TouchGuide: 通过触觉引导在推理时操控视觉-触觉策略
TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance
AI总结：
本文提出TouchGuide，一种新的跨策略视觉-触觉融合方法，通过触觉引导在推理时优化预训练的视觉-触觉策略，提升机器人精细接触操作能力。
摘要：
细粒度且接触丰富的操作仍使机器人面临挑战，主要由于触觉反馈的利用不足。为此，我们引入TouchGuide，一种新颖的跨策略视觉-触觉融合范式，在低维动作空间内融合多种模态。具体而言，TouchGuide分两阶段在推理时引导预训练的扩散或流匹配视觉-触觉策略。首先，策略仅使用视觉输入在早期采样中生成粗略且视觉合理的动作。其次，任务特定的接触物理模型（CPM）提供触觉引导以操控和细化动作，确保其符合现实物理接触条件。通过对比学习在有限专家示范上训练，CPM提供触觉感知的可行性评分以引导采样过程向满足物理接触约束的精细动作发展。此外，为促进TouchGuide训练使用高质量且成本效益高的数据，我们引入TacUMI数据收集系统。TacUMI在精度和成本之间取得良好平衡；通过利用刚性指尖，它获得直接触觉反馈，从而收集到可靠的触觉数据。在五个具有挑战性的接触丰富任务，如系鞋带和芯片交接上进行的广泛实验表明，TouchGuide在一致性与显著性上均优于最先进的视觉-触觉策略。
英文摘要：
Fine-grained and contact-rich manipulation remain challenging for robots, largely due to the underutilization of tactile feedback. To address this, we introduce TouchGuide, a novel cross-policy visuo-tactile fusion paradigm that fuses modalities within a low-dimensional action space. Specifically, TouchGuide operates in two stages to guide a pre-trained diffusion or flow-matching visuomotor policy at inference time. First, the policy produces a coarse, visually-plausible action using only visual inputs during early sampling. Second, a task-specific Contact Physical Model (CPM) provides tactile guidance to steer and refine the action, ensuring it aligns with realistic physical contact conditions. Trained through contrastive learning on limited expert demonstrations, the CPM provides a tactile-informed feasibility score to steer the sampling process toward refined actions that satisfy physical contact constraints. Furthermore, to facilitate TouchGuide training with high-quality and cost-effective data, we introduce TacUMI, a data collection system. TacUMI achieves a favorable trade-off between precision and affordability; by leveraging rigid fingertips, it obtains direct tactile feedback, thereby enabling the collection of reliable tactile data. Extensive experiments on five challenging contact-rich tasks, such as shoe lacing and chip handover, show that TouchGuide consistently and significantly outperforms state-of-the-art visuo-tactile policies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
