We used DexMimicGen to autonomously generate over 20,000 demonstrations for bimanual dexterous robots from just 60 source human demonstrations across 9 tasks, multiple simulators, and the real-world.
Can Sorting
Success Rate: 97.3 ± 0.9%
Coffee
Success Rate: 77.3 ± 0.9%
Pouring
Success Rate: 79.3 ± 0.9%
Tray Lift
Success Rate: 88.7 ± 0.9%
Box Cleanup
Success Rate: 92.0 ± 4.3%
Drawer Cleanup
Success Rate: 76.0 ± 0.0%
Threading
Success Rate: 69.3 ± 1.9%
Transport
Success Rate: 83.3 ± 0.9%
Piece Assembly
Success Rate: 80.7 ± 0.9%
We showcase datasets generated by DexMimicGen across different reset distributions for three tasks in Robosuite below.
Reset Distribution D0
Reset Distribution D1
Reset Distribution D2
Reset Distribution D0
Reset Distribution D1
Reset Distribution D2
Reset Distribution D0
Reset Distribution D1
Reset Distribution D2
Reset Distribution D0
Reset Distribution D1
@inproceedings{jiang2024dexmimicen,
title = {DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning},
author = {Jiang, Zhenyu and Xie, Yuqi and Lin, Kevin and Xu, Zhenjia and Wan, Weikang and Mandlekar, Ajay and Fan, Linxi and Zhu, Yuke},
journal = {arXiv preprint arXiv:2410.24185},
year = {2024}
}
If you have any questions, please feel free to contact Zhenyu Jiang, Ajay Mandelkar, Jim Fan and Yuke Zhu.