DexDiffuser: Generating Dexterous Grasps with Diffusion Models

2024/02/05 by Zehang Weng, Weng, Zehang, Haofei Lu +5 · 15 citations
Computer Science · #Computability, Logic, AI Algorithms #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2402.02989

openalex publication_date 2024/02/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and the dexterous grasp evaluator DexEvaluator. DexSampler generates high-quality grasps conditioned on object point clouds by iterative denoising of randomly sampled grasps. We also introduce two grasp refinement strategies: Evaluator-Guided Diffusion (EGD) and Evaluator-based Sampling Refinement (ESR). The experiment results demonstrate that DexDiffuser consistently outperforms the state-of-the-art multi-finger grasp generation method FFHNet with an, on average, 9.12% and 19.44% higher grasp success rate in simulation and real robot experiments, respectively. Supplementary materials are available at https://yulihn.github.io/DexDiffuser_page/

Cited by

• FIRMGrasp: A Friction-Informed Risk Margin for Robust Grasp Synthesis
• ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
• OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordance
• Phy-Tac: Toward Human-Like Grasping via Physics-Conditioned Tactile Goals
• Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
• Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields
• ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation
• DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation
• Diffusing Trajectory Optimization Problems for Recovery During Multi-Finger Manipulation
• DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
• DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps
• D3Grasp: Diverse and Deformable Dexterous Grasping for General Objects
• Learning Geometry-Aware Nonprehensile Pushing and Pulling with Dexterous Hands
• First Plan Then Evaluate: Use a Vectorized Motion Planner for Grasping
• Real-Time Iteration Scheme for Diffusion Policy

Related

• DexGrasp-Diffusion: Diffusion-based Unified Functional Grasp Synthesis Method for Multi-Dexterous Robotic Hands
• HGDiffuser: Efficient Task-Oriented Grasp Generation via Human-Guided Grasp Diffusion Models
• DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
• Fast-Grasp'D: Dexterous Multi-finger Grasp Generation Through Differentiable Simulation
• DVGG: Deep Variational Grasp Generation for Dextrous Manipulation