Tactile sensing is an important sensing modality for robot manipulation. Among different types of tactile sensors, magnet-based sensors, like u-skin, balance well between high durability and tactile density. However, the large sim-to-real gap of tactile sensors prevents robots from acquiring useful tactile-based manipulation skills from simulation data, a recipe that has been successful for achieving complex and sophisticated control policies. Prior work has implemented binarization techniques to bridge the sim-to-real gap for dexterous in-hand manipulation. However, binarization inherently loses much information that is useful in many other tasks, e.g., insertion. In our work, we propose GCS, a novel sim-to-real technique to learn contact-rich skills with dense, distributed, 3-axis tactile readings. We evaluate our approach on blind insertion tasks and show zero-shot sim-to-real transfer of RL policies with raw tactile reading as input.
View on arXiv@article{han2025_2505.02915,
title={ Zero-shot Sim2Real Transfer for Magnet-Based Tactile Sensor on Insertion Tasks },
author={ Beining Han and Abhishek Joshi and Jia Deng },
journal={arXiv preprint arXiv:2505.02915},
year={ 2025 }
}