BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes
Mu Lin, Yi-Lin Wei, Jiaxuan Chen, Yuhao Lin, Shuoyu Chen, Jiangran Lyu, Jiayi Chen, Yansong Tang, He Wang, Wei-Shi Zheng

TL;DR
This paper introduces BiDexGrasp, a large-scale bimanual grasp dataset and a novel generation model, advancing robotic dexterous grasping across diverse object geometries and sizes.
Contribution
It presents a new dataset construction pipeline and a generative framework for coordinated bimanual grasps adaptable to various object sizes and shapes.
Findings
Constructed a dataset with 9.7 million grasp annotations for 6351 objects.
Demonstrated the effectiveness of the dataset and model in simulation and real-world tests.
Abstract
Bimanual dexterous grasping is a fundamental and promising area in robotics, yet its progress is constrained by the lack of comprehensive datasets and powerful generation models. In this work, we propose BiDexGrasp, consists of a large-scale bimanual dexterous grasp dataset and a novel generation model. For dataset, we propose a novel bimanual grasp synthesis pipeline to efficiently annotate physically feasible data for dataset construction. This pipeline addresses the challenges of high-dimensional bimanual grasping through a two-stage synthesis strategy of efficient region-based grasp initialization and decoupled force-closure grasp optimization. Powered by this pipeline, we construct a large-scale bimanual dexterous grasp dataset, comprising 6351 diverse objects with sizes ranging from 30 to 80 cm, along with 9.7 million annotated grasp data. Based on this dataset, we further…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
