HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid

TL;DR

HumanVLA enables a humanoid robot to perform general object rearrangement tasks using vision and language, leveraging a teacher-student framework and a new dataset for training and evaluation.

Contribution

We introduce HumanVLA, a novel framework combining reinforcement learning and behavior cloning for vision-language guided object rearrangement by humanoids, supported by a new comprehensive dataset.

Findings

Effective in diverse rearrangement tasks

Outperforms baseline methods

Demonstrates generalization to unseen objects

Abstract

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.