mlsanityData to 7 Oct 2026

DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects

arXiv 2305.05706 ↗First posted 9 May 2023cs.RO cs.CV cs.LGcited by 64

Not on the map. Why?

Abstract (arXiv)

To enable general-purpose robots, we will require the robot to operate daily articulated objects as humans do. Current robot manipulation has heavily relied on using a parallel gripper, which restricts the robot to a limited set of objects. On the other hand, operating with a multi-finger robot hand will allow better approximation to human behavior and enable the robot to operate on diverse articulated objects. To this end, we propose a new benchmark called DexArt, which involves Dexterous manipulation with Articulated objects in a physical simulator. In our benchmark, we define multiple complex manipulation tasks, and the robot hand will need to manipulate diverse articulated objects within each task. Our main focus is to evaluate the generalizability of the learned policy on unseen articulated objects. This is very challenging given the high degrees of freedom of both hands and objects. We use Reinforcement Learning with 3D representation learning to achieve generalization. Through extensive studies, we provide new insights into how 3D representation learning affects decision making in RL with 3D point cloud inputs. More details can be found at https://www.chenbao.tech/dexart/.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 57 of its 68 references that are in the map. First posted on arXiv 9 May 2023.

Builds on

57 of 68 references.

References · 57

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  8. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  9. 2018Learning Dexterous In-Hand Manipulationcited by 643
  10. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  11. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  12. 2018PCN: Point Completion Networkcited by 382
38 more
  1. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 313
  2. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  3. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  4. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  5. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  6. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  7. 2019Category-Level Articulated Object Pose Estimationcited by 158
  8. 2021A System for General In-Hand Object Re-Orientationcited by 155
  9. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 152
  10. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  11. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  12. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  13. 2013Data-Driven Grasp Synthesis - A Surveycited by 104
  14. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstrationcited by 92
  15. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 90
  16. 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
  17. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 83
  18. 2018PointNetGPD: Detecting Grasp Configurations from Point Setscited by 80
  19. 2018Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Costcited by 79
  20. 2022From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperationcited by 79
  21. 2021VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objectscited by 78
  22. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 78
  23. 2018Deep Part Induction from Articulated Object Pairscited by 66
  24. 2021UMPNet: Universal Manipulation Policy Network for Articulated Objectscited by 64
  25. 2019S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenescited by 51
  26. 2021Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learningcited by 49
  27. 2021O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learningcited by 46
  28. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 46
  29. 2021Act the Part: Learning Interaction Strategies for Articulated Object Part Discoverycited by 45
  30. 2021Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulationcited by 44
  31. 2015Learning Contact-Rich Manipulation Skills with Guided Policy Searchcited by 37
  32. 2020Visual Identification of Articulated Object Partscited by 36
  33. 2016Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstrationcited by 35
  34. 2022Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrationscited by 34
  35. 2022Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Cloudscited by 31
  36. 2019kPAM-SC: Generalizable Manipulation Planning using KeyPoint Affordance and Shape Completioncited by 27
  37. 2020Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimationcited by 25
  38. 2020Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Cloudscited by 24

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 15; 2025: 20; 2026: 25.

64 papers.

Sort:

By area:

  1. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 115
  2. 2023General In-Hand Object Rotation with Vision and Touchcited by 87
  3. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  4. 2025RoboArena: Distributed Real-World Evaluation of Generalist Robot Policiescited by 63
  5. 2024Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learningcited by 56
  6. 2023Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensingcited by 51
  7. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Trainingcited by 43
  8. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 41
  9. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
  10. 2025VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Modelscited by 34
  11. 2023Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objectscited by 33
  12. 2024ViViDex: Learning Vision-based Dexterous Manipulation from Human Videoscited by 33
38 more
  1. 2023UGG: Unified Generative Graspingcited by 30
  2. 2025DexMachina: Functional Retargeting for Bimanual Dexterous Manipulationcited by 30
  3. 2024Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasetscited by 23
  4. 2025Dex1B: Learning with 1B Demonstrations for Dexterous Manipulationcited by 23
  5. 2024Lessons from Learning to Spin "Pens"cited by 22
  6. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
  7. 2024Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Modelscited by 22
  8. 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
  9. 2025Dense Policy: Bidirectional Autoregressive Learning of Actionscited by 19
  10. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  11. 2024Point Cloud Models Improve Visual Robustness in Robotic Learnerscited by 13
  12. 2025H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learningcited by 13
  13. 2025FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistencycited by 13
  14. 2024Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillationcited by 12
  15. 2025FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokenscited by 9
  16. 2025CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusioncited by 8
  17. 2025DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Roboticscited by 8
  18. 2025Spatial-Temporal Aware Visuomotor Diffusion Policy Learningcited by 8
  19. 2025Can Vision-Language Models Answer Face to Face Questions in the Real-World?cited by 7
  20. 2024SM3: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objectscited by 5
  21. 2026Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulationcited by 5
  22. 2026One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policiescited by 5
  23. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  24. 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editingcited by 4
  25. 2024Dexterous Functional Pre-Grasp Manipulation with Diffusion Policycited by 3
  26. 2024Dexterous Manipulation Based on Prior Dexterous Grasp Pose Knowledgecited by 2
  27. 2025VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulationcited by 2
  28. 2025Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equationcited by 2
  29. 2026X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learningcited by 2
  30. 2026Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learningcited by 2
  31. 2026Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversalcited by 2
  32. 2026Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Handscited by 2
  33. 2025Task-Oriented Human Grasp Synthesis via Context- and Task-Aware Diffuserscited by 1
  34. 2026Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometrycited by 1
  35. 2026High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matchingcited by 1
  36. 2024KineDepth: Utilizing Robot Kinematics for Online Metric Depth Estimationcited by 0
  37. 2025DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulationcited by 0
  38. 2026KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKVcited by 0

50 most cited of 64 All 64 (JSON)