发表机构
Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出机器人基础模型Facet-0，通过联合动作-力提议等技术，在ManuFacet-1K上训练后，五项亚毫米计算机装配任务平均成功率达82%，远超基线的15%，实现精密接触型机器人装配。
AI 中文摘要
亚毫米公差的实际机器人装配需要空间精度、柔顺交互以及对接触故障的鲁棒性。本文提出Facet-0，一种可预测并评估其动作接触后果的机器人基础模型。Facet-0围绕联合动作-力提议统一多模态表征学习与强化学习（RL）后训练：将因果力历史与视觉-语言语义及运动学状态对齐，通过流匹配生成每个动作块及其预期会引发的未来腕力曲线。部署部署训练分布型动作-力评论器，以区分任务进度相似但接触结果不同的动作；同时，相位感知奖励和接触选择性信用将策略改进集中于决定性交互。为适配部件特定动力学，轻量有界动作器复用冻结表征进行机器人上适配；RL仍在可执行笛卡尔动作上定义，而辅助力头保留预测性、非命令动作-接触耦合。在ManuFacet-1K（一个覆盖三个实体和多个制造单元的1000小时力同步语料库）上训练后，该有界任务适配系统在五项亚毫米计算机装配任务上达到82%的平均成功率，最强基线仅为15%，且具备0.5毫米放置精度和50毫秒命令延迟。
英文摘要
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.
CommentsProject page: https://pine-lab-ntu.github.io/facet-0/
