通过软硬件协同设计，实现高可用触觉数据采集与动态触觉表征学习。
exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation
- 构建可扩展触觉采集装置，支持自校准与多模态感知
- 基于100万帧触觉数据预训练，显著提升触觉动作预测能力
- 适合触觉强化学习、人机共融操作等研究者使用
现有触觉机器人学习面临数据稀缺与稀疏性挑战，且缺乏力反馈机制。为此，我们提出exUMI系统，结合硬件与算法创新：设计可扩展的数据采集装置，集成主动运动捕捉（AR MoCap）与旋转编码器实现鲁棒本体感知，支持模块化视觉-触觉传感与自动校准，达到100%数据可用性。在此基础上，基于超过100万帧触觉数据，提出触觉预测预训练（TPP）框架，通过动作感知的时序触觉预测，捕捉接触动态并缓解触觉稀疏问题。真实世界实验表明，TPP优于传统触觉模仿学习。本工作通过软硬件协同设计，弥合人类触觉直觉与机器人学习之间的差距，开源项目地址：https://silicx.github.io/exUMI。
原文摘要 · Abstract (English)
Tactile-aware robot learning faces critical challenges in data collection and representation due to data scarcity and sparsity, and the absence of force feedback in existing systems. To address these limitations, we introduce a tactile robot learning system with both hardware and algorithm innovations. We present exUMI, an extensible data collection device that enhances the vanilla UMI with robust proprioception (via AR MoCap and rotary encoder), modular visuo-tactile sensing, and automated calibration, achieving 100% data usability. Building on an efficient collection of over 1 M tactile frames, we propose Tactile Prediction Pretraining (TPP), a representation learning framework through action-aware temporal tactile prediction, capturing contact dynamics and mitigating tactile sparsity. Real-world experiments show that TPP outperforms traditional tactile imitation learning. Our work bridges the gap between human tactile intuition and robot learning through co-designed hardware and algorithms, offering open-source resources to advance contact-rich manipulation research. Project page: https://silicx.github.io/exUMI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。