cs.ROMar 5, 2026

UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data

Authors: Sizhe Yang, Yiman Xie, Zhixuan Liang, Yang Tian, Jia Zeng, Dahua Lin, Jiangmiao Pang

Organizations: Shanghai AI Laboratory · The Chinese University of Hong Kong · Zhejiang University · The University of Hong Kong · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Grasping is a fundamental capability for robots to interact with the physical world. Humans, equipped with two hands, autonomously select appropriate grasp strategies based on the shape, size, and weight of objects, enabling robust grasping and subsequent manipulation. In contrast, current robotic grasping remains limited, particularly in multi-strategy settings. Although substantial efforts have targeted parallel-gripper and single-hand grasping, dexterous grasping for bimanual robots remains underexplored, with data being a primary bottleneck. Achieving physically plausible and geometrically conforming grasps that can withstand external wrenches poses significant challenges. To address these issues, we introduce UltraDexGrasp, a framework for universal dexterous grasping with bimanual robots. The proposed data-generation pipeline integrates optimization-based grasp synthesis with planning-based demonstration generation, yielding high-quality and diverse trajectories across multiple grasp strategies. With this framework, we curate UltraDexGrasp-20M, a large-scale, multi-strategy grasp dataset comprising 20 million frames across 1,000 objects. Based on UltraDexGrasp-20M, we further develop a simple yet effective grasp policy that takes point clouds as input, aggregates scene features via unidirectional attention, and predicts control commands. Trained exclusively on synthetic data, the policy achieves robust zero-shot sim-to-real transfer and consistently succeeds on novel objects with varied shapes, sizes, and weights, attaining an average success rate of 81.2% in real-world universal dexterous grasping. To facilitate future research on grasping with bimanual robots, we open-source the data generation pipeline at https://github.com/InternRobotics/UltraDexGrasp.

Figures & tables

Fig. 2 : Overview of data generation pipeline. 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.
Fig. 3 : Hand contact points for various grasp strategies. Different grasp strategies select distinct fingertip contact points, which are used to compute energy terms in the optimization process of grasp synthesis.
Fig. 4 : Overview of the policy architecture. 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.
BenchmarkObject SizeDP3DexGraspNetOurs
Seen ObjectsSmall41.745.678.8
Medium54.372.084.3
Large48.5-90.4
Unseen ObjectsSmall37.445.676.9
Medium50.172.085.8
Large48.1-87.5
TABLE I : Results on simulation benchmarks. The success rates (%) of each policy are reported. The proposed grasp policy trained on UltraDexGrasp-20M demonstrates strong generalization to diverse objects and consistently outperforms the baselines. The best results are highlighted in bold .
Fig. 5 : The variation in performance with growing amounts of training data. The performance of the policy consistently improves as the volume of data increases.
 w/o Dist. Pred.w/o Uni. Attn.Ours
Success Rate (%)73.568.284.0
TABLE II : Ablation study on policy design choices. The success rates (%) are reported. Both the bounded Gaussian distribution prediction and the unidirectional attention mechanism significantly improve performance.
Fig. 6 : Real-world experiment setup. We employ two UR5e robots, two XHand, and two eye-on-base Azure Kinect DK cameras. A variety of objects are collected for testing.
Object SizeDP3DexGraspNetOurs
Small37.351.372.0
Medium56.073.382.2
Large46.7-89.3
Average46.762.381.2
TABLE III : Results on real-world benchmarks. The success rates (%) are reported. The proposed grasp policy trained on UltraDexGrasp-20M demonstrates robust sim-to-real transfer and consistently outperforms the baselines.
More in this topic

Robotic Grasping

Robotic grasping studies how robots perceive, plan, and execute stable, task-appropriate contacts with objects across varied shapes and conditions.

See all 311 papers

Explore similar work

CardsList
Apr 8, 2026

BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes

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, consisting of a large-scale bimanual dexterous grasp dataset and a novel learning-based framework. For dataset construction, we propose a novel bimanual grasp synthesis pipeline to efficiently annotate physically feasible data. 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 9.53 million annotated grasp data. Based on this dataset, we further introduce a novel learning-based dexterous grasping generation framework. The framework lies in two key designs: a bimanual coordination module and a geometry-size-adaptive grasp generation strategy to generate coordinated and high-quality grasps on unseen objects. Extensive experiments conducted in both simulation and real world demonstrate the superior performance of our proposed data synthesis pipeline and learned generative framework.

Mu Lin, Yi-Lin Wei, Jiaxuan Chen +7

Sun Yat-sen University · Peking University · Tsinghua University

Robotic GraspingDexterous ManipulationBimanual Robotic ManipulationSynthetic Data Generation for Robotics
AskPDF
Aug 11, 2026

Learning Cooperative Bimanual Dexterous Grasp of Large Objects with Tactile Sensing

Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation. However, most existing studies focus on sequential manipulation rather than cooperative grasping, and methods addressing such bimanual tasks have largely been limited to simulation. These limitations stem from the difficulty of acquiring full 3D object models and generating physically plausible grasping actions. To fill this gap, we propose a real-world bimanual grasping framework that includes: a multimodal dataset capturing joint angles, visual observations and force signals; a Denoising Diffusion Probabilistic Model (DDPM)-based module that generates joint-level grasp configurations from segmented point clouds; and an execution strategy that integrates motion planning with online grasp refinement to ensure physical stability and feasibility. Our approach enables the synthesis of executable bimanual grasps from single-view inputs, reducing dependence on complete 3D object models and ensuring stable real-world performance. Experiments on a dual-arm robot demonstrate high success rates across unseen objects with varying geometries and poses, and ablation studies confirm the contributions of key components of our system.

Ziming Li, Mingxuan Wu, Jiaqi Zhang +4

School of Computer Science, The University of Auckland, Auckland 1010, New Zealand · College of Computer Science, Chongqing University, Chongqing 401331, China · College of Electronic and Information Engineering, Southwest University, Chongqing 400715, China

Robotic GraspingBimanual Robotic Manipulation
AskPDF
Jan 31, 2026

DiffMorphGrasp: A Diffusion Framework Conditioned on Hand Morphology for Cross-Embodiment Grasp Generation

As robots are deployed across diverse environments, manipulation tasks require robot hands with different morphologies to satisfy varying task requirements, hardware capabilities, and cost constraints. However, transferring grasping policies learned on one robot hand to another with a different morphology remains a fundamental challenge due to variations in kinematic structures and degrees of freedom across embodiments. To address these limitations, we propose DiffMorphGrasp, the first diffusion-based framework that incorporates hand morphology information into the generative process for cross-embodiment dexterous grasping. The proposed approach maps grasps from diverse robotic hands into a reference hand pose, providing a common space for learning. Grasp generation is then continuously conditioned on structured representations of hand kinematics, encoded as graphs derived from hand configurations, together with object geometry. In addition, we introduce a loss function that computes joint-level errors over the hand kinematic structure to constrain the generated grasps during training. To evaluate DiffMorphGrasp, we construct a new benchmark for assessing grasp generation performance across robot hands with different morphologies. Extensive experiments demonstrate that DiffMorphGrasp achieves strong zero-shot generalization to unseen hand morphologies, enabling scalable cross-embodiment grasp deployment. Project page: https://georgewuzy.github.io/DiffMorphGrasp-website

Zhiyuan Wu, Xiangyu Zhang, Zhuo Chen +3

Department of Engineering, King’s College London, Strand, London, WC2R 2LS, United Kingdom · Imperial College London, London, SW7 2AZ, United Kingdom

Robotic GraspingCross-Embodiment Robot LearningZero-Shot Robotic ManipulationDiffusion Models
AskPDF