キーポイント模倣学習の汎化能力、設計選択、および限界について
On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning
RGBベースの模倣学習の汎化を改善するため、視覚基盤モデルによるキーポイント表現を用いた模倣学習(KIL)の設計選択を検討し、実機2000回以上の試行で評価。KILはRGBベースライン(47%)を上回る75%の成功率を達成し、S2拡散モデルと同等の性能を示した。
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: Thomas Lips, Marco Moletta, Michael C. Welle, Danica Kragic, Francis wyffels
分類: cs.RO
原文アブストラクト
RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representations to improve generalization for robotic manipulation. Visual foundation models enable one-shot extraction of keypoints to provide such representation. However, it remains unclear how to integrate them into imitation learning optimally and when they outperform alternative representations. We combine approaches from previous works on keypoint imitation learning (KIL) and investigate several design choices to provide practical guidelines. Using over 2000 real-world rollouts, we also assess the generalization capabilities of KIL to unseen objects and scene variations. KIL achieves a 75% overall success rate across five tasks, significantly outperforming the RGB baseline (47%) and performing on par with S2-diffusion (73%). Finally, we explore the limitations of the foundation models used for keypoint extraction and extend KIL to tasks with multiple object instances. Our results confirm KIL as a data-efficient approach for robot learning, though it does not outperform alternative representations and inherits limitations of the foundation models used for keypoint extraction. All rollout videos, demonstrations, and results are available at https://kil-manipulation.github.io/.
