An Electromagnetism-Inspired Method for Estimating In-Grasp Torque from Visuotactile Sensors

TL;DR

This paper introduces a novel electromechanics-inspired method to estimate in-grasp tilt torques from visuotactile sensors, enabling accurate torque measurement without complex modeling or deep learning, demonstrated across multiple sensors and objects.

Contribution

The authors propose the Tactile Dipole Moment, a simple analytical approach for torque estimation from tactile sensor data, avoiding reliance on deep learning or detailed sensor models.

Findings

Accurately estimates tilt torques across different sensors and objects.

Effective in practical tasks like USB stick insertion with a robot.

Simple method achieves reliable torque measurements without complex modeling.

Abstract

Tactile sensing has become a popular sensing modality for robot manipulators, due to the promise of providing robots with the ability to measure the rich contact information that gets transmitted through its sense of touch. Among the diverse range of information accessible from tactile sensors, torques transmitted from the grasped object to the fingers through extrinsic environmental contact may be particularly important for tasks such as object insertion. However, tactile torque estimation has received relatively little attention when compared to other sensing modalities, such as force, texture, or slip identification. In this work, we introduce the notion of the Tactile Dipole Moment, which we use to estimate tilt torques from gel-based visuotactile sensors. This method does not rely on deep learning, sensor-specific mechanical, or optical modeling, and instead takes inspiration from electromechanics to analyze the vector field produced from 2D marker displacements. Despite the simplicity of our technique, we demonstrate its ability to provide accurate torque readings over two different tactile sensors and three object geometries, and highlight its practicality for the task of USB stick insertion with a compliant robot arm. These results suggest that simple analytical calculations based on dipole moments can sufficiently extract physical quantities from visuotactile sensors.