ArXiv arXiv Code Code








UltraDexGrasp:

Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data



ICRA 2026

UltraDexGrasp is a framework for universal dexterous grasping with bimanual robots.

The proposed data generation pipeline integrates an optimization-based grasp synthesizer with a planning-based demonstration generation module, and supports multiple grasp strategies, including two-finger pinch, three-finger tripod, whole-hand grasp, and bimanual grasp.

Trained on data produced by this pipeline, the policy demonstrates robust zero-shot sim-to-real transfer and strong generalization to novel objects with varied shapes, sizes, and weights.

Robo3R Demo

Method


Model

We first collect diverse object assets and import the objects and the robot URDF files into the simulator. An optimization-based grasp synthesizer is then used to generate feasible grasps, from which the preferred grasp is selected. Finally, motion planning is employed to generate demonstration trajectories.


Module

The proposed grasp policy takes point clouds as input, encodes them using a point encoder, aggregates scene features via unidirectional attention, and predicts control commands. The policy supports multiple grasp strategies and improves generalization across diverse objects.

Real-World Deployment


Our Team

Sizhe Yang1,2
Yiman Xie1,3
Zhixuan Liang1,4
Yang Tian1,5
Jia Zeng1
Dahua Lin1,2
Jiangmiao Pang1
1Shanghai AI Laboratory, 2The Chinese University of Hong Kong, 3Zhejiang University, 4The University of Hong Kong, 5Peking University

If you have any questions, please contact Sizhe Yang.

BibTeX


@article{yang2026ultradexgrasp,
  title={UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data},
  author={Yang, Sizhe and Xie, Yiman and Liang, Zhixuan and Tian, Yang and Zeng, Jia and Lin, Dahua and Pang, Jiangmiao},
  journal={arXiv preprint arXiv:2603.05312},
  year={2026}
}