mlsanityData to 7 Oct 2026

UMPNet: Universal Manipulation Policy Network for Articulated Objects

arXiv 2109.05668 ↗First posted 13 Sep 2021cs.CV cs.ROcited by 64

Not on the map. Why?

Abstract (arXiv)

We introduce the Universal Manipulation Policy Network (UMPNet) -- a single image-based policy network that infers closed-loop action sequences for manipulating arbitrary articulated objects. To infer a wide range of action trajectories, the policy supports 6DoF action representation and varying trajectory length. To handle a diverse set of objects, the policy learns from objects with different articulation structures and generalizes to unseen objects or categories. The policy is trained with self-guided exploration without any human demonstrations, scripted policy, or pre-defined goal conditions. To support effective multi-step interaction, we introduce a novel Arrow-of-Time action attribute that indicates whether an action will change the object state back to the past or forward into the future. With the Arrow-of-Time inference at each interaction step, the learned policy is able to select actions that consistently lead towards or away from a given state, thereby, enabling both effective state exploration and goal-conditioned manipulation. Video is available at https://youtu.be/KqlvcL9RqKM

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

21 of 37 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  3. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  4. 2019Learning Latent Plans from Playcited by 310
  5. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  6. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  7. 2019Category-Level Articulated Object Pose Estimationcited by 158
  8. 2016Learning to Poke by Poking: Experiential Learning of Intuitive Physicscited by 152
  9. 2019ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imagingcited by 145
  10. 2019Planning with Goal-Conditioned Policiescited by 144
  11. 2019TossingBot: Learning to Throw Arbitrary Objects with Residual Physicscited by 131
  12. 2018Grounded Human-Object Interaction Hotspots from Videocited by 128
9 more
  1. 2017Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matchingcited by 124
  2. 2020EGO-TOPO: Environment Affordances from Egocentric Videocited by 111
  3. 2019Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrationscited by 104
  4. 2020ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theorycited by 70
  5. 2018Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstrationcited by 60
  6. 2021Act the Part: Learning Interaction Strategies for Articulated Object Part Discoverycited by 45
  7. 2021Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulationcited by 44
  8. 2019Learning Hybrid Object Kinematics for Efficient Hierarchical Planning Under Uncertaintycited by 9
  9. 2019Motion Reasoning for Goal-Based Imitation Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 18; 2024: 21; 2025: 7; 2026: 6.

64 papers.

Sort:

By area:

  1. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  2. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 157
  3. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 102
  4. 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 101
  5. 2023GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fieldscited by 99
  6. 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
  7. 2023DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objectscited by 64
  8. 2021AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactionscited by 56
  9. 2024RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesiscited by 55
  10. 2022End-to-End Affordance Learning for Robotic Manipulationcited by 54
  11. 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulationcited by 46
  12. 2023PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observationscited by 40
38 more
  1. 2023Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objectscited by 33
  2. 2024A3VLM: Actionable Articulation-Aware Vision Language Modelcited by 33
  3. 2022K-VIL: Keypoints-based Visual Imitation Learningcited by 27
  4. 2023HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulationcited by 27
  5. 2022Category-Independent Articulated Object Tracking with Factor Graphscited by 24
  6. 2024PhysPart: Physically Plausible Part Completion for Interactable Objectscited by 24
  7. 2023Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusionscited by 23
  8. 2024Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representationscited by 23
  9. 2024DNAct: Diffusion Guided Multi-Task 3D Policy Learningcited by 22
  10. 20233D Implicit Transporter for Temporally Consistent Keypoint Discoverycited by 20
  11. 2024A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulationcited by 20
  12. 2024AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulationcited by 20
  13. 2024Composable Part-Based Manipulationcited by 17
  14. 2024Survey on Modeling of Human-made Articulated Objectscited by 14
  15. 2024Open-World Reinforcement Learning over Long Short-Term Imaginationcited by 13
  16. 2025AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learningcited by 12
  17. 2025ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulationcited by 10
  18. 2024Part-Guided 3D RL for Sim2Real Articulated Object Manipulationcited by 9
  19. 2026Articulated 3D Scene Graphs for Open-World Mobile Manipulationcited by 9
  20. 2022The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fieldscited by 8
  21. 2023Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformationcited by 8
  22. 2022Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objectscited by 7
  23. 2023Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmarkcited by 7
  24. 2021Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assemblycited by 6
  25. 2024UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Modelscited by 6
  26. 2025CrayonRobo: Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulationcited by 6
  27. 2023ImageManip: Image-based Robotic Manipulation with Affordance-guided Next View Selectioncited by 5
  28. 2023Learning Part Motion of Articulated Objects Using Spatially Continuous Neural Implicit Representationscited by 5
  29. 2023SAGE: Bridging Semantic and Actionable Parts for GEneralizable Manipulation of Articulated Objectscited by 5
  30. 2024RPMArt: Towards Robust Perception and Manipulation for Articulated Objectscited by 5
  31. 2024HACMan++: Spatially-Grounded Motion Primitives for Manipulationcited by 5
  32. 2022Structure from Action: Learning Interactions for Articulated Object 3D Structure Discoverycited by 4
  33. 2024Ensuring Force Safety in Vision-Guided Robotic Manipulation via Implicit Tactile Calibrationcited by 4
  34. 2022BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environmentcited by 3
  35. 2022H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactionscited by 3
  36. 2023Spatial-Language Attention Policies for Efficient Robot Learningcited by 3
  37. 2024Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Trackingcited by 3
  38. 2024Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulationcited by 3

50 most cited of 64 All 64 (JSON)