Data Pyramid: a survey

Data Pyramid of Embodied Manipulation: A Survey

PKU NTU HKUST NUS CUHK HKU Duke UCB GBU NJU SJTU

News

Project updates

Updated the data accumulation charts and refreshed Ego Engineering on GitHub, including Ego2Robot and EgoEngine. Added two new datasets: RekaCS2-10k and RekaDaily-10k.

We open-sourced the website and project. Please use the curated links for dataset downloads. Issues and pull requests are welcome to help the open-source community access data more easily.

Overview

Current coverage

Tasks

Task groups

Dataset Table

Datasets by category and task

Task Data Links Observations Actions # Demos License Citation

Bibliography

@misc{ye2026datapyramid,
      title={Data Pyramid for Embodied Manipulation},
      author={Yifan Ye and Yankai Fu and Yaoxu Lv and Bohan Hou and Jun Cen and Lingdong Kong and Duo Zheng and Tianxing Chen and Jiaming Liu and Ziang Cao and Yunfan Lou and Wei Chow and Xian Sun and Yingshuo Wang and Kuangzhi Ge and Xiaowei Chi and Xidong Zhang and Zhibo Pang and Yiwu Zhong and Sirui Han and Zhihe Lu and Weihao Yuan and Qifeng Chen and Michael Yu Wang and Yao Mu and Ziwei Liu and Jianfei Yang and Ping Luo and Shanghang Zhang},
      year={2026},
      eprint={2607.24744},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2607.24744},
}

Acknowledgement

Acknowledge to UMI-Data-Community and IRMVLab/awesome-robot-learning-from-human-videos.