Behavior prediction for several seconds using human body model and non-contact sensor

Yosuke Kimura, Akira Mita

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

Abstract

Based on social background such as aging and diversification of individual's lives, we propose the concept of Biofied building. The Biofied building is a concept that provides a safe, secure and comfortable space for residents by using small robots. The small robots used in the Biofied building sense the human position and motion. However, in the current system it is difficult to prevent accidents such as falls. The robots are not designed not disturb residents. Therefore, in this research, in order to realize more natural space control of the robot, the purpose is to incorporate motion prediction in the system in addition to motion recognition. Many conventional motion prediction methods use RNN (Recurrent Neural Networks), which is considered to be difficult to implement due to the necessity of big data and the large calculation cost. Furthermore, in RNN, it was a problem that physical constraints of the human body were not taken into consideration. Therefore, this study aims to propose a simple motion prediction method using a human body model based on dynamics.

Original languageEnglish
Title of host publicationBioinspiration, Biomimetics, and Bioreplication IX
EditorsRaul J. Martin-Palma, Mato Knez, Akhlesh Lakhtakia
PublisherSPIE
ISBN (Electronic)9781510625853
DOIs
Publication statusPublished - 2019 Jan 1
EventBioinspiration, Biomimetics, and Bioreplication IX 2019 - Denver, United States
Duration: 2019 Mar 42019 Mar 5

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10965
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceBioinspiration, Biomimetics, and Bioreplication IX 2019
CountryUnited States
CityDenver
Period19/3/419/3/5

Fingerprint

Non-contact
human body
robots
Robots
Sensor
Robot
Motion
Recurrent neural networks
Prediction
sensors
Sensors
predictions
Recurrent Neural Networks
Model
Diversification
Accidents
accidents
Aging of materials
Human
Model-based

Keywords

  • Behavior Prediction
  • Human body model
  • Living Space

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Kimura, Y., & Mita, A. (2019). Behavior prediction for several seconds using human body model and non-contact sensor. In R. J. Martin-Palma, M. Knez, & A. Lakhtakia (Eds.), Bioinspiration, Biomimetics, and Bioreplication IX [109650U] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10965). SPIE. https://doi.org/10.1117/12.2514032

Behavior prediction for several seconds using human body model and non-contact sensor. / Kimura, Yosuke; Mita, Akira.

Bioinspiration, Biomimetics, and Bioreplication IX. ed. / Raul J. Martin-Palma; Mato Knez; Akhlesh Lakhtakia. SPIE, 2019. 109650U (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10965).

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

Kimura, Y & Mita, A 2019, Behavior prediction for several seconds using human body model and non-contact sensor. in RJ Martin-Palma, M Knez & A Lakhtakia (eds), Bioinspiration, Biomimetics, and Bioreplication IX., 109650U, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10965, SPIE, Bioinspiration, Biomimetics, and Bioreplication IX 2019, Denver, United States, 19/3/4. https://doi.org/10.1117/12.2514032
Kimura Y, Mita A. Behavior prediction for several seconds using human body model and non-contact sensor. In Martin-Palma RJ, Knez M, Lakhtakia A, editors, Bioinspiration, Biomimetics, and Bioreplication IX. SPIE. 2019. 109650U. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2514032
Kimura, Yosuke ; Mita, Akira. / Behavior prediction for several seconds using human body model and non-contact sensor. Bioinspiration, Biomimetics, and Bioreplication IX. editor / Raul J. Martin-Palma ; Mato Knez ; Akhlesh Lakhtakia. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{80e4e9c203f24636aa9455810e393464,
title = "Behavior prediction for several seconds using human body model and non-contact sensor",
abstract = "Based on social background such as aging and diversification of individual's lives, we propose the concept of Biofied building. The Biofied building is a concept that provides a safe, secure and comfortable space for residents by using small robots. The small robots used in the Biofied building sense the human position and motion. However, in the current system it is difficult to prevent accidents such as falls. The robots are not designed not disturb residents. Therefore, in this research, in order to realize more natural space control of the robot, the purpose is to incorporate motion prediction in the system in addition to motion recognition. Many conventional motion prediction methods use RNN (Recurrent Neural Networks), which is considered to be difficult to implement due to the necessity of big data and the large calculation cost. Furthermore, in RNN, it was a problem that physical constraints of the human body were not taken into consideration. Therefore, this study aims to propose a simple motion prediction method using a human body model based on dynamics.",
keywords = "Behavior Prediction, Human body model, Living Space",
author = "Yosuke Kimura and Akira Mita",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2514032",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Martin-Palma, {Raul J.} and Mato Knez and Akhlesh Lakhtakia",
booktitle = "Bioinspiration, Biomimetics, and Bioreplication IX",

}

TY - GEN

T1 - Behavior prediction for several seconds using human body model and non-contact sensor

AU - Kimura, Yosuke

AU - Mita, Akira

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Based on social background such as aging and diversification of individual's lives, we propose the concept of Biofied building. The Biofied building is a concept that provides a safe, secure and comfortable space for residents by using small robots. The small robots used in the Biofied building sense the human position and motion. However, in the current system it is difficult to prevent accidents such as falls. The robots are not designed not disturb residents. Therefore, in this research, in order to realize more natural space control of the robot, the purpose is to incorporate motion prediction in the system in addition to motion recognition. Many conventional motion prediction methods use RNN (Recurrent Neural Networks), which is considered to be difficult to implement due to the necessity of big data and the large calculation cost. Furthermore, in RNN, it was a problem that physical constraints of the human body were not taken into consideration. Therefore, this study aims to propose a simple motion prediction method using a human body model based on dynamics.

AB - Based on social background such as aging and diversification of individual's lives, we propose the concept of Biofied building. The Biofied building is a concept that provides a safe, secure and comfortable space for residents by using small robots. The small robots used in the Biofied building sense the human position and motion. However, in the current system it is difficult to prevent accidents such as falls. The robots are not designed not disturb residents. Therefore, in this research, in order to realize more natural space control of the robot, the purpose is to incorporate motion prediction in the system in addition to motion recognition. Many conventional motion prediction methods use RNN (Recurrent Neural Networks), which is considered to be difficult to implement due to the necessity of big data and the large calculation cost. Furthermore, in RNN, it was a problem that physical constraints of the human body were not taken into consideration. Therefore, this study aims to propose a simple motion prediction method using a human body model based on dynamics.

KW - Behavior Prediction

KW - Human body model

KW - Living Space

UR - http://www.scopus.com/inward/record.url?scp=85069788116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069788116&partnerID=8YFLogxK

U2 - 10.1117/12.2514032

DO - 10.1117/12.2514032

M3 - Conference contribution

AN - SCOPUS:85069788116

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Bioinspiration, Biomimetics, and Bioreplication IX

A2 - Martin-Palma, Raul J.

A2 - Knez, Mato

A2 - Lakhtakia, Akhlesh

PB - SPIE

ER -