経路誘導型CBF-QP修復による安全な視覚言語行動モデル
Route-Guided CBF-QP Repair for Safe Vision-Language-Action Models
VLAモデルの行動をCBF-QP安全フィルタで補正する際、障害物を迂回して元の軌道に復帰できるよう経路誘導項を加えるポストホック修復手法を提案し、衝突回避とタスク成功率を改善した。
著者: Chan Park, Sunwoo Hong, Kirak Kim, Yoonjeong Park, Alexander W. Olson, Ali Pesaranghader
分類: cs.AI, cs.RO
原文アブストラクト
Vision-language-action (VLA) models can generate task-oriented robot actions, but they do not guarantee safe execution in obstacle-rich manipulation scenes. Although CBF-QP safety filters can locally project unsafe actions into a safe set, such correction may push the robot away from the learned task trajectory and leave the VLA policy without a reliable recovery direction. We propose Route-Guided CBF-QP Repair, a post-hoc repair module that uses the short-horizon action chunk predicted by the VLA to detect blocked nominal trajectories and generate entry-exit-rejoin guidance around obstacles. The selected route is added to the CBF-QP objective as a soft guidance term, while the CBF safety constraint remains hard. On SafeLIBERO, our method improves collision avoidance, task success, and SafeSuccess compared with AEGIS. Our project page is available at GitHub.