手首情報を統合した触覚表現による接触の多いマニピュレーション
WiTac: Wrist-Informed Tactile Representations for Contact-Rich Manipulation
触覚信号と手首視覚・手の動きを事前学習で深く融合し、VLAポリシーに組み込むことで接触の多い操作タスクの成功率を向上させた研究。
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: Haotian He, Yiyang Chen, Congsheng Xu, Wenchao Yue, Mingze Ye, Shuai Chen, Yi Yang, Yaping Li, Haonan Wang, Weinan E, Wenzhao Lian, Zhijie Deng
分類: cs.RO
原文アブストラクト
Similar tactile contacts can call for different corrections depending on the configuration of the hand, object and target. Rather than supplying touch and wrist vision separately, fusing them before policy injection better grounds tactile features in visual context, yielding more accurate contact representations. We introduce Wrist-Informed Tactile Representations (WiTac), a pretrained encoder that learns such representations before action generation. Pretrained on nearly 300 hours of SharpaDex data, WiTac deeply fuses tactile signals with hand motion and wrist views into a comprehensive contact representation. Conditioning downstream VLA policies (GR00T N1.7 and $π_{0.5}$) on WiTac substantially improves task success over vision-only base policies across four contact-rich manipulation tasks (+28.8% and +15.0% on average), and further outperforms a wrist-free tactile encoder by 18.8% and 7.5%, respectively. Offline analyses further show that incorporating wrist vision yields more accurate contact descriptors, stronger joint task-contact discrimination, greater feature stability under tactile noise, and clearer action-direction readout from similar contacts.Project page: https://wrist-informed-tactile-representations.github.io/.
