# DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation

arXiv: https://arxiv.org/abs/2608.00554 · HTML: https://mlsanity.com/paper/2608.00554/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [Rotating without Seeing: Towards In-hand Dexterity through Touch](https://mlsanity.com/paper/2303.10880/) (2023)
- [LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning](https://mlsanity.com/paper/2309.06440/) (2023)
- [ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning](https://mlsanity.com/paper/2503.21860/) (2025)
- [Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration](https://mlsanity.com/paper/2504.12609/) (2025)
- [Complex In-Hand Manipulation via Compliance-Enabled Finger Gaiting and Multi-Modal Planning](https://mlsanity.com/paper/2201.07928/) (2022)
- [Lessons from Learning to Spin "Pens"](https://mlsanity.com/paper/2407.18902/) (2024)
- [AnyRotate: Gravity-Invariant In-Hand Object Rotation with Sim-to-Real Touch](https://mlsanity.com/paper/2405.07391/) (2024)
- [Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition](https://mlsanity.com/paper/2407.00299/) (2024)
- [TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation](https://mlsanity.com/paper/2606.16272/) (2026)
- [Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation](https://mlsanity.com/paper/2607.01067/) (2026)
- [Human-to-Robot Manipulability Domain Adaptation with Parallel Transport and Manifold-Aware ICP](https://mlsanity.com/paper/2208.07588/) (2022)
- [TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-to-Sim Digital Twin Sensor Model](https://mlsanity.com/paper/2509.10063/) (2025)
- [ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation](https://mlsanity.com/paper/2510.23016/) (2025)
- [HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision](https://mlsanity.com/paper/2606.19161/) (2026)

## Built on by (most cited first, 1 of 1)

- [Touch2Robot: Robot Touch in the Human Demonstration Loop](https://mlsanity.com/paper/2609.24660/) (2026)

## Abstract (arXiv)

Dexterous object rotation is a sequential contact problem: each support, release, and re-contact decision must both produce the desired object motion, and prepare the hand configuration for continued rotation. Existing reinforcement learning methods discover such movement patterns through trial and error on specific robotic hand embodiments, without explicitly accounting for how each contact transition affects the hand's ability to sustain object rotation in subsequent steps. We introduce DexMani, a framework that transfers human demonstrations as contact-conditioned manipulability evolution. This prior captures how successful human contact transitions reshape the object-rotation directions available to the hand. DexMani then learns this manipulability evolution and uses it to guide downstream reinforcement learning, enabling rotation skills to be acquired across robot embodiments with distinct kinematics and active-contact configurations. Across the Shadow Hand, Allegro Hand, and XHand, DexMani achieves the highest success rates in every evaluated setting for both seen and unseen objects. DexMani reaches an average success rate of 57.5% on LEAP Hand, outperforming other baselines and producing smoother rotatory motions. Project site: https://dexmani.github.io