AnySkill: 対話型エージェントのためのオープン語彙物理スキル学習
AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents
模倣学習で獲得した原子動作を、CLIP類似度を報酬とする高レベル方策で組み合わせ、未知のテキスト指示に応じた物理的に自然な人間動作を生成する階層的手法を提案。
著者: Jieming Cui, Tengyu Liu, Nian Liu, Yaodong Yang, Yixin Zhu, Siyuan Huang
分類: cs.CV, cs.RO
原文アブストラクト
Traditional approaches in physics-based motion generation, centered around imitation learning and reward shaping, often struggle to adapt to new scenarios. To tackle this limitation, we propose AnySkill, a novel hierarchical method that learns physically plausible interactions following open-vocabulary instructions. Our approach begins by developing a set of atomic actions via a low-level controller trained via imitation learning. Upon receiving an open-vocabulary textual instruction, AnySkill employs a high-level policy that selects and integrates these atomic actions to maximize the CLIP similarity between the agent's rendered images and the text. An important feature of our method is the use of image-based rewards for the high-level policy, which allows the agent to learn interactions with objects without manual reward engineering. We demonstrate AnySkill's capability to generate realistic and natural motion sequences in response to unseen instructions of varying lengths, marking it the first method capable of open-vocabulary physical skill learning for interactive humanoid agents.
