ABNet: 安全でスケーラブルなロボット学習のための注意バリアネットワーク
ABNet: Attention BarrierNet for Safe and Scalable Robot Learning
バリア関数ベースの安全学習をスケーラブルにするため、複数のバリアヘッドが異なる特徴に注目するAttention BarrierNetを提案し、安全性を理論保証しつつ障害物回避や操作、自動運転で堅牢性を示した。
著者: Wei Xiao, Tsun-Hsuan Wang, Daniela Rus
分類: cs.LG, cs.RO, cs.SY, eess.SY
原文アブストラクト
Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Barrier-based method is one of the dominant approaches for safe robot learning. However, this method is not scalable, hard to train, and tends to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address these challenges, we propose a novel Attention BarrierNet (ABNet) that is scalable to build larger foundational safe models in an incremental manner. Each head of BarrierNet in the ABNet could learn safe robot control policies from different features and focus on specific part of the observation. In this way, we do not need to one-shotly construct a large model for complex tasks, which significantly facilitates the training of the model while ensuring its stable output. Most importantly, we can still formally prove the safety guarantees of the ABNet. We demonstrate the strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving, with results showing much better robustness and guarantees over existing models.
