Humanoid-DART: 拡散ガイドによるリラベリングと追跡を用いたヒューマノイド移動操作
Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking
少数のデモから自己教師ありで行動レパートリーを拡張し、拡散モデルによる軌道生成と強化学習を組み合わせてヒューマノイドの移動操作ポリシーを学習する手法を提案した。
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: Pranav Debbad, Kanish Thiagarajan, Victor Dhédin, Shafeef Omar, Majid Khadiv
分類: cs.RO
原文アブストラクト
Imitating human demonstrations has emerged as a dominant paradigm for learning humanoid loco-manipulation policies. However, scaling these approaches remains challenging due to the high cost of collecting diverse demonstrations and the need for continual human intervention to correct policy failures. In this paper, we present a self-supervised framework that bootstraps from sparse demonstrations and progressively expands its behavioral repertoire, enabling the learning of a goal-conditioned policy that automatically explores the goal space with minimal expert supervision. Our approach combines diffusion-based trajectory generation with reinforcement learning, where the latter is used to track goal-conditioned trajectories produced by the diffusion model for a range of loco-manipulation skills. Through extensive ablation studies and comparisons with state-of-the-art methods, we demonstrate the effectiveness of our framework on multiple humanoid loco-manipulation skills.
