全方位視点とクロスモダリティ知識蒸留による移動ロボットの視覚ベース方策の強化
Enhancing Vision-Based Policies with Omni-View and Cross-Modality Knowledge Distillation for Mobile Robots
全方位深度画像を持つ教師方策から、軽量な単眼カメラ方策へ知識蒸留を行い、シーン転移性とナビゲーション性能を向上させる手法を提案した。
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: Kai Li, Shiyu Zhao
分類: cs.RO
原文アブストラクト
Vision-based policies are widely applied in robotics for tasks such as manipulation and locomotion. On lightweight mobile robots, however, they face a trilemma of limited scene transferability, restricted onboard computation resources, and sensor hardware cost. To address these issues, we propose a knowledge distillation approach that transfers knowledge from an information-rich, appearance invariant omniview depth policy to a lightweight monocular policy. The key idea is to train the student not only to mimic the expert actions but also to align with the latent embeddings of the omni view depth teacher. Experiments demonstrate that omni-view and depth inputs improve the scene transfer and navigation performance, and that the proposed distillation method enhances the performance of a singleview monocular policy, compared with policies solely imitating actions. Real world experiments further validate the effectiveness and practicality of our approach. Code will be released publicly.
