DeepMNavigate：局所・大域衝突回避を統合した深層強化学習によるマルチロボットナビゲーション
DeepMNavigate: Deep Reinforced Multi-Robot Navigation Unifying Local & Global Collision Avoidance
各ロボットの運動情報マップから局所・大域情報を3層CNNで処理し、深層強化学習で密集環境での最適なナビゲーション方策を学習する手法を提案した。
著者: Qingyang Tan, Tingxiang Fan, Jia Pan, Dinesh Manocha
分類: cs.MA, cs.AI, cs.RO
原文アブストラクト
We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning (DRL). Our approach uses local and global information for each robot from motion information maps. We use a three-layer CNN that takes these maps as input to generate a suitable action to drive each robot to its goal position. Our approach is general, learns an optimal policy using a multi-scenario, multi-state training algorithm, and can directly handle raw sensor measurements for local observations. We demonstrate the performance on dense, complex benchmarks with narrow passages and environments with tens of agents. We highlight the algorithm's benefits over prior learning methods and geometric decentralized algorithms in complex scenarios.
