密集・動的環境におけるロボット運動計画のためのアドバンテージ付きアクター・クリティックアルゴリズム
An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios
連続行動空間での複雑な運動計画に適応させたアドバンテージ付きアクター・クリティック強化学習を提案し、密集・動的障害物環境で従来の価値ベースRLより高速かつ安定に収束し、成功率と到達時間を改善した。
著者: Chengmin Zhou, Bingding Huang, Pasi Fränti
分類: cs.RO, cs.AI
原文アブストラクト
Intelligent robots provide a new insight into efficiency improvement in industrial and service scenarios to replace human labor. However, these scenarios include dense and dynamic obstacles that make motion planning of robots challenging. Traditional algorithms like A* can plan collision-free trajectories in static environment, but their performance degrades and computational cost increases steeply in dense and dynamic scenarios. Optimal-value reinforcement learning algorithms (RL) can address these problems but suffer slow speed and instability in network convergence. Network of policy gradient RL converge fast in Atari games where action is discrete and finite, but few works have been done to address problems where continuous actions and large action space are required. In this paper, we modify existing advantage actor-critic algorithm and suit it to complex motion planning, therefore optimal speeds and directions of robot are generated. Experimental results demonstrate that our algorithm converges faster and stable than optimal-value RL. It achieves higher success rate in motion planning with lesser processing time for robot to reach its goal.
