知識駆動型模倣学習：多様な条件への汎化を実現する
Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions
外部の構造的意味知識を活用して物体表現を抽象化し、少ない実演データでロボットマニピュレーションの汎化性能を高める知識駆動型模倣学習を提案した。
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: Zhuochen Miao, Jun Lv, Hongjie Fang, Yang Jin, Cewu Lu
分類: cs.RO
原文アブストラクト
Imitation learning has emerged as a powerful paradigm in robot manipulation, yet its generalization capability remains constrained by object-specific dependencies in limited expert demonstrations. To address this challenge, we propose knowledge-driven imitation learning, a framework that leverages external structural semantic knowledge to abstract object representations within the same category. We introduce a novel semantic keypoint graph as a knowledge template and develop a coarse-to-fine template-matching algorithm that optimizes both structural consistency and semantic similarity. Evaluated on three real-world robotic manipulation tasks, our method achieves superior performance, surpassing image-based diffusion policies with only one-quarter of the expert demonstrations. Extensive experiments further demonstrate its robustness across novel objects, backgrounds, and lighting conditions. This work pioneers a knowledge-driven approach to data-efficient robotic learning in real-world settings. Code and more materials are available on https://knowledge-driven.github.io/.
