Estimation method using genetic programming for location and depth on distributed 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: Sasai, Shiho^* | Nakamoto, Hiroyuki | Kobayashi, Futoshi | Kojima, Fumio

Affiliations: Graduate School of system Informatics, Kobe University, Kobe, Japan

Correspondence: [*] Corresponding author: Shiho Sasai, Graduate School of System Informatics, Kobe University, 1-1 Rokkodai-cho, Nada-ku, Kobe, 657-8501, Japan. E-mail: [email protected]

Abstract: Tactile sensors are required in various areas such as robotics, human interfaces. Since sensing elements and wiring space are limited, it is important that a few sensing elements cover a large area. In this study, a tactile sensor which comprises of an elastic layer and a substrate layer is proposed. This sensor has some magnets and giant magnetoresistance effect elements (GMR elements) as sensor elements. The tactile sensor estimates a location and depth of a touch based on the output voltages of GMR elements. The estimate equation is determined by the genetic programming. The effectiveness of the tactile sensor is confirmed through laboratory experiments.

Keywords: Tactile sensor, GMR, GP, multiple regression analysis

DOI: 10.3233/JAE-162090

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 52, no. 3-4, pp. 1221-1229, 2016