[3O3-GS-5] Agents: multi-agents

[3O3-GS-5-05] Multi-agent Reinforcement Learning using Shortest Path Information for Drone Routing Problem

〇Hideki Aoyama¹, Shiyao Ding², Donghui Lin² (1. Panasonic Corporation, 2. Kyoto University)

Keywords:Multi-agent path finding, Multi-agent reinforcement learning, Vehicle routing problem

Safe and efficient drone delivery services require navigational controls and flight space restrictions to avoid collisions and reduce damage from unexpected falls.This paper formulates this optimization problem and proposes it as Drone Routing Problem (DRP).And we propose a multi-agent reinforcement learning method using analytically calculated shortest path information, and show its effectiveness through experiments.