Cloak: エンドエフェクタをVLAからマスクすることで実現するゼロショット異機種間操作
Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA
手首カメラ画像からエンドエフェクタをマスクする訓練手法Cloakを提案し、単一グリッパのデータのみで訓練したVLAが、未見の異なるロボット構成へゼロショットで転移できることを示した。
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: Michael Piseno, Guy Tevet, C. Karen Liu
分類: cs.RO
原文アブストラクト
We present Cloak, a training recipe that endows a Vision-Language-Action (VLA) model with zero-shot cross-embodiment transfer by cloaking the end-effector from its own wrist camera. The end-effector occupies a large and consistent region of the wrist view and masking it allows for embodiment-agnostic visual reasoning. Cloak renders a mask in simulation from the robot's known geometry, accurately and in real time, with no segmentation or generative models. During training, we augment the mask so the model generalizes to embodiments unseen at training time. We demonstrate the recipe with Cloak-VLA, a VLA trained with Cloak on a single parallel-jaw gripper dataset. No data of new embodiments is ever collected. Cloak-VLA transfers zero-shot to various unseen embodiments, including another gripper, another arm, and a five-fingered hand, while preserving the source embodiment's performance. By decoupling the wrist view from its own embodiment, Cloak allows data to outlive the hardware it was collected on.
