敵対的強化学習による故障に強いロバスト制御
Fault-Aware Robust Control via Adversarial Reinforcement Learning
関節故障のケースを敵対的に学習させる強化学習フレームワークを提案し、シミュレーションのみで訓練して実機に直接展開できることを示した。
著者: Fan Yang, Chao Yang, Di Guo, Huaping Liu, Fuchun Sun
分類: cs.RO, cs.LG
原文アブストラクト
Robots have limited adaptation ability compared to humans and animals in the case of damage. However, robot damages are prevalent in real-world applications, especially for robots deployed in extreme environments. The fragility of robots greatly limits their widespread application. We propose an adversarial reinforcement learning framework, which significantly increases robot robustness over joint damage cases in both manipulation tasks and locomotion tasks. The agent is trained iteratively under the joint damage cases where it has poor performance. We validate our algorithm on a three-fingered robot hand and a quadruped robot. Our algorithm can be trained only in simulation and directly deployed on a real robot without any fine-tuning. It also demonstrates exceeding success rates over arbitrary joint damage cases.
