E Skin
E-skin, or electronic skin, aims to replicate the sensory capabilities of human skin by creating flexible, artificial sensors capable of detecting various stimuli like pressure, shear force, temperature, and proximity. Current research heavily utilizes machine learning, particularly deep learning models such as convolutional neural networks and transformers, to process data from capacitive and acoustic sensor arrays, enabling tasks like object recognition, force estimation, and even human-robot interaction. This technology holds significant promise for advancing robotics, particularly in human-robot collaboration and soft robotics, as well as improving prosthetics and human-computer interfaces by providing more nuanced and natural interaction.
Papers
Design of a Five-Fingered Hand with Full-Fingered Tactile Sensors Using Conductive Filaments and Its Application to Bending after Insertion Motion
Kazuhiro Miyama, Shun Hasegawa, Kento Kawaharazuka, Naoya Yamaguchi, Kei Okada, Masayuki Inaba
A Machine Learning Approach to Contact Localization in Variable Density Three-Dimensional Tactile Artificial Skin
Carson Kohlbrenner, Mitchell Murray, Yutong Zhang, Caleb Escobedo, Thomas Dunnington, Nolan Stevenson, Nikolaus Correll, Alessandro Roncone
Going In Blind: Object Motion Classification using Distributed Tactile Sensing for Safe Reaching in Clutter
Rachel Thomasson, Etienne Roberge, Mark R. Cutkosky, Jean-Philippe Roberge
Deep Learning Classification of Touch Gestures Using Distributed Normal and Shear Force
Hojung Choi, Dane Brouwer, Michael A. Lin, Kyle T. Yoshida, Carine Rognon, Benjamin Stephens-Fripp, Allison M. Okamura, Mark R. Cutkosky