mlsanityData to 7 Oct 2026

DextrAH-G: Pixels-to-Action Dexterous Arm-Hand Grasping with Geometric Fabrics

arXiv 2407.02274 ↗First posted 2 Jul 2024cs.ROcited by 36

Not on the map. Why?

Abstract (arXiv)

A pivotal challenge in robotics is achieving fast, safe, and robust dexterous grasping across a diverse range of objects, an important goal within industrial applications. However, existing methods often have very limited speed, dexterity, and generality, along with limited or no hardware safety guarantees. In this work, we introduce DextrAH-G, a depth-based dexterous grasping policy trained entirely in simulation that combines reinforcement learning, geometric fabrics, and teacher-student distillation. We address key challenges in joint arm-hand policy learning, such as high-dimensional observation and action spaces, the sim2real gap, collision avoidance, and hardware constraints. DextrAH-G enables a 23 motor arm-hand robot to safely and continuously grasp and transport a large variety of objects at high speed using multi-modal inputs including depth images, allowing generalization across object geometry. Videos at https://sites.google.com/view/dextrah-g.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 19; 2026: 15.

36 papers.

Sort:

By area:

  1. 2025DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Graspingcited by 87
  2. 2024SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splattingcited by 63
  3. 2025Visual Imitation Enables Contextual Humanoid Controlcited by 57
  4. 2025Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoidscited by 40
  5. 2025DexMachina: Functional Retargeting for Bimanual Dexterous Manipulationcited by 30
  6. 2025Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstrationcited by 27
  7. 2025Dex1B: Learning with 1B Demonstrations for Dexterous Manipulationcited by 23
  8. 2024Local Policies Enable Zero-shot Long-horizon Manipulationcited by 21
  9. 2025AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiencycited by 14
  10. 2025Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecificationcited by 12
  11. 2026Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulationcited by 10
  12. 2026SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulationcited by 10
24 more
  1. 2025Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Explorationcited by 9
  2. 2025Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robotscited by 8
  3. 2025Scaffolding Dexterous Manipulation with Vision-Language Modelscited by 7
  4. 2025Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learningcited by 5
  5. 2025End-to-end RL Improves Dexterous Grasping Policiescited by 5
  6. 2025LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrationscited by 3
  7. 2026DeFM: Learning Foundation Representations from Depth for Roboticscited by 3
  8. 2025RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AIcited by 2
  9. 2025Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Datacited by 2
  10. 2025OmniDexVLG: Learning Dexterous Grasp Generation from Vision Language Model-Guided Grasp Semantics, Taxonomy and Functional Affordancecited by 2
  11. 2026Human Universal Graspingcited by 2
  12. 2025Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Controlcited by 1
  13. 2026How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preferencecited by 1
  14. 2026StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perceptioncited by 1
  15. 2026Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradientcited by 1
  16. 2026Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?cited by 1
  17. 2026UniCross: Unified Cross-Skill Dexterous Manipulation Synthesiscited by 1
  18. 2025Placeit! A Framework for Learning Robot Object Placement Skillscited by 0
  19. 2026Mana: Dexterous Manipulation of Articulated Toolscited by 0
  20. 2026ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learningcited by 0
  21. 2026WM-Craftnet: World Synesthesia Model for Generalizable and Robust Dexterous In-Hand Manipulationcited by 0
  22. 2026Kintsugi-VLA: Turning Failed Robot Rollouts into Recovery Data through Interventional Recoverabilitycited by 0
  23. 2026Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Controlcited by 0
  24. 2026DexAgent: An Agentic Human2Sim2Robot Framework for Dexterous Manipulation with Self-Evolving Tool Librarycited by 0