mlsanityData to 14 Oct 2026

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

arXiv 2303.00938 ↗First posted 2 Mar 2023cs.RO cs.CVcited by 124

Not on the map. Why?

Abstract (arXiv)

In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. The goal is to grasp and lift up objects in high-quality and diverse ways and generalize across hundreds of categories and even the unseen. Inspired by successful pipelines used in parallel gripper grasping, we split the task into two stages: 1) grasp proposal (pose) generation and 2) goal-conditioned grasp execution. For the first stage, we propose a novel probabilistic model of grasp pose conditioned on the point cloud observation that factorizes rotation from translation and articulation. Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud.For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution. Note that it is very challenging to learn this highly generalizable grasp policy that only takes realistic inputs without oracle states. We thus propose several important innovations, including state canonicalization, object curriculum, and teacher-student distillation. Integrating the two stages, our final pipeline becomes the first to achieve universal generalization for dexterous grasping, demonstrating an average success rate of more than 60% on thousands of object instances, which significantly outperforms all baselines, meanwhile showing only a minimal generalization gap.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). Builds on 49 of its 70 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

49 of 70 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2016Density estimation using Real NVPcited by 2,042
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  10. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  11. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  12. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
37 more
  1. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  3. 2019Solving Rubik's Cube with a Robot Handcited by 734
  4. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  5. 2018Learning Dexterous In-Hand Manipulationcited by 687
  6. 2019Learning by Cheatingcited by 383
  7. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
  8. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 218
  9. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 206
  10. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 206
  11. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 197
  12. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 197
  13. 2021A System for General In-Hand Object Re-Orientationcited by 165
  14. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
  15. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  16. 2019ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imagingcited by 147
  17. 2021ContactOpt: Optimizing Contact to Improve Graspscited by 139
  18. 2022DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulationcited by 137
  19. 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 113
  20. 2019Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Researchcited by 98
  21. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 95
  22. 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 89
  23. 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
  24. 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 85
  25. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 84
  26. 2021Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimatorcited by 71
  27. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 67
  28. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  29. 2022GenDexGrasp: Generalizable Dexterous Graspingcited by 56
  30. 2022TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baselinecited by 55
  31. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 51
  32. 2021Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learningcited by 50
  33. 2020Deep Differentiable Grasp Planner for High-DOF Gripperscited by 39
  34. 2021RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Imagescited by 39
  35. 2022Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interactioncited by 24
  36. 2022Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentationcited by 22
  37. 2022Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrationscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 16; 2024: 36; 2025: 34; 2026: 38.

124 papers.

Sort:

By area:

  1. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 213
  2. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 162
  3. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 137
  4. 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 107
  5. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 102
  6. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 82
  7. 2023PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interactioncited by 76
  8. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 71
  9. 2023ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenescited by 69
  10. 2025ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learningcited by 66
  11. 2024DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptionscited by 62
  12. 2024GraspXL: Generating Grasping Motions for Diverse Objects at Scalecited by 60
38 more
  1. 2024RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulationcited by 58
  2. 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 55
  3. 2025RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learningcited by 54
  4. 2024DexDiffuser: Generating Dexterous Grasps with Diffusion Modelscited by 48
  5. 2024CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementcited by 44
  6. 2024DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenescited by 44
  7. 2023PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observationscited by 42
  8. 2023Dexterous Functional Graspingcited by 39
  9. 2024Hand-Object Interaction Pretraining from Videoscited by 39
  10. 2024ViViDex: Learning Vision-based Dexterous Manipulation from Human Videoscited by 35
  11. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 35
  12. 2025Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstrationcited by 34
  13. 2023UGG: Unified Generative Graspingcited by 30
  14. 2024SemGrasp: Semantic Grasp Generation via Language Aligned Discretizationcited by 29
  15. 2024Cross-Embodiment Dexterous Grasping with Reinforcement Learningcited by 27
  16. 2025DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awarenesscited by 26
  17. 2025SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrationscited by 25
  18. 2024Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representationscited by 24
  19. 2025Dex1B: Learning with 1B Demonstrations for Dexterous Manipulationcited by 24
  20. 2023GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Graspingcited by 23
  21. 2024An Economic Framework for 6-DoF Grasp Detectioncited by 23
  22. 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learnerscited by 23
  23. 2023SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulationcited by 22
  24. 2024Local Policies Enable Zero-shot Long-horizon Manipulationcited by 22
  25. 2024A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulationcited by 21
  26. 2024GEARS: Local Geometry-aware Hand-object Interaction Synthesiscited by 20
  27. 2025Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomycited by 20
  28. 2025DexVLG: Dexterous Vision-Language-Grasp Model at Scalecited by 20
  29. 2023Grasp Multiple Objects with One Handcited by 18
  30. 2023DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Fieldcited by 17
  31. 2025DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human Referencescited by 17
  32. 2025AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiencycited by 16
  33. 2024Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrationscited by 15
  34. 2026SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulationcited by 15
  35. 2026Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulationcited by 14
  36. 2023SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handoverscited by 13
  37. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactionscited by 13
  38. 2023MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervisioncited by 12

50 most cited of 124 All 124 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
  2. 2024UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
  3. 2026Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field ↗
  4. 2025Learning Adaptive Dexterous Grasping from Single Demonstrations
  5. 2026CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes
  6. 2023GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models
  7. 2025DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
  8. 2026GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion