VLSA: プラグアンドプレイ安全制約層を備えた視覚-言語-行動モデル
VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
VLAモデルに制御バリア関数ベースの安全制約層を追加し、指示追従性能を保ちつつ衝突回避を改善する手法を提案し、SafeLIBEROベンチマークで評価した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Songqiao Hu, Zeyi Liu, Shuang Liu, Jun Cen, Zihan Meng, Shihefeng Wang, Xiang Li, Xiao He
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves over 50% improvement in obstacle avoidance rate while substantially increasing the task success rate by nearly 10%. All benchmark datasets, code, and supplementary materials are publicly available at https://vlsa-aegis.github.io/.
