DemoGrasp: Universal Dexterous Grasping from a Single Demonstration

[Website] [arXiv]

DemoGrasp is a framework for learning universal dexterous grasping policies via reinforcement learning (RL) augmented with a single demonstration. It achieves state-of-the-art performance across diverse robotic hand embodiments and transfers effectively to real robots, demonstrating strong generalization.

Citation

If you find our work useful, please consider citing us!

@article{yuan2025demograsp,
  title={DemoGrasp: Universal Dexterous Grasping from a Single Demonstration},
  author={Yuan, Haoqi and Huang, Ziye and Wang, Ye and Mao, Chuan and Xu, Chaoyi and Lu, Zongqing},
  journal={arXiv preprint arXiv:2509.22149},
  year={2025}
}