GuidedAttention: OODロバストなロボット操作のための解釈可能かつ修正可能な視覚的注意機構
GuidedAttention: Interpretable and Correctable Visual Attention for OOD-Robust Robot Manipulation via Imitation Learning
視覚運動ポリシーに解釈可能で修正可能な注意キーポイントを中間表現として導入し、ユーザーが初期化時に修正可能な模倣学習フレームワークを提案。シミュレーションと実世界でOOD条件下での操作性能を向上させた。
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: Masaki Murooka, Ryoichi Nakajo, Keisuke Shirai, Tomohiro Motoda, Hanbit Oh, Ryo Hanai, Yukiyasu Domae
分類: cs.RO
原文アブストラクト
End-to-end visuomotor policies provide little opportunity for humans to understand or correct the policy's visual attention. We propose GuidedAttention, a visuomotor imitation learning framework that introduces interpretable and correctable visual attention as an explicit intermediate representation. Task-relevant attention keypoints are predicted from camera images and condition a diffusion-based action policy. Users can inspect and optionally correct selected keypoints once at rollout initialization, after which the corrected attention is automatically propagated throughout execution by a tracking module. Experiments in simulation and the real world demonstrate that GuidedAttention consistently improves robot manipulation performance, particularly under positional and appearance out-of-distribution (OOD) conditions. https://mmurooka.github.io/guided-attention-project-page
