外观
论文arXiv 2608.179622 个月前
PRISM：具有多模态感知的高精度富接触真实世界工业技能数据集
原文链接：PRISM: Precision and contact-rich Real-world Industrial Skill dataset with Multimodal sensing（arXiv 2608.17962 · 发布日期：2026-08-18）
PRISM: Precision and contact-rich Real-world Industrial Skill dataset with Multimodal sensing
PRISM面向工业装配的高精度富接触学习，收集同步多模态遥操作数据，并在真实制造操作上提供基准。
核心要点
- 现有数据多偏向短时低接触任务，难覆盖工业装配所需的力/触觉调节。
- PRISM记录同步多视角RGB-D、力/扭矩、触觉与机器人状态测量。
- 数据涵盖25余项操作、5000余条轨迹和45小时遥操作演示。
- 数据集已开源，旨在作为高精度工业约束下多模态感知与控制基准。
验证范围与局限：验证范围为真实世界工业操作数据集，摘要未描述具体学习算法的评测。
英文摘要 (Abstract)
Recent progress in robotic learning has been fueled by large-scale datasets collected in everyday environments. However, most existing datasets emphasize short-horizon, low-contact tasks such as pick-and-place, and therefore do not capture the precision control, force/torque or tactile regulation, and multimodal feedback required for industrial assembly. To address this gap, we introduce PRISM, a large-scale multimodal dataset for contact-rich industrial operations. The dataset spans more than 25 manipulation tasks (e.g., electronic components plug/unplug, conveyor-based sorting) and covers diverse mechanical constraints. PRISM includes more than 5,000 trajectories totaling 45 hours of teleoperated demonstrations, recorded using synchronized multi-view RGB-D, force/torque, tactile, and robot-state measurements. In contrast to datasets collected in household or laboratory settings, PRISM provides a realistic benchmark for multimodal perception and control under high-precision industrial constraints, and serves as a foundation for contact-rich, generalizable manipulation in real-world manufacturing environments. The dataset is open-sourced at: https://tengbo-yu.github.io/PRISM/
作者：Tengbo Yu, Jiahao Wu, Hanning Wang, Rui Chen, Chuanhou Liu, Chuang Sun, Hangxin Liu
来源
本页事实对应的公开页面，以原文为准。