Gait measurement for human behavior estimation against autonomous mobile robot

Ayanori Yorozu, Masaki Takahashi

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

Abstract

To realize a safe collision avoidance of autonomous mobile robots, understanding human behavior against the robots is important. This paper has proposed a gait measurement method for human behavior estimation against autonomous mobile robot. The proposed method using a laser range sensor consists of five observed leg patterns recognition and global nearest neighbor (GNN)-based data association with a variable validation region based on the state of each leg. To verify the effectiveness of the proposed system, a verification test in a hospital that staff is recruited as participants were carried out. From the experimental results in the hospital, we confirm that the proposed method can reduce the chance of losing track of both legs and the variable validation region can reduce the chance of false tracking.

Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Computing
PublisherSpringer Verlag
Pages1021-1033
Number of pages13
Volume302
ISBN (Print)9783319083377
DOIs
Publication statusPublished - 2016
Event13th International Conference on Intelligent Autonomous Systems, IAS 2014 - Padova, Italy
Duration: 2014 Jul 152014 Jul 18

Publication series

NameAdvances in Intelligent Systems and Computing
Volume302
ISSN (Print)21945357

Other

Other13th International Conference on Intelligent Autonomous Systems, IAS 2014
CountryItaly
CityPadova
Period14/7/1514/7/18

Fingerprint

Mobile robots
Collision avoidance
Pattern recognition
Robots
Lasers
Sensors

Keywords

  • Autonomous mobile robot
  • Data association
  • Global nearest neighbor
  • Kalman filter
  • Laser range sensor
  • Leg tracking

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Yorozu, A., & Takahashi, M. (2016). Gait measurement for human behavior estimation against autonomous mobile robot. In Advances in Intelligent Systems and Computing (Vol. 302, pp. 1021-1033). (Advances in Intelligent Systems and Computing; Vol. 302). Springer Verlag. https://doi.org/10.1007/978-3-319-08338-4_74

Gait measurement for human behavior estimation against autonomous mobile robot. / Yorozu, Ayanori; Takahashi, Masaki.

Advances in Intelligent Systems and Computing. Vol. 302 Springer Verlag, 2016. p. 1021-1033 (Advances in Intelligent Systems and Computing; Vol. 302).

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

Yorozu, A & Takahashi, M 2016, Gait measurement for human behavior estimation against autonomous mobile robot. in Advances in Intelligent Systems and Computing. vol. 302, Advances in Intelligent Systems and Computing, vol. 302, Springer Verlag, pp. 1021-1033, 13th International Conference on Intelligent Autonomous Systems, IAS 2014, Padova, Italy, 14/7/15. https://doi.org/10.1007/978-3-319-08338-4_74
Yorozu A, Takahashi M. Gait measurement for human behavior estimation against autonomous mobile robot. In Advances in Intelligent Systems and Computing. Vol. 302. Springer Verlag. 2016. p. 1021-1033. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-08338-4_74
Yorozu, Ayanori ; Takahashi, Masaki. / Gait measurement for human behavior estimation against autonomous mobile robot. Advances in Intelligent Systems and Computing. Vol. 302 Springer Verlag, 2016. pp. 1021-1033 (Advances in Intelligent Systems and Computing).
@inproceedings{7129a625118f4b37b4703defe4539298,
title = "Gait measurement for human behavior estimation against autonomous mobile robot",
abstract = "To realize a safe collision avoidance of autonomous mobile robots, understanding human behavior against the robots is important. This paper has proposed a gait measurement method for human behavior estimation against autonomous mobile robot. The proposed method using a laser range sensor consists of five observed leg patterns recognition and global nearest neighbor (GNN)-based data association with a variable validation region based on the state of each leg. To verify the effectiveness of the proposed system, a verification test in a hospital that staff is recruited as participants were carried out. From the experimental results in the hospital, we confirm that the proposed method can reduce the chance of losing track of both legs and the variable validation region can reduce the chance of false tracking.",
keywords = "Autonomous mobile robot, Data association, Global nearest neighbor, Kalman filter, Laser range sensor, Leg tracking",
author = "Ayanori Yorozu and Masaki Takahashi",
year = "2016",
doi = "10.1007/978-3-319-08338-4_74",
language = "English",
isbn = "9783319083377",
volume = "302",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "1021--1033",
booktitle = "Advances in Intelligent Systems and Computing",

}

TY - GEN

T1 - Gait measurement for human behavior estimation against autonomous mobile robot

AU - Yorozu, Ayanori

AU - Takahashi, Masaki

PY - 2016

Y1 - 2016

N2 - To realize a safe collision avoidance of autonomous mobile robots, understanding human behavior against the robots is important. This paper has proposed a gait measurement method for human behavior estimation against autonomous mobile robot. The proposed method using a laser range sensor consists of five observed leg patterns recognition and global nearest neighbor (GNN)-based data association with a variable validation region based on the state of each leg. To verify the effectiveness of the proposed system, a verification test in a hospital that staff is recruited as participants were carried out. From the experimental results in the hospital, we confirm that the proposed method can reduce the chance of losing track of both legs and the variable validation region can reduce the chance of false tracking.

AB - To realize a safe collision avoidance of autonomous mobile robots, understanding human behavior against the robots is important. This paper has proposed a gait measurement method for human behavior estimation against autonomous mobile robot. The proposed method using a laser range sensor consists of five observed leg patterns recognition and global nearest neighbor (GNN)-based data association with a variable validation region based on the state of each leg. To verify the effectiveness of the proposed system, a verification test in a hospital that staff is recruited as participants were carried out. From the experimental results in the hospital, we confirm that the proposed method can reduce the chance of losing track of both legs and the variable validation region can reduce the chance of false tracking.

KW - Autonomous mobile robot

KW - Data association

KW - Global nearest neighbor

KW - Kalman filter

KW - Laser range sensor

KW - Leg tracking

UR - http://www.scopus.com/inward/record.url?scp=84945947050&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945947050&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-08338-4_74

DO - 10.1007/978-3-319-08338-4_74

M3 - Conference contribution

SN - 9783319083377

VL - 302

T3 - Advances in Intelligent Systems and Computing

SP - 1021

EP - 1033

BT - Advances in Intelligent Systems and Computing

PB - Springer Verlag

ER -