Estimation system of human behaviors using a fuzzy neural network based object selection

Kiyotaka Izumi, Kohei Kamohara, Keigo Watanabe

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

2 Citations (Scopus)

Abstract

The estimation of human behaviors by robots is one of key technologies in an environment in which humans and robots coexist. In this paper, a method is proposed for promptly estimating the behavioral targets by applying a fuzzy neural network (FNN). Here, inputs to the FNN are the human velocity, the angle of the human relative to an object, and the distance between the human and an object, whereas outputs are confidences that each object among all candidates is selected to be an intended object. The resultant human behavior can be estimated as a combination of the human action estimation and the behavioral target estimation.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1989-1993
Number of pages5
DOIs
Publication statusPublished - 2008
Externally publishedYes
EventSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology - Tokyo, Japan
Duration: Aug 20 2008Aug 22 2008

Other

OtherSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology
CountryJapan
CityTokyo
Period8/20/088/22/08

Fingerprint

Fuzzy neural networks
Robots

Keywords

  • Estimation of human behaviors
  • Fuzzy neural networks
  • Object estimation
  • Posture detection

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Izumi, K., Kamohara, K., & Watanabe, K. (2008). Estimation system of human behaviors using a fuzzy neural network based object selection. In Proceedings of the SICE Annual Conference (pp. 1989-1993). [4654988] https://doi.org/10.1109/SICE.2008.4654988

Estimation system of human behaviors using a fuzzy neural network based object selection. / Izumi, Kiyotaka; Kamohara, Kohei; Watanabe, Keigo.

Proceedings of the SICE Annual Conference. 2008. p. 1989-1993 4654988.

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

Izumi, K, Kamohara, K & Watanabe, K 2008, Estimation system of human behaviors using a fuzzy neural network based object selection. in Proceedings of the SICE Annual Conference., 4654988, pp. 1989-1993, SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology, Tokyo, Japan, 8/20/08. https://doi.org/10.1109/SICE.2008.4654988
Izumi K, Kamohara K, Watanabe K. Estimation system of human behaviors using a fuzzy neural network based object selection. In Proceedings of the SICE Annual Conference. 2008. p. 1989-1993. 4654988 https://doi.org/10.1109/SICE.2008.4654988
Izumi, Kiyotaka ; Kamohara, Kohei ; Watanabe, Keigo. / Estimation system of human behaviors using a fuzzy neural network based object selection. Proceedings of the SICE Annual Conference. 2008. pp. 1989-1993
@inproceedings{7b49118cce294370a1e422f56039ce39,
title = "Estimation system of human behaviors using a fuzzy neural network based object selection",
abstract = "The estimation of human behaviors by robots is one of key technologies in an environment in which humans and robots coexist. In this paper, a method is proposed for promptly estimating the behavioral targets by applying a fuzzy neural network (FNN). Here, inputs to the FNN are the human velocity, the angle of the human relative to an object, and the distance between the human and an object, whereas outputs are confidences that each object among all candidates is selected to be an intended object. The resultant human behavior can be estimated as a combination of the human action estimation and the behavioral target estimation.",
keywords = "Estimation of human behaviors, Fuzzy neural networks, Object estimation, Posture detection",
author = "Kiyotaka Izumi and Kohei Kamohara and Keigo Watanabe",
year = "2008",
doi = "10.1109/SICE.2008.4654988",
language = "English",
isbn = "9784907764296",
pages = "1989--1993",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Estimation system of human behaviors using a fuzzy neural network based object selection

AU - Izumi, Kiyotaka

AU - Kamohara, Kohei

AU - Watanabe, Keigo

PY - 2008

Y1 - 2008

N2 - The estimation of human behaviors by robots is one of key technologies in an environment in which humans and robots coexist. In this paper, a method is proposed for promptly estimating the behavioral targets by applying a fuzzy neural network (FNN). Here, inputs to the FNN are the human velocity, the angle of the human relative to an object, and the distance between the human and an object, whereas outputs are confidences that each object among all candidates is selected to be an intended object. The resultant human behavior can be estimated as a combination of the human action estimation and the behavioral target estimation.

AB - The estimation of human behaviors by robots is one of key technologies in an environment in which humans and robots coexist. In this paper, a method is proposed for promptly estimating the behavioral targets by applying a fuzzy neural network (FNN). Here, inputs to the FNN are the human velocity, the angle of the human relative to an object, and the distance between the human and an object, whereas outputs are confidences that each object among all candidates is selected to be an intended object. The resultant human behavior can be estimated as a combination of the human action estimation and the behavioral target estimation.

KW - Estimation of human behaviors

KW - Fuzzy neural networks

KW - Object estimation

KW - Posture detection

UR - http://www.scopus.com/inward/record.url?scp=56749107609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56749107609&partnerID=8YFLogxK

U2 - 10.1109/SICE.2008.4654988

DO - 10.1109/SICE.2008.4654988

M3 - Conference contribution

AN - SCOPUS:56749107609

SN - 9784907764296

SP - 1989

EP - 1993

BT - Proceedings of the SICE Annual Conference

ER -