触覚で動作を洗練させるタイミングを学ぶ器用把持VTLAポリシー
TipDex-VTLA: Learning When to Refine Actions with Touch for Dexterous Manipulation
視覚の信頼度推定と触覚予測の照合を組み合わせ、照明変化下でも触覚を使って実行中の動作を補正するVTLAポリシーを提案し、実機4タスクで高い成功率を示した。
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: Xudi Ge, Yepeng Liu, Haifeng Liu, Enze Shi, Liangqi Zhang, Yongchao Xu
分類: cs.RO, cs.AI
原文アブストラクト
Changes in illumination can induce action drift in dexterous manipulation even when the physical state remains unchanged. Although existing vision--tactile--language--action (VTLA) policies incorporate tactile feedback, when and how touch refines actions under changing visual conditions remains challenging. We introduce \textbf{TipDex-VTLA}, a VTLA policy that combines estimated visual action reliability and tactile forecast verification to regulate execution-time refinement. Specifically, Visual Action Sensitivity Estimation (VASE) learns visual reliability from a frozen reference policy's action sensitivity to illumination perturbations. Tactile Anticipation and Correction during Execution (TACE) compares predicted and measured touch at matched times and combines the resulting discrepancy with visual reliability to gate bounded feature corrections for unexecuted actions. This effectively helps to refine actions under challenging unseen visual conditions. We evaluate TipDex-VTLA on four real-world dexterous manipulation tasks and the UniVTAC simulation benchmark. TipDex-VTLA trained on data collected under normal visual conditions, achieves average full-task success rates of 87.5% (resp. 73.8%) under normal (resp. challenging unseen) lighting in real-world tasks, significantly outperforming some state-of-the-art methods. We will release the collected data and source code.
