# TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-to-Sim Digital Twin Sensor Model

arXiv: https://arxiv.org/abs/2509.10063 · HTML: https://mlsanity.com/paper/2509.10063/

## Key facts

- Cited by 4 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 18 of its 43 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## 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, 18 of 18)

- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation](https://mlsanity.com/paper/2005.14679/) (2020)
- [More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch](https://mlsanity.com/paper/1805.11085/) (2018)
- [Taxim: An Example-based Simulation Model for GelSight Tactile Sensors](https://mlsanity.com/paper/2109.04027/) (2021)
- [Fast Tetrahedral Meshing in the Wild](https://mlsanity.com/paper/1908.03581/) (2019)
- [Sim-to-Real for Robotic Tactile Sensing via Physics-Based Simulation and Learned Latent Projections](https://mlsanity.com/paper/2103.16747/) (2021)
- [TacSL: A Library for Visuotactile Sensor Simulation and Learning](https://mlsanity.com/paper/2408.06506/) (2024)
- [DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation](https://mlsanity.com/paper/2403.08716/) (2024)
- [Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing](https://mlsanity.com/paper/2407.07885/) (2024)
- [Tactile Regrasp: Grasp Adjustments via Simulated Tactile Transformations](https://mlsanity.com/paper/1803.01940/) (2018)
- [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)
- [Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation](https://mlsanity.com/paper/2102.11051/) (2021)
- [EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation](https://mlsanity.com/paper/2408.06265/) (2024)
- [TacIPC: Intersection- and Inversion-free FEM-based Elastomer Simulation For Optical Tactile Sensors](https://mlsanity.com/paper/2311.05843/) (2023)
- [When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors from the Signal Processing Perspective](https://mlsanity.com/paper/2406.12226/) (2024)
- [GelSight Svelte Hand: A Three-finger, Two-DoF, Tactile-rich, Low-cost Robot Hand for Dexterous Manipulation](https://mlsanity.com/paper/2309.10886/) (2023)
- [3D Force and Contact Estimation for a Soft-Bubble Visuotactile Sensor Using FEM](https://mlsanity.com/paper/2310.11372/) (2023)

## Built on by (most cited first, 4 of 4)

- [Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning](https://mlsanity.com/paper/2606.11767/) (2026)
- [DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation](https://mlsanity.com/paper/2608.00554/) (2026)
- [Tac2Pix: Image-Space Visuo-Tactile Fusion for Dexterous Manipulation](https://mlsanity.com/paper/2606.08765/) (2026)
- [Touch2Robot: Robot Touch in the Human Demonstration Loop](https://mlsanity.com/paper/2609.24660/) (2026)

## Abstract (arXiv)

Robot skill acquisition processes driven by reinforcement learning often rely on simulations to efficiently generate large-scale interaction data. However, the absence of simulation models for tactile sensors has hindered the use of tactile sensing in such skill learning processes, limiting the development of effective policies driven by tactile perception. To bridge this gap, we present TwinTac, a system that combines the design of a physical tactile sensor with its digital twin model. Our hardware sensor is designed for high sensitivity and a wide measurement range, enabling high quality sensing data essential for object interaction tasks. Building upon the hardware sensor, we develop the digital twin model using a real-to-sim approach. This involves collecting synchronized cross-domain data, including finite element method results and the physical sensor's outputs, and then training neural networks to map simulated data to real sensor responses. Through experimental evaluation, we characterized the sensitivity of the physical sensor and demonstrated the consistency of the digital twin in replicating the physical sensor's output. Furthermore, by conducting an object classification task, we showed that simulation data generated by our digital twin sensor can effectively augment real-world data, leading to improved accuracy. These results highlight TwinTac's potential to bridge the gap in cross-domain learning tasks.