HumanVLA：視覚言語指示による物理ヒューマノイドの物体再配置
HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
視覚と言語の指示に従って物理ヒューマノイドが物体を再配置するためのVLAモデルを、教師方策の蒸留により構築し、新データセットで有効性を示した。
著者: Xinyu Xu, Yizheng Zhang, Yong-Lu Li, Lei Han, Cewu Lu
分類: cs.RO
原文アブストラクト
Physical Human-Scene Interaction (HSI) plays a crucial role in numerous applications. However, existing HSI techniques are limited to specific object dynamics and privileged information, which prevents the development of more comprehensive applications. To address this limitation, we introduce HumanVLA for general object rearrangement directed by practical vision and language. A teacher-student framework is utilized to develop HumanVLA. A state-based teacher policy is trained first using goal-conditioned reinforcement learning and adversarial motion prior. Then, it is distilled into a vision-language-action model via behavior cloning. We propose several key insights to facilitate the large-scale learning process. To support general object rearrangement by physical humanoid, we introduce a novel Human-in-the-Room dataset encompassing various rearrangement tasks. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed approach.
