:

[0058]

[0059] It should be noted that the input real-time load W now , remaining battery power B now and used time T now are required, so that the output dynamic constraint threshold vector ΔW max , ΔL max , ΔT max can be calculated through the formula;

[0060] The path planning algorithm module is connected to the constraint condition setting module. The path planning algorithm module uses the genetic algorithm. The genetic algorithm is specifically:

[0061]

[0062] Among them:

[0063] T k (P): Total path time = truck driving time · number of path segments + drone flight time · charging coefficient;

[0064]

[0065] λ = 100: Time reference weight, Δk m ax is dynamically calculated by the constraint relaxation factor algorithm;

[0066] It should be noted that the candidate path chromosome P needs to be input, and the relaxation constraints ΔW max , ΔL max , ΔT max should be relaxed in real time, so as to calculate the output path optimization fitness value F(P) through formula calculation;

[0067] The collaborative path planning module is connected with a real-time monitoring and adjustment module. The real-time monitoring and adjustment module monitors various information in the distribution process in real time and timely reminds the staff to make adjustments. At the same time, the path planning module transmits the optimized path parameters to the real-time monitoring module, and the monitoring module dynamically adjusts the strategy according to the device status;

[0068] The real-time monitoring and adjustment module includes: a real-time monitoring module. The real-time monitoring module uses high-precision GPS positioning to obtain the real-time position coordinates of the truck and the real-time position coordinates of the drone, and calculates the real-time distance D through the distance formula between two points. Considering environmental factors such as wind speed α (0 - 1), the distance D is corrected adjusted = D × (1 + α), which is used to evaluate the feasibility of the drone's return journey;

[0069] The real-time monitoring module is connected with an adjustment strategy module. The adjustment strategy module calculates according to the data of the real-time monitoring module using a calculation formula and makes corresponding strategy adjustments according to the results. The specific calculation formula is:

[0070]

[0071] Where:

[0072] S suitability represents the adaptability of the device to undertake new tasks. The higher this value, the more suitable the device is to undertake the tasks reallocated due to equipment failures or order demand changes under the comprehensive conditions of distance, load, remaining power or fuel. By comparing the S suitability values of different devices, the adjustment strategy module can make reasonable task allocation decisions to ensure the distribution efficiency;

[0073] D distance-adjusted represents the distance from the device to the relevant task point after being corrected by factors such as traffic conditions and road conditions, and is usually obtained by using traffic information APIs, in-vehicle GPS, and roadside sensors, etc.;

[0074] W load-remaining represents the remaining load of the device, which is usually obtained by using load sensors installed on the truck;

[0075] Q energy-remaining-adjusted represents the remaining power or fuel after being corrected for the energy consumption differences under different working conditions of the device;

[0076] The specific strategy adjustments include:

[0077] Device selection and task assignment strategy: According to the adaptability S of the device suitability , the task is preferentially assigned to the device with high adaptability to ensure that the task can be completed by the device that is relatively close to the task point and has the best comprehensive conditions of remaining load and energy state, so as to improve the distribution efficiency;

[0078] Distance and energy adjustment strategy:

[0079] For the unmanned aerial vehicle, if the corrected distance D from it to the task point distance-adjusted is relatively long and the remaining energy Q energy-remaining-adjusted is not enough to support the flight, the task is transferred to a more suitable device or it is made to fly to a transfer point to wait for assistance or replenish energy;

[0080] For the truck, if the remaining fuel quantity Q energy-remaining-adjusted is not enough to reach the task point, plan a route passing through a gas station to ensure that it can complete the subsequent tasks;

[0081] Load and energy balance strategy:

[0082] Avoid assigning new tasks to devices that are fully loaded or nearly fully loaded W load-remaining close to 0 to ensure the device performance and transportation safety; and when multiple devices are available, preferentially assign the task to the device that has both sufficient remaining load W load-remaining and sufficient energy Q energy-remaining-adjusted .

[0083] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A truck and heterogeneous UAV collaborative distribution path planning system based on dynamic requirements, characterized in that Including: A data acquisition module, to which a dynamic demand analysis module is connected. The dynamic demand analysis module is updated according to order changes and environmental changes, and predicts subsequent order demands and delivery demands. A collaborative path planning module is connected to the dynamic demand analysis module, and the collaborative path planning module sets constraint thresholds. A real-time monitoring and adjustment module is connected to the collaborative path planning module, and the real-time monitoring and adjustment module monitors various information during the delivery process in real time. The dynamic demand analysis module includes: a demand change monitoring module and an order update module. The collaborative path planning module includes: a constraint condition setting module and a path planning algorithm module. The real-time monitoring and adjustment module includes: a real-time monitoring module and an adjustment strategy module.

2. The truck and heterogeneous UAV collaborative distribution path planning system based on dynamic demand according to claim 1, wherein The order information includes: the quantity, weight, volume, and delivery address of the order.

3. The truck and heterogeneous UAV collaborative distribution path planning system based on dynamic demand according to claim 1, wherein The traffic conditions include: using traffic information APIs, in-vehicle GPS, and roadside sensors to obtain real-time road congestion conditions and average vehicle speeds.

4. The collaborative delivery path planning system for trucks and heterogeneous UAVs based on dynamic demand according to claim 1, wherein The weather conditions include: wind speed, rainfall, and visibility under real-time weather.

5. The collaborative distribution path planning system for trucks and heterogeneous UAVs based on dynamic demand according to claim 1, wherein The vehicle and drone status includes: collecting the real-time positions, battery levels, fuel levels, and load capacities of trucks and drones through in-vehicle sensors and flight data recording devices carried by drones.

6. The collaborative delivery path planning system for trucks and heterogeneous UAVs based on dynamic demand according to claim 1, wherein The constraint thresholds include load constraints, endurance constraints, and time constraints, and an algorithm is used to plan and calculate the delivery path.

7. The collaborative distribution path planning system for trucks and heterogeneous UAVs based on dynamic demand according to claim 1, wherein The monitoring of order changes specifically refers to: listening to messages from the order system in real time and updating the corresponding order status.

8. The collaborative distribution path planning system for trucks and heterogeneous drones based on dynamic demand according to claim 1, wherein, The constraint data specifically refers to: load constraints, endurance constraints, and time constraints.

9. The collaborative distribution path planning system for trucks and heterogeneous UAVs based on dynamic requirements according to claim 1, wherein The specific calculation formula in the adjustment strategy module is: Where: S suitability Represents the adaptability of the device to undertake new tasks; D distance-adjusted The distance from the equipment to the relevant task points, after being corrected for traffic conditions and road condition factors; W load-remaining Represents the remaining load capacity of the device; Q energy-remaining-adjusted Represents the remaining power or fuel volume after correction for the energy consumption difference of the device under different operating conditions.

Images