TouchScale: 500 Hours of Human Vision and Touch for Visual-T
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. Chinese robotics — Hardware and sensing: TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning. TouchScale is a large-scale human vision-touch dataset that enables scaling benefits in both perception and robotic manipulation. It uses a unified sensor setup and provides high-quality data for training robots to perfo… Machine Heart — Robotics on WeChat: TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning. TouchScale is a 500-hour human visual-tactile dataset collected with unified sensors and synchronization, showing scaling benefits in both perception and robotic manipulation. The dataset enables cross-sensor generalizat…
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported duration: 500 hours · Basis not reported · Differing source assertions
“把人类双手的「手感」移植给机器人：500 小时真实操作数据，任务成功率翻番”
Exact source · revision 1jiqizhixin
“把人类双手的「手感」移植给机器人：500 小时真实操作数据”
Exact source · revision 3Source owner not reported
Reported quantity · Reported duration: 500 hours · Basis not reported · Differing source assertions
“TouchScale 包含 500 小时人类双手视觉-触觉同步数据，全部由同一套穿戴式系统采集，同步记录头部 RGB-D、双腕 RGB 和双手全手触觉信号。”
Exact source · revision 1jiqizhixin
Reported quantity · Reported success rate: 22.5 percent · Basis not reported · Differing source assertions
“无需人类动作标签，也不把人手动作映射到机器人，只用人类视触觉数据做 mid-training，机器人 4 个真机接触任务的平均成功率从 22.5% 升到 57.5%。”
Exact source · revision 1jiqizhixin
“无需人类动作标签，也不把人手动作映射到机器人，只用人类视触觉数据做 mid-training，机器人 4 个真机接触任务的平均成功率从 22.5% 升到 57.5%。”
Exact source · revision 3Source owner not reported
Reported quantity · Reported success rate: 57.5 percent · Basis not reported · Differing source assertions
“无需人类动作标签，也不把人手动作映射到机器人，只用人类视触觉数据做 mid-training，机器人 4 个真机接触任务的平均成功率从 22.5% 升到 57.5%。”
Exact source · revision 1jiqizhixin
“无需人类动作标签，也不把人手动作映射到机器人，只用人类视触觉数据做 mid-training，机器人 4 个真机接触任务的平均成功率从 22.5% 升到 57.5%。”
Exact source · revision 3Source owner not reported
Artifact availability · paper: available
“题目：TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning 论文链接： https://arxiv.org/abs/2610.10288 项目主页：https://touch-scale.github.io/ 数据集地址：https://huggingface.co/datasets/2077AIDataFoundation/TouchScale 500 小时触觉数据，难的不只是「采得多」 对 TouchScale 来说，真正的难点不是把小时数简单堆到 500，而是在同一套传感器、同一套同步与采集流程下持续扩展。”
Exact source · revision 1jiqizhixin
“题目：TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning 论文链接：https://arxiv.org/abs/2610.10288 项目主页：https://touch-scale.github.io/ 数据集地址：https://huggingface.co/datasets/2077AIDataFoundation/TouchScale 500 小时触觉数据，难的不只是「采得多」 对 TouchScale 来说，真正的难点不是把小时数简单堆到 500，而是在同一套传感器、同一套同步与采集流程下持续扩展。”
Exact source · revision 3Source owner not reported
Artifact availability · dataset: available
“题目：TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning 论文链接： https://arxiv.org/abs/2610.10288 项目主页：https://touch-scale.github.io/ 数据集地址：https://huggingface.co/datasets/2077AIDataFoundation/TouchScale 500 小时触觉数据，难的不只是「采得多」 对 TouchScale 来说，真正的难点不是把小时数简单堆到 500，而是在同一套传感器、同一套同步与采集流程下持续扩展。”
Exact source · revision 1jiqizhixin
“题目：TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning 论文链接：https://arxiv.org/abs/2610.10288 项目主页：https://touch-scale.github.io/ 数据集地址：https://huggingface.co/datasets/2077AIDataFoundation/TouchScale 500 小时触觉数据，难的不只是「采得多」 对 TouchScale 来说，真正的难点不是把小时数简单堆到 500，而是在同一套传感器、同一套同步与采集流程下持续扩展。”
Exact source · revision 3Source owner not reported
Reported quantity · Reported duration: 500 hours · Basis not reported · Differing source assertions
“TouchScale 包含 500 小时人类双手视觉-触觉同步数据，全部由同一套穿戴式系统采集，同步记录头部 RGB-D、双腕 RGB 和双手全手触觉信号。”
Exact source · revision 3Source owner not reported
Reported quantity · Reported duration: 500 hours · Basis not reported · Differing source assertions
“题目：TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning 论文链接：https://arxiv.org/abs/2610.10288 项目主页：https://touch-scale.github.io/ 数据集地址：https://huggingface.co/datasets/2077AIDataFoundation/TouchScale 500 小时触觉数据，难的不只是「采得多」 对 TouchScale 来说，真正的难点不是把小时数简单堆到 500，而是在同一套传感器、同一套同步与采集流程下持续扩展。”
Exact source · revision 3Source owner not reported
Reported quantity · Reported duration: 30 hours · Basis not reported · Differing source assertions
“此前公开的人类视觉-触觉数据集大多不足 30 小时；如果直接把多个小数据集拼在一起，不同硬件和采集流程会与数据规模一起变化，很难把规模本身的影响单独拿出来研究。”
Exact source · revision 3Source owner not reported
Reported quantity · taxel: 880 other · Basis not reported
“与已有公开的人类视觉-触觉数据相比，TouchScale 不仅将规模扩展到 500 小时，还始终保持统一的传感器和采集流程，并提供双手全手触觉采集，每只手包含 880 个 taxel。”
Exact source · revision 3Source owner not reported
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Hardware and sensingSignalTouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning
TouchScale is a large-scale human vision-touch dataset that enables scaling benefits in both perception and robotic manipulation. It uses a unified sensor setup and provides high-quality data for training robots to perform contact-intensive tasks with improved success rates.
- Machine Heart — Robotics on WeChatSignalTouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning
TouchScale is a 500-hour human visual-tactile dataset collected with unified sensors and synchronization, showing scaling benefits in both perception and robotic manipulation. The dataset enables cross-sensor generalization and improves robot task success rates from 22.5% to 57.5% through mid-training. The study highlights the potential of large-scale visual-tactile data to enhance embodied AI systems.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).