Featureless classification of tactile contacts in a gripper using neural networks

Antonio R. Jiménez*, Adhi Sudadi Soembagijo, Dominiek Reynaerts, Hendrik Van Brussel, Ramón Ceres, Jose L Pons

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

28 Scopus citations

Abstract

A direct, featureless process to classify contact impressions of objects gripped by a robot hand is presented. The information about the type of contact allows the selection of the most appropriate manipulating strategy to handle the grasped object. A learning vector quantization (LVQ) network is applied introducing a contact-pattern preprocessing technique to improve the robustness of the classification with respect to the pattern variations in position, orientation and size.

Original languageEnglish (US)
Pages (from-to)488-491
Number of pages4
JournalSensors and Actuators, A: Physical
Volume62
Issue number1-3
DOIs
StatePublished - Jul 1997

Keywords

  • Neural networks
  • Pattern classification
  • Shape recognition
  • Tactile sensing

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Instrumentation
  • Condensed Matter Physics
  • Surfaces, Coatings and Films
  • Metals and Alloys
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Featureless classification of tactile contacts in a gripper using neural networks'. Together they form a unique fingerprint.

Cite this