aiqbench analysis
This research addresses the critical sim-to-real gap in robot manipulation by introducing GCS, a technique enabling zero-shot transfer of reinforcement learning policies using raw 3-axis magnet-based tactile data for insertion tasks. By avoiding information-lossy binarization methods common in prior work, this approach allows robots to effectively learn contact-rich skills directly from simulation without retraining on physical hardware.
Zero-shot Sim2Real Transfer for Magnet-Based Tactile Sensor on Insertion Tasks
arXiv:2505.02915v2 Announce Type: replace Abstract: 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.
Abstract: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.
Robotics (cs.RO)
arXiv:2505.02915 [cs.RO]
(or arXiv:2505.02915v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2505.02915 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 223 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction
arXiv · Aug 18, 2026
ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning
arXiv · Aug 21, 2026
News
Quantum Computing Report · Jul 25, 2026