SuperMag: Vision-based Tactile Data Guided High-resolution Tactile Shape Reconstruction for Magnetic Tactile Sensors

TL;DR

SuperMag introduces a method that uses high-resolution vision-based tactile data to enhance the spatial resolution of magnetic tactile sensors, enabling high-speed, high-precision tactile shape reconstruction for robotic applications.

Contribution

The paper presents a novel cross-modality approach combining vision-based and magnetic tactile sensors with a generative model for super-resolution shape reconstruction.

Findings

Achieves high-resolution tactile shape reconstruction at 125 Hz sampling rate.

Inference time for shape reconstruction is within 2.5 milliseconds.

Demonstrates improved tactile perception capabilities for robotic tasks.

Abstract

Magnetic-based tactile sensors (MBTS) combine the advantages of compact design and high-frequency operation but suffer from limited spatial resolution due to their sparse taxel arrays. This paper proposes SuperMag, a tactile shape reconstruction method that addresses this limitation by leveraging high-resolution vision-based tactile sensor (VBTS) data to supervise MBTS super-resolution. Co-designed, open-source VBTS and MBTS with identical contact modules enable synchronized data collection of high-resolution shapes and magnetic signals via a symmetric calibration setup. We frame tactile shape reconstruction as a conditional generative problem, employing a conditional variational auto-encoder to infer high-resolution shapes from low-resolution MBTS inputs. The MBTS achieves a sampling frequency of 125 Hz, whereas the shape reconstruction sustains an inference time within 2.5 ms. This cross-modality synergy advances tactile perception of the MBTS, potentially unlocking its new capabilities in high-precision robotic tasks.