mlsanityData to 7 Oct 2026

DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation

arXiv 2505.21864 ↗First posted 28 May 2025cs.ROcited by 58

Not on the map. Why?

Abstract (arXiv)

We present DexUMI - a data collection and policy learning framework that uses the human hand as the natural interface to transfer dexterous manipulation skills to various robot hands. DexUMI includes hardware and software adaptations to minimize the embodiment gap between the human hand and various robot hands. The hardware adaptation bridges the kinematics gap using a wearable hand exoskeleton. It allows direct haptic feedback in manipulation data collection and adapts human motion to feasible robot hand motion. The software adaptation bridges the visual gap by replacing the human hand in video data with high-fidelity robot hand inpainting. We demonstrate DexUMI's capabilities through comprehensive real-world experiments on two different dexterous robot hand hardware platforms, achieving an average task success rate of 86%.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 47.

58 papers.

Sort:

By area:

  1. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  2. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  3. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  4. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  5. 2025H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulationcited by 41
  6. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 36
  7. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalizationcited by 29
  8. 2026CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videoscited by 27
  9. 2025SPIDER: Scalable Physics-Informed Dexterous Retargetingcited by 25
  10. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  11. 2025In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Datacited by 21
  12. 2026A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulationcited by 20
38 more
  1. 2026Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stackcited by 20
  2. 2025ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrationscited by 17
  3. 2025DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulationcited by 15
  4. 2025OPENTOUCH: Bringing Full-Hand Touch to Real-World Interactioncited by 11
  5. 2026Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrationscited by 11
  6. 2026SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulationcited by 10
  7. 2025UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policiescited by 9
  8. 2026Dexora: Open-source VLA for High-DoF Bimanual Dexteritycited by 9
  9. 2025OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfercited by 6
  10. 2026Cross-Hand Latent Representation for Vision-Language-Action Modelscited by 5
  11. 2026UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perceptioncited by 4
  12. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  13. 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editingcited by 4
  14. 2026AoE: Always-on Egocentric Human Video Collection for Embodied AIcited by 3
  15. 2026A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policiescited by 3
  16. 2026Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLAcited by 3
  17. 2026FACT: Failure-Aware Causal Training for World-Action Modelscited by 3
  18. 2025MILE: A Mechanically Isomorphic Hand Exoskeleton and Visuotactile Robotic Hand for Data Collection in Dexterous Manipulationcited by 2
  19. 2026HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Modelcited by 2
  20. 2026VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Trainingcited by 2
  21. 2026YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scalecited by 2
  22. 2026Human Universal Graspingcited by 2
  23. 2026HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alonecited by 2
  24. 2026RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learningcited by 1
  25. 2026Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulationcited by 1
  26. 2026Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulationcited by 1
  27. 2026Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedbackcited by 1
  28. 2026Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Modelscited by 1
  29. 2026KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulationcited by 1
  30. 2026Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?cited by 1
  31. 2026Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robotscited by 1
  32. 2026A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulationcited by 1
  33. 2026RAPID: Reconfigurable, Adaptive Platform for Iterative Designcited by 0
  34. 2026Structural Action Transformer for 3D Dexterous Manipulationcited by 0
  35. 2026UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperationcited by 0
  36. 2026WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulationcited by 0
  37. 2026Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfercited by 0
  38. 2026Pre-training Visual Dexterity in Simulationcited by 0

50 most cited of 58 All 58 (JSON)