# Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning

arXiv: https://arxiv.org/abs/2606.11767 · HTML: https://mlsanity.com/paper/2606.11767/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 30 of 30)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch](https://mlsanity.com/paper/1805.11085/) (2018)
- [Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research](https://mlsanity.com/paper/1911.05063/) (2019)
- [Rotating without Seeing: Towards In-hand Dexterity through Touch](https://mlsanity.com/paper/2303.10880/) (2023)
- [3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing](https://mlsanity.com/paper/2410.24091/) (2024)
- [Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator](https://mlsanity.com/paper/2104.09194/) (2021)
- [Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing](https://mlsanity.com/paper/2312.01853/) (2023)
- [Taxim: An Example-based Simulation Model for GelSight Tactile Sensors](https://mlsanity.com/paper/2109.04027/) (2021)
- [Twisting Lids Off with Two Hands](https://mlsanity.com/paper/2403.02338/) (2024)
- [Sim-to-Real for Robotic Tactile Sensing via Physics-Based Simulation and Learned Latent Projections](https://mlsanity.com/paper/2103.16747/) (2021)
- [AnyRotate: Gravity-Invariant In-Hand Object Rotation with Sim-to-Real Touch](https://mlsanity.com/paper/2405.07391/) (2024)
- [Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering](https://mlsanity.com/paper/2012.05205/) (2020)
- [BODex: Scalable and Efficient Robotic Dexterous Grasp Synthesis Using Bilevel Optimization](https://mlsanity.com/paper/2412.16490/) (2024)
- [Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomy](https://mlsanity.com/paper/2504.18829/) (2025)
- [Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation](https://mlsanity.com/paper/2106.08796/) (2021)
- [TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors](https://mlsanity.com/paper/1901.06181/) (2019)
- [ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion](https://mlsanity.com/paper/2309.05662/) (2023)
- [DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexterity](https://mlsanity.com/paper/2401.12496/) (2024)
- [Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory](https://mlsanity.com/paper/2103.00410/) (2021)
- [Embedding high-resolution touch across robotic hands enables adaptive human-like grasping](https://mlsanity.com/paper/2412.14482/) (2024)
- [Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation](https://mlsanity.com/paper/2504.12908/) (2025)
- [Spatially anchored Tactile Awareness for Robust Dexterous Manipulation](https://mlsanity.com/paper/2510.14647/) (2025)
- [GelSLAM: A Real-time, High-Fidelity, and Robust 3D Tactile SLAM System](https://mlsanity.com/paper/2508.15990/) (2025)
- [T(R,O) Grasp: Efficient Graph Diffusion of Robot-Object Spatial Transformation for Cross-Embodiment Dexterous Grasping](https://mlsanity.com/paper/2510.12724/) (2025)
- [PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands](https://mlsanity.com/paper/2504.16649/) (2025)
- [Learning to Detect Slip through Tactile Estimation of the Contact Force Field and its Entropy](https://mlsanity.com/paper/2303.00935/) (2023)
- [TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-to-Sim Digital Twin Sensor Model](https://mlsanity.com/paper/2509.10063/) (2025)
- [ViTaSCOPE: Visuo-tactile Implicit Representation for In-hand Pose and Extrinsic Contact Estimation](https://mlsanity.com/paper/2506.12239/) (2025)
- [Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot](https://mlsanity.com/paper/2311.07245/) (2023)

## Built on by (most cited first, 3 of 3)

- [BiView-Touch: Learning Bimanual Tactile Representations by Cross-Hand Completion](https://mlsanity.com/paper/2609.23352/) (2026)
- [Touch2Robot: Robot Touch in the Human Demonstration Loop](https://mlsanity.com/paper/2609.24660/) (2026)
- [Dexterous Tactile World Model](https://mlsanity.com/paper/2609.34286/) (2026)

## Abstract (arXiv)

Blind grasping with a dexterous hand is a crucial manipulation capability. Nevertheless, learning such tactile-only policies for real robots remains challenging due to the tactile sim-to-real gap and the limited expressiveness of sparse tactile signals. To bridge this gap, we propose a framework for tactile-only blind grasping that is deployable on a physical multi-fingered robotic hand. Our approach combines three key components. First, we introduce a Real2Sim tactile calibration pipeline that constructs a contact-calibrated digital-twin simulator capable of reproducing real tactile signals. Second, we improve the expressiveness of sparse tactile observations using a layout-aware tactile encoder, which incorporates sensor-geometry priors through self-supervised pretraining. Third, to improve generalization to unseen objects, we train object-specific reinforcement-learning experts in the calibrated simulator and aggregate their successful grasp trajectories into a tactile-conditioned Diffusion Policy. We evaluate our method on a physical LEAP Hand equipped with distributed tactile sensing across 10 seen and 10 unseen objects. The deployed policy achieves a 27% real-world grasp success rate across all 20 objects, without real-world grasping demonstrations or visual input. Simulation ablations show that layout-aware tactile pretraining improves grasping performance, while sensing-level evaluations confirm that Real2Sim calibration increases the consistency of tactile contact events between simulation and hardware. Together, these results suggest that contact-event calibration, geometry-aware tactile representation learning, and diffusion-based policy aggregation provide an effective path toward tactile-only blind grasping on real dexterous robotic hands. Project page:Dex-Blind-Grasp.github.io.