Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation

2026-09-01

AI Summary

为解决高精度机械组装中的接触问题，提出Facet-0模型，结合多模态表示学习和强化学习预测动作后果，实现亚毫米级精准操作。

Abstract

Real-world robotic assembly at sub-millimeter tolerances demands spatial precision, compliant interaction, and robustness to contact failures. We present Facet-0, a robotic foundation model that predicts and values the contact consequences of its actions. Facet-0 unifies multimodal representation learning and reinforcement learning (RL) post-training around a joint action-wrench proposal: a causal wrench history is aligned with vision-language semantics and kinematic state, and flow matching generates each action chunk together with the future wrist-wrench profile it is expected to induce. Deployment rollouts train a distributional Action-Wrench Critic to distinguish motions with similar task progress but different contact outcomes, while phase-aware rewards and contact-selective credit concentrate policy improvement on decisive interactions. To accommodate part-specific dynamics, a lightweight bounded actor reuses the frozen representation for on-robot adaptation; RL remains defined over executable Cartesian actions, while an auxiliary wrench head preserves predictive, non-commanded action-contact coupling. Trained on ManuFacet-1K, a 1,000-hour force-synchronized corpus spanning three embodiments and multiple manufacturing cells, the bounded task-adapted system reaches 82% mean success on five sub-millimeter computer-assembly tasks, compared with 15% for the strongest baseline, with 0.5 mm placement accuracy and 50 ms command latency.

Problem

• Robotic Assembly
• Sub-millimeter Tolerances
• Contact-rich Manipulation
• Precision
• Compliance

Innovation

• contact-rich precise manipulation
• multimodal representation learning
• reinforcement learning
• action-wrench proposal
• phase-aware rewards