Vehicle-UAV collaborative delivery path optimization method based on deep reinforcement learning

By adopting a deep reinforcement learning method in vehicle-drone collaborative distribution path optimization, combining dynamic logistics distribution time function and path optimization model, the problems of dynamic demand and time-varying characteristics of traffic flow are solved, efficient and flexible distribution path optimization is achieved, and distribution efficiency and time reliability are significantly improved.

CN119168528BActive Publication Date: 2025-03-28NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
2 Cites 0 Cited by

Patent Information

Application Number
CN202411658940.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-11-20
Publication Date
2025-03-28
Estimated Expiration
2044-11-20

AI Technical Summary

Technical Problem

The existing vehicle-drone collaborative distribution path optimization algorithm is difficult to effectively handle the time-varying characteristics of dynamic demands and traffic flows, resulting in inefficient delivery efficiency and unreliable time in complex and changing urban environments.

Method used

Using a method based on deep reinforcement learning, a dynamic logistics distribution time function and a vehicle-drone fleet low-altitude logistics collaborative distribution path optimization model are established, and the distribution path and time are dynamically adjusted in combination with real-time traffic flow data.

Benefits of technology

It significantly improves the efficiency of vehicle-drone collaborative delivery path optimization, can adaptively handle random changes in order quantity and location, update path planning in real time, shorten delivery time, and adapt to complex urban environments.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses a vehicle-UAV collaborative delivery path optimization method based on deep reinforcement learning, which relates to the field of path optimization technology and aims to solve the logistics distribution uncertainty problem caused by dynamic customer demands and time-varying characteristics of traffic flow in urban terminal delivery. First, considering the change of vehicle speed under different traffic flow conditions, a dynamic logistics delivery time function is established; secondly, with the delivery timeliness that meets customer needs as the goal, a vehicle-UAV collaborative delivery path optimization model is constructed; then, according to the dynamic delivery time and dynamic customer needs, a reward function with demand expiration penalty is designed; finally, a deep reinforcement learning algorithm is used to solve the dynamic path optimization model. The method of the present invention can dynamically adjust the allocation strategy, improve the efficiency of path planning and delivery timeliness, and significantly improve the overall service level of urban terminal delivery.
Need to check novelty before this filing date? Find Prior Art