A Machine Learning Approach to Contact Localization in Variable Density Three-Dimensional Tactile Artificial Skin

Mitchell Murray, Yutong Zhang, Carson Kohlbrenner, Caleb Escobedo, Thomas Dunnington, Nolan Stevenson, Nikolaus Correll, Alessandro Roncone

Keywords: tactile sensing, machine learning, contact localization, artificial skin, robotics, mutual capacitance

TL;DR: We present a machine learning approach for localizing contact points on non-uniformly arranged tactile sensors embedded in artificial skin.

Abstract: In artificial tactile sensing, accurately localizing contact points on artificial skin is an important function. The performance of existing contact localization methods is constrained by the specific geometry and sensor locations used in the artificial skin, which limits their ability to be used on 3D surfaces. This paper studies the contact localization on an artificial skin embedded with mutual capacitance tactile sensors, arranged non-uniformly in a semi-conical 3D geometry. A fully-connected neural network is trained to localize the touching points on the embedded tactile sensors. The precision exhibits a standard deviation of localization error of 6 ± 3 mm. This research contributes a versatile tool and robust solution for contact localization in artificial tactile systems.

Submission Number: 3