Accurate Decoding of Material Textures Using a finger Mounted Accelerometer - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2018

Accurate Decoding of Material Textures Using a finger Mounted Accelerometer

Abstract

Tactile feedback plays a crucial role in our experience and control of physical interaction with objects in our environment. However, the technology for low-cost and efficient tactile feedback remains a big challenge during stroke rehabilitation, and for prosthetic designs. Here we show that a low-cost accelerometer mounted on the finger can provide accurate decoding of many daily life materials during touch. We first designed a customized touch analysis system that allowed us to present different materials for touch by human participants, while controlling for the contact force and touch speed. Then, we collected data from six participants, who touched seven daily life materials-plastic, cork, wool, aluminum, paper, denim, cotton. We use linear sparse logistic regression and show that the materials can be classified from accelerometer recordings with an accuracy of 88c/o across materials and participants within 7 seconds of touch.
Fichier principal
Vignette du fichier
Robio_Sakurada_2018.pdf (1021.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

lirmm-02158999 , version 1 (18-06-2019)

Identifiers

Cite

Kuniharu Sakurada, Gowrishankar Ganesh, Wenwei Yu, Kahori Kita. Accurate Decoding of Material Textures Using a finger Mounted Accelerometer. ROBIO 2018 - 15th IEEE International Conference on Robotics and Biomimetics, Dec 2018, Kuala Lumpur, Malaysia. pp.1316-1321, ⟨10.1109/robio.2018.8665189⟩. ⟨lirmm-02158999⟩
59 View
223 Download

Altmetric

Share

Gmail Facebook X LinkedIn More