MotionDisco: 極限ヒューマノイド移動操作のための動作発見
MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
テレオペや人間のデモを使わずに、LLMガイドの進化探索と軌道最適化を組み合わせて、長期的な接触リッチなヒューマノイド移動操作動作をゼロから発見し、実機に転移するフレームワークを提案。
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: Ilyass Taouil, Michal Ciebelski, Shafeef Omar, Haizhou Zhao, Angela Dai, Aaron M. Johnson, Majid Khadiv
分類: cs.RO
原文アブストラクト
We present MotionDisco, a framework that discovers contact-rich, long-horizon humanoid loco-manipulation motions from scratch, without relying on teleoperation or motion retargeting from human demonstrations. This is challenging because the space of possible contact interactions grows combinatorially with the task horizon and the number of objects in the scene. MotionDisco enables rapid discovery of novel motions by coupling a large language model (LLM) guided evolutionary search over sequences of interactions with an efficient sequential kinodynamic trajectory optimizer and pruning strategy, enabling the rapid discovery of novel skills. Through extensive ablation studies, we show that our LLM-guided search discovers successful whole-body trajectories across several challenging long-horizon tasks. Finally, by training reinforcement learning tracking policies on the discovered trajectories, we transfer the motions to a real humanoid robot. This is the first work to discover and deploy long-horizon humanoid loco-manipulation skills entirely through automated evolutionary search. Supplementary videos of the experiments are available at: https://youtu.be/DHiVz34QYlw.
