DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model
Abstract
A novel framework enables a single simulation-trained policy to generalize to diverse real-world object rotations by learning joint-wise dynamics and autonomously collecting data.
Achieving generalized in-hand object rotation remains a significant challenge in robotics, largely due to the difficulty of transferring policies from simulation to the real world. The complex, contact-rich dynamics of dexterous manipulation create a "reality gap" that has limited prior work to constrained scenarios involving simple geometries, limited object sizes and aspect ratios, constrained wrist poses, or customized hands. We address this sim-to-real challenge with a novel framework that enables a single policy, trained in simulation, to generalize to a wide variety of objects and conditions in the real world. The core of our method is a joint-wise dynamics model that learns to bridge the reality gap by effectively fitting limited amount of real-world collected data and then adapting the sim policy's actions accordingly. The model is highly data-efficient and generalizable across different whole-hand interaction distributions by factorizing dynamics across joints, compressing system-wide influences into low-dimensional variables, and learning each joint's evolution from its own dynamic profile, implicitly capturing these net effects. We pair this with a fully autonomous data collection strategy that gathers diverse, real-world interaction data with minimal human intervention. Our complete pipeline demonstrates unprecedented generality: a single policy successfully rotates challenging objects with complex shapes (e.g., animals), high aspect ratios (up to 5.33), and small sizes, all while handling diverse wrist orientations and rotation axes. Comprehensive real-world evaluations and a teleoperation application for complex tasks validate the effectiveness and robustness of our approach. Website: https://meowuu7.github.io/DexNDM/
Community
A sim-to-real approach that enables unprecedented in-hand rotation (long, small, complex shapes; down-facing hand) in the real world.
Project Website: https://meowuu7.github.io/DexNDM/
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration (2025)
- In-Hand Manipulation of Articulated Tools with Dexterous Robot Hands with Sim-to-Real Transfer (2025)
- DemoGrasp: Universal Dexterous Grasping from a Single Demonstration (2025)
- LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations (2025)
- ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning (2025)
- TacRefineNet: Tactile-Only Grasp Refinement Between Arbitrary In-Hand Object Poses (2025)
- HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper