Tactile texture classification using magnetic tactile sensor

Issue title: Proceedings from the 17th International Symposium on Applied Electromagnetics and Mechanics (ISEM 2015)

Guest editors: Fumio Kojima, Futoshi Kobayashi and Hiroyuki Nakamoto

Article type: Research Article

Authors: Nakamoto, Hiroyuki^{a; *} | Matsumoto, Takuya^b

Affiliations: [a] Graduate School of System Informatics, Kobe University, Nada, Kobe, Japan | [b] Information Science and Technology Center, Kobe University, Nada, Kobe, Japan

Correspondence: [*] Corresponding author: Hiroyuki Nakamoto, Graduate School of System Informatics, Kobe University, 1-1 Rokkodai, Nada 6578501, Kobe, Japan. E-mail:[email protected]

Abstract: Human skin has tactile receptors that have different response characteristics. These characteristics are effective for the tactile texture classification. In this paper, we propose a classification method by using a magnetic tactile sensor. The tactile sensor has two sensing elements that detects slow and fast deformations occurred on the surface of itself. We confirm that the output voltages of the sensing elements include frequency characteristics of tactile texture. In addition, a support vector machine classifies tactile textures based on the output voltages.

Keywords: Tactile sensor, GMR, inductor, tactile texture

DOI: 10.3233/JAE-162125

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 52, no. 3-4, pp. 1673-1679, 2016