Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration
This addresses the challenge of enabling more human-like adaptive control for humanoid robots, though it appears incremental by building on existing whole-body control architectures.
The paper tackles the problem of limited autonomous interaction in humanoid robot control by proposing Humanoid-VLA, a framework integrating language, egocentric vision, and motion control, which achieves enhanced contextual awareness for object interaction and environment exploration tasks.
This paper addresses the limitations of current humanoid robot control frameworks, which primarily rely on reactive mechanisms and lack autonomous interaction capabilities due to data scarcity. We propose Humanoid-VLA, a novel framework that integrates language understanding, egocentric scene perception, and motion control, enabling universal humanoid control. Humanoid-VLA begins with language-motion pre-alignment using non-egocentric human motion datasets paired with textual descriptions, allowing the model to learn universal motion patterns and action semantics. We then incorporate egocentric visual context through a parameter efficient video-conditioned fine-tuning, enabling context-aware motion generation. Furthermore, we introduce a self-supervised data augmentation strategy that automatically generates pseudoannotations directly derived from motion data. This process converts raw motion sequences into informative question-answer pairs, facilitating the effective use of large-scale unlabeled video data. Built upon whole-body control architectures, extensive experiments show that Humanoid-VLA achieves object interaction and environment exploration tasks with enhanced contextual awareness, demonstrating a more human-like capacity for adaptive and intelligent engagement.