Leaning Impedance Distribution of Object from Images Using Fully Convolutional Neural Networks

Masahiro Kamigaki, Hisayoshi Muramatsu, Seiichiro Katsura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Robots have been introduced into industrial factory automation. It is necessary to consider interactions between the robots and environments to expand executable tasks of the robots. In the interaction, impedance is an essential factor for the robot to contact with the environment, whereas the impedance is unobservable without contact. In this study, we introduce a concept of affordance for impedance estimation without contact. We propose the impedance estimation method from an RGB image input using deep learning. In this paper, we show that the proposed method can extract pixels corresponding to sponges with its impedance composed of stiffness and viscosity, including the distribution of the impedance. We conducted the experiments to validate the proposed method.

Original languageEnglish
Title of host publicationProceedings - IECON 2020
Subtitle of host publication46th Annual Conference of the IEEE Industrial Electronics Society
PublisherIEEE Computer Society
Pages2662-2667
Number of pages6
ISBN (Electronic)9781728154145
DOIs
Publication statusPublished - 2020 Oct 18
Event46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020 - Virtual, Singapore, Singapore
Duration: 2020 Oct 192020 Oct 21

Publication series

NameIECON Proceedings (Industrial Electronics Conference)
Volume2020-October

Conference

Conference46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020
CountrySingapore
CityVirtual, Singapore
Period20/10/1920/10/21

Keywords

  • Environmental impedance estimation
  • deep learning
  • visual affordance

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Leaning Impedance Distribution of Object from Images Using Fully Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this