CN-122015867-A - Refrigerator car-unmanned aerial vehicle-rider cooperative path planning method considering fresh loss

CN122015867ACN 122015867 ACN122015867 ACN 122015867ACN-122015867-A

Abstract

The application discloses a method for planning a collaborative path of a refrigerated truck, an unmanned aerial vehicle and a rider by considering fresh loss, which relates to the technical field of path planning and comprises the steps of defining path planning parameters of the refrigerated truck, the unmanned aerial vehicle and the rider by considering the fresh loss; the method comprises the steps of constructing a path planning model according to path planning parameters, generating an initial solution of the path planning model based on a greedy insertion algorithm, carrying out local search improvement on the initial solution to obtain a target solution, and carrying out collaborative execution on fresh distribution service according to a target demodulation degree refrigerator car, an unmanned aerial vehicle and a rider. According to the application, the path planning model considering the fresh loss is constructed, so that an initial solution is generated and a target solution is searched, the delivery routes of the refrigerated truck, the rider and the unmanned aerial vehicle can be synchronously decided, and the arrival freshness of fresh products can be improved and stabilized.

Inventors

TAO YI
XU LAN
LIN QIANG
LIN XIAOGANG
FAN JIE

Assignees

广东工业大学

Dates

Publication Date: 20260512
Application Date: 20260316

Claims (9)

1. A refrigerated vehicle-unmanned aerial vehicle-rider collaborative path planning method considering fresh loss, characterized in that the method comprises the following steps: defining path planning parameters of a refrigerated vehicle, an unmanned aerial vehicle and a rider considering fresh loss; constructing a path planning model according to the path planning parameters; Generating an initial solution of the path planning model based on a greedy insertion algorithm; Performing local search improvement on the initial solution to obtain a target solution; and cooperatively executing fresh-keeping delivery service by the refrigerated truck, the unmanned aerial vehicle and the rider according to the target unscheduled refrigerated truck.
2. The method for planning a collaborative path for a refrigerated vehicle, unmanned aerial vehicle and rider considering fresh losses according to claim 1, wherein the defining of path planning parameters for a refrigerated vehicle, unmanned aerial vehicle and rider considering fresh losses comprises the steps of: Constructing a directed graph And defines the following parameters: Fresh distribution service provider has a central warehouse Virtual endpoint for a mobile device A group of prepositioned bins close to customer points Virtual endpoint for a mobile device The service provider has a set of orders, each order having a customer's discharge location Time window The time window includes the earliest time of arrival And the latest arrival time Service time And parcel weight Wherein Index for customer collection, a central warehouse is configured with a set of refrigerated vehicles And a group of unmanned aerial vehicles Each front-mounted bin Equipped with a corresponding group of riders The rider fleet being Front-mounted bin Position and number of (a) is predetermined; Respectively show refrigerator car Rider(s) And unmanned aerial vehicle Defining the straight line flight of the unmanned aerial vehicle, and calculating the Euclidean distance between any two nodes when the unmanned aerial vehicle runs When the refrigerator car and the rider are running, the Manhattan distance is calculated It is assumed that the time of arrival of the daily fresh product at the central bin is recorded as It is defined that the fresh product is completely fresh at this time, the freshness loss rate when the fresh product is stored in the center warehouse and the front warehouse is set to α1, the freshness loss rate when the fresh product is stored in the refrigerating equipment of the refrigerator car is set to α2, the freshness loss rate when the fresh product is stored in the heat insulation boxes of the unmanned aerial vehicle and the rider is set to α3, and α1< α2< α3.
3. The method for collaborative route planning for a refrigerated vehicle-unmanned aerial vehicle-rider considering fresh loss according to claim 2, wherein the constructing a route planning model according to the route planning parameters comprises the steps of: The constructing the objective function of the path planning model comprises: ; ; ; ; ; ; Wherein min is the minimization function, the total cost Comprising a refrigerator car Rider(s) And unmanned aerial vehicle Is to be transported at a cost of (2) And freshness loss 。
4. The method for collaborative route planning for a refrigerated vehicle-unmanned aerial vehicle-rider with consideration of fresh loss according to claim 1, wherein the greedy insertion algorithm-based generation of an initial solution for the route planning model comprises the steps of: Constructing a first gradient route, setting a planned route to use all the refrigerated vehicles according to the path planning model, and adding a front bin distribution task for each refrigerated vehicle in sequence; initializing available routes of the unmanned aerial vehicle and the rider, and inserting each customer to be distributed into a certain position in the route of the unmanned aerial vehicle or the rider at the lowest insertion cost to obtain the initial solution, wherein the load limit, the maximum flight distance limit of the unmanned aerial vehicle and the time window limit are met before the current insertion position is calculated.
5. The method for planning a collaborative path for a refrigerated truck-unmanned aerial vehicle-rider considering fresh loss according to claim 1, wherein the performing a local search improvement on the initial solution to obtain a target solution comprises the following steps: Constructing four removing operators and four repairing operators according to the path planning model, wherein the removing operators comprise a random removing operator, a worst removing operator with cost, a worst removing operator with freshness and a random pre-bin removing operator; Predicting the selection probability of each operator by using a logistic regression model based on the accumulated characteristic values and taking the selection probability as the self-adaptive weight of the corresponding operator, wherein the characteristic values comprise solution state characteristics, operator characteristics and stage characteristics, the solution state characteristics comprise an optimal solution improvement value, a current solution improvement value, route similarity, optimal solution improvement times and current solution improvement times, the operator characteristics are feasibility rates, and the stage characteristics are iteration times; Selecting a removal operator and a repair operator for use in each iteration based on the adaptive weights using a roulette algorithm; performing local search improvement by using the selected removal operator and repair operator to obtain updated route and characteristic value; and continuously iterating the steps until a preset termination condition is reached, and obtaining the target solution.
6. The refrigerated vehicle-unmanned aerial vehicle-rider collaborative path planning method considering fresh losses according to claim 5, wherein the logistic regression model is trained by: training to obtain a static logistic regression model by using training examples with different scales and corresponding complete search track data in advance; Or setting the initial parameters of the logistic regression model to zero values or preset priori values, and updating the parameters of the logistic regression model periodically based on the accumulated characteristic value data increment in the solving process of the target solution.
7. Refrigerated vehicle-unmanned aerial vehicle-rider cooperative path planning apparatus taking into account fresh losses, characterized in that it comprises: The parameter definition unit is used for defining path planning parameters of the refrigerated truck, the unmanned aerial vehicle and the rider considering the fresh loss; The model construction unit is used for constructing a path planning model according to the path planning parameters; an initial solution generating unit, configured to generate an initial solution of the path planning model based on a greedy insertion algorithm; The target solution searching unit is used for carrying out local search improvement on the initial solution to obtain a target solution; And the delivery scheduling unit is used for rescheduling the refrigerated truck, the unmanned aerial vehicle and the rider to cooperatively execute fresh-keeping delivery service according to the target.
8. An electronic device comprising a processor and a memory; the memory is used for storing programs; The processor executing the program implements the method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the storage medium stores a program that is executed by a processor to implement the method of any one of claims 1 to 6.

Description

Refrigerator car-unmanned aerial vehicle-rider cooperative path planning method considering fresh loss Technical Field The application relates to the technical field of path planning, in particular to a refrigerator car-unmanned aerial vehicle-rider collaborative path planning method considering fresh loss. Background With the rapid development of electronic commerce and new retail sales, the demand for instant delivery of fresh products has increased dramatically. Fresh products (such as vegetables, fruits, aquatic products, meats, etc.) have the biological characteristics of perishability, vulnerability, and short shelf life, and the quality thereof decays with time during circulation. Fresh supply chains play a vital role in preserving perishable product quality. However, current fresh distribution does not substantially take into account the freshness of the product, resulting in unstable freshness of the product received by the user. Disclosure of Invention In view of this, the embodiment of the application provides a method for planning a cooperative path of a refrigerated vehicle, an unmanned aerial vehicle and a rider, which considers fresh loss, and related equipment, so as to improve and stabilize the arrival freshness of fresh product delivery. An aspect of an embodiment of the present application provides a refrigerated vehicle-unmanned aerial vehicle-rider cooperative path planning method considering fresh loss, the method including the steps of: defining path planning parameters of a refrigerated vehicle, an unmanned aerial vehicle and a rider considering fresh loss; constructing a path planning model according to the path planning parameters; Generating an initial solution of the path planning model based on a greedy insertion algorithm; Performing local search improvement on the initial solution to obtain a target solution; and cooperatively executing fresh-keeping delivery service by the refrigerated truck, the unmanned aerial vehicle and the rider according to the target unscheduled refrigerated truck. In some embodiments, the defining the path planning parameters of the refrigerated truck, the unmanned aerial vehicle, the rider taking into account the fresh loss comprises the steps of: Constructing a directed graph And defines the following parameters: Fresh distribution service provider has a central warehouse Virtual endpoint for a mobile deviceA group of prepositioned bins close to customer pointsVirtual endpoint for a mobile deviceThe service provider has a set of orders, each order having a customer's discharge locationTime windowThe time window includes the earliest time of arrivalAnd the latest arrival timeService timeAnd parcel weightWhereinIndex for customer collection, a central warehouse is configured with a set of refrigerated vehiclesAnd a group of unmanned aerial vehiclesEach front-mounted binEquipped with a corresponding group of ridersThe rider fleet beingFront-mounted binPosition and number of (a) is predetermined; Respectively show refrigerator car Rider(s)And unmanned aerial vehicleDefining the straight line flight of the unmanned aerial vehicle, and calculating the Euclidean distance between any two nodes when the unmanned aerial vehicle runsWhen the refrigerator car and the rider are running, the Manhattan distance is calculatedIt is assumed that the time of arrival of the daily fresh product at the central bin is recorded asIt is defined that the fresh product is completely fresh at this time, the freshness loss rate when the fresh product is stored in the center warehouse and the front warehouse is set to α1, the freshness loss rate when the fresh product is stored in the refrigerating equipment of the refrigerator car is set to α2, the freshness loss rate when the fresh product is stored in the heat insulation boxes of the unmanned aerial vehicle and the rider is set to α3, and α1< α2< α3. In some embodiments, the constructing a path planning model according to the path planning parameters includes the steps of: The constructing the objective function of the path planning model comprises: ; ; ; ; ; ; Wherein min is the minimization function, the total cost Comprising a refrigerator carRider(s)And unmanned aerial vehicleIs to be transported at a cost of (2)And freshness loss。 In some embodiments, the greedy-insertion-based algorithm generates an initial solution for the path-planning model, comprising the steps of: Constructing a first gradient route, setting a planned route to use all the refrigerated vehicles according to the path planning model, and adding a front bin distribution task for each refrigerated vehicle in sequence; initializing available routes of the unmanned aerial vehicle and the rider, and inserting each customer to be distributed into a certain position in the route of the unmanned aerial vehicle or the rider at the lowest insertion cost to obtain the initial solution, wherein the load limit, the maximum flight distance limit of the unmanned aer