MatchingPolicy: 対応関係を考慮したポリシーによる物体横断的な文脈内学習の実現
MatchingPolicy: Correspondence-Aware Policy Enables Cross-Object In-Context Learning
デモとシーンの対応関係を明示的に分離し、密な意味的対応に基づいてロボットの動作を条件付ける拡散ポリシーを導入。未見の物体やカテゴリへの汎化性能を向上させた。
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: Qijin She, Hanyang Yu, Zeming Li, Ping Tan
分類: cs.RO
原文アブストラクト
In-context imitation learning enables few-shot policy generalization but struggles to maintain performance on unseen objects and novel scenarios. To address this, we introduce MatchingPolicy, a correspondence-driven framework that explicitly decouples demonstration-to-scene matching from policy learning. Central to our method is a correspondence-aware diffusion policy that conditions robotic actions directly on dense semantic correspondences. This architectural separation resolves the inherent conflict between correspondence identification and action adaptation, enabling robust out-of-distribution transfer. Our framework integrates vision foundation models with a novel two-stage matching algorithm to dynamically establish reliable correspondences. Extensive evaluations on RLBench and real-world manipulation tasks confirm that MatchingPolicy achieves superior few-shot performance, generalizing reliably across unseen object instances and semantic categories.