mlsanityData to 7 Oct 2026

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning

arXiv 2304.00464 ↗First posted 2 Apr 2023cs.RO cs.CVcited by 101

Not on the map. Why?

Abstract (arXiv)

We propose a novel, object-agnostic method for learning a universal policy for dexterous object grasping from realistic point cloud observations and proprioceptive information under a table-top setting, namely UniDexGrasp++. To address the challenge of learning the vision-based policy across thousands of object instances, we propose Geometry-aware Curriculum Learning (GeoCurriculum) and Geometry-aware iterative Generalist-Specialist Learning (GiGSL) which leverage the geometry feature of the task and significantly improve the generalizability. With our proposed techniques, our final policy shows universal dexterous grasping on thousands of object instances with 85.4% and 78.2% success rate on the train set and test set which outperforms the state-of-the-art baseline UniDexGrasp by 11.7% and 11.3%, respectively.

Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). Builds on 58 of its 74 references that are in the map. First posted on arXiv 2 Apr 2023.

Builds on

58 of 74 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2016Generative Adversarial Imitation Learningcited by 1,576
  7. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  8. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  10. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  11. 2019Solving Rubik's Cube with a Robot Handcited by 699
  12. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
38 more
  1. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  2. 2018Learning Dexterous In-Hand Manipulationcited by 643
  3. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  4. 2018Behavioral Cloning from Observationcited by 482
  5. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  6. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  7. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  8. 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 268
  9. 2020Decoupling Representation Learning from Reinforcement Learningcited by 263
  10. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 245
  11. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 241
  12. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  13. 2021Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenescited by 213
  14. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  15. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  16. 2022Masked World Models for Visual Controlcited by 169
  17. 2021A System for General In-Hand Object Re-Orientationcited by 155
  18. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  19. 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policycited by 117
  20. 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 109
  21. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 107
  22. 2022In-Hand Object Rotation via Rapid Motor Adaptationcited by 102
  23. 2021Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Cluttercited by 94
  24. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 90
  25. 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 83
  26. 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 80
  27. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
  28. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 78
  29. 2019State Alignment-based Imitation Learningcited by 73
  30. 2021UMPNet: Universal Manipulation Policy Network for Articulated Objectscited by 64
  31. 2022GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRFcited by 64
  32. 2022TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baselinecited by 55
  33. 2022End-to-End Affordance Learning for Robotic Manipulationcited by 54
  34. 2021Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learningcited by 49
  35. 2017Divide-and-Conquer Reinforcement Learningcited by 46
  36. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 46
  37. 2023PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observationscited by 40
  38. 2021RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Imagescited by 38

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 43; 2025: 31; 2026: 20.

101 papers.

Sort:

By area:

  1. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  2. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 157
  3. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  4. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 102
  5. 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videoscited by 94
  6. 2025DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Graspingcited by 87
  7. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 78
  8. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 69
  9. 2023ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenescited by 68
  10. 2024DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptionscited by 60
  11. 2024GraspXL: Generating Grasping Motions for Diverse Objects at Scalecited by 59
  12. 2025ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learningcited by 56
38 more
  1. 2024RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulationcited by 55
  2. 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 53
  3. 2024DexDiffuser: Generating Dexterous Grasps with Diffusion Modelscited by 46
  4. 2024DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenescited by 41
  5. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
  6. 2024CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementcited by 40
  7. 2025VLA-R1: Enhancing Reasoning in Vision-Language-Action Modelscited by 38
  8. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
  9. 2024RealDex: Towards Human-like Grasping for Robotic Dexterous Handcited by 33
  10. 2024ViViDex: Learning Vision-based Dexterous Manipulation from Human Videoscited by 33
  11. 2023UGG: Unified Generative Graspingcited by 30
  12. 2025HUMOTO: A 4D Dataset of Mocap Human Object Interactionscited by 30
  13. 2024SemGrasp: Semantic Grasp Generation via Language Aligned Discretizationcited by 29
  14. 2024BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objectscited by 29
  15. 2025Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstrationcited by 27
  16. 2024SUGAR: Pre-training 3D Visual Representations for Roboticscited by 26
  17. 2024EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Viewscited by 26
  18. 2024PhysPart: Physically Plausible Part Completion for Interactable Objectscited by 24
  19. 2024Cross-Embodiment Dexterous Grasping with Reinforcement Learningcited by 24
  20. 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learnerscited by 23
  21. 2023SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulationcited by 22
  22. 2024Lessons from Learning to Spin "Pens"cited by 22
  23. 2024ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusioncited by 21
  24. 2024A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulationcited by 20
  25. 2024AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulationcited by 20
  26. 2025Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomycited by 19
  27. 2025DexVLG: Dexterous Vision-Language-Grasp Model at Scalecited by 19
  28. 2023Grasp Multiple Objects with One Handcited by 18
  29. 2024PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitationcited by 18
  30. 2024DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulationcited by 15
  31. 2025AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiencycited by 14
  32. 2024HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactionscited by 13
  33. 2024Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrationscited by 12
  34. 2024SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesiscited by 12
  35. 2025MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulationcited by 12
  36. 2025Towards Embodiment Scaling Laws in Robot Locomotioncited by 12
  37. 2024Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Controlcited by 11
  38. 2025Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactionscited by 10

50 most cited of 101 All 101 (JSON)