LUCID: 想像上のダイナミクスによる潜在スキル統合制御による長期的ヒューマノイド移動操作
LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation
長期的なヒューマノイドの移動操作タスクを解決するため、学習したダイナミクスモデルを用いた想像上のロールアウトを通じて再利用可能なスキルを計画する階層的モデルベース強化学習フレームワークを提案した。
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: Cheng Guo, Mingzhe Ni, Angelo Cangelosi, Arash Ajoudani
分類: cs.LG, cs.RO
原文アブストラクト
Long-horizon humanoid loco-manipulation requires composing versatile whole-body skills and reliable high-level decision making. Existing methods often coordinate pretrained skills with scripted planners, finite-state machines or task-specific model-free policies, restricting their ability to handle complex task sequences. To address this limitation, we propose \textbf{LUCID}, a hierarchical model-based reinforcement learning framework that plans over reusable skills through imagined rollouts of a learned dynamics model. LUCID first trains a structured latent-conditioned low-level policy via adversarial imitation and then freezes it while jointly learning a high-level policy and macro-dynamics world model. The world model predicts the temporally extended state transitions induced by latent decisions, enabling high-level policy optimization through imagined rollouts. We evaluate our framework across various simulated multi-object rearrangement scenarios. Experimental results show that LUCID improves the full-task success and partial-completion rates compared to prior baseline methods, demonstrating its effectiveness in complex sequential loco-manipulation tasks.