HABILIS Brain 0: Geometry-Change Supervision for Vision-Language-Action and Residual Flow Recovery

2026-09-21

AI Summary

研究通过几何变化监督和多阶段训练方法，解决了视觉-语言-动作策略中缺乏对操作变化描述的问题，提高了机器人任务成功率。

Abstract

Vision-language-action policies benefit from geometric supervision, but current-frame geometry alone does not explicitly describe the changes associated with manipulation. This design is motivated by the goal of learning an embodiment-agnostic visual interface that can be pretrained across robot and egocentric video before robot-specific action alignment. We introduce Geometry-Change VLA (GC-VLA), which learns to predict multiview future-current geometry-change tokens from current observations. Offline frame pairs define a nominal 0.5-second prediction horizon; future observations are used only to construct training targets. Stage 1 trains a geometry-change vision-language model (GC-VLM). Stage 2 introduces a continuous ActionExpert and aligns it with robot actions while stopping action-flow gradients at the VLM interface. Stage 3 enables these gradients to update the trainable VLM components jointly with the ActionExpert. Stage 4 freezes GC-VLA and applies Geometry-Conditioned Residual Flow (GCRF), using a binary intervention router and a single bounded residual velocity policy learned from closed-loop feedback. GC-VLA achieves 95.20% success on LIBERO, and GC-VLA with GCRF achieves 99.55%. Inference uses current observations and the learned GC representation without executing the offline target encoders.

Problem

• Geometry-Change
• Vision-Language-Action
• Residual Flow Recovery
• Geometric Supervision
• Manipulation

Innovation

• Geometry-Change VLA
• ActionExpert
• Geometry-Conditioned Residual Flow
• multiview future-current geometry-change tokens