• DocumentCode
    1629435
  • Title

    A study on tactile texture recognition using magnetic type tactile sensor

  • Author

    Matsumoto, Tad ; Nakamoto, Hiroyuki

  • Author_Institution
    Hyogo Prefectural Inst. of Technol., Kobe, Japan
  • fYear
    2013
  • Firstpage
    477
  • Lastpage
    481
  • Abstract
    For the purpose of developing a human-friendly robot, a texture recognition method using tactile sensing in which a magnetic type tactile sensor is used is proposed. The magnetic sensor has soft and elastic structure part which interact with a object and two sensing elements. One is GMR (Giant MagnetoResistance) which can sense displacement of the elastic part. The other is IND (INDuctor) which can sense motion and vibration of elastic part. Support Vector Machine is used to learn texture information. Through some experiments, it is find that each of two sensing elements have strong points in different frequency ranges. Then, it is showed that leaning setting in which adequate frequencies are used in GMR and IND brings high recognition rate.
  • Keywords
    haptic interfaces; image texture; magnetic sensors; support vector machines; tactile sensors; GMR; Giant MagnetoResistance; elastic structure part; high recognition rate; human-friendly robot; magnetic type tactile sensor; support vector machine; tactile sensing; tactile texture recognition; Force; Magnetoelasticity; Shearing; Skin; Tactile sensors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    System Integration (SII), 2013 IEEE/SICE International Symposium on
  • Conference_Location
    Kobe
  • Type

    conf

  • DOI
    10.1109/SII.2013.6776725
  • Filename
    6776725