Predictive control of an efficient human following robot using Kinect sensor

Shin Nyeong Heo, Jang Myung Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper proposes a predictive control for an efficient human following robot using Kinect sensor. Especially, this research is focused on detecting of foot-end-point and foot-vector instead of human body which can be occluded easily by the obstacles. Recognition of the foot-end-point by the Kinect sensor is reliable since the two feet images can be utilized, which increases the detection possibility of the human motion. Depth image features and a decision tree have been utilized to estimate the foot endpoint precisely. A tracking point average algorithm is also adopted in this research to estimate the location of foot accurately. Using the continuous locations of foot, the human motion trajectory is estimated to guide the mobile robot along a smooth path to the human. It is verified through the experiments that detecting foot-end-point is more reliable and efficient than detecting the human body. Finally, the tracking performance of the mobile robot is demonstrated with a human motion along an 'L' shape course.

Original languageKorean
Pages (from-to)957-963
Number of pages7
JournalJournal of Institute of Control, Robotics and Systems
Volume20
Issue number9
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Predictive Control
Point contacts
Decision trees
Decision tree
Mobile Robot
Mobile robots
Robot
Robots
Sensor
Sensors
End point
Trajectories
Motion
Continuous Location
Experiments
Human
Estimate
Trajectory
Path
Experiment

Keywords

  • Foot vector
  • Human following robot
  • Kinect sensor
  • Tracking performance

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Applied Mathematics

Cite this

Predictive control of an efficient human following robot using Kinect sensor. / Heo, Shin Nyeong; Lee, Jang Myung.

In: Journal of Institute of Control, Robotics and Systems, Vol. 20, No. 9, 2014, p. 957-963.

Research output: Contribution to journalArticle

@article{162bd2911f614c42924e0c3d4b78ead0,
title = "Predictive control of an efficient human following robot using Kinect sensor",
abstract = "This paper proposes a predictive control for an efficient human following robot using Kinect sensor. Especially, this research is focused on detecting of foot-end-point and foot-vector instead of human body which can be occluded easily by the obstacles. Recognition of the foot-end-point by the Kinect sensor is reliable since the two feet images can be utilized, which increases the detection possibility of the human motion. Depth image features and a decision tree have been utilized to estimate the foot endpoint precisely. A tracking point average algorithm is also adopted in this research to estimate the location of foot accurately. Using the continuous locations of foot, the human motion trajectory is estimated to guide the mobile robot along a smooth path to the human. It is verified through the experiments that detecting foot-end-point is more reliable and efficient than detecting the human body. Finally, the tracking performance of the mobile robot is demonstrated with a human motion along an 'L' shape course.",
keywords = "Foot vector, Human following robot, Kinect sensor, Tracking performance",
author = "Heo, {Shin Nyeong} and Lee, {Jang Myung}",
year = "2014",
doi = "10.5302/J.ICROS.2014.14.0019",
language = "Korean",
volume = "20",
pages = "957--963",
journal = "Journal of Institute of Control, Robotics and Systems",
issn = "1976-5622",
publisher = "Institute of Control, Robotics and Systems",
number = "9",

}

TY - JOUR

T1 - Predictive control of an efficient human following robot using Kinect sensor

AU - Heo, Shin Nyeong

AU - Lee, Jang Myung

PY - 2014

Y1 - 2014

N2 - This paper proposes a predictive control for an efficient human following robot using Kinect sensor. Especially, this research is focused on detecting of foot-end-point and foot-vector instead of human body which can be occluded easily by the obstacles. Recognition of the foot-end-point by the Kinect sensor is reliable since the two feet images can be utilized, which increases the detection possibility of the human motion. Depth image features and a decision tree have been utilized to estimate the foot endpoint precisely. A tracking point average algorithm is also adopted in this research to estimate the location of foot accurately. Using the continuous locations of foot, the human motion trajectory is estimated to guide the mobile robot along a smooth path to the human. It is verified through the experiments that detecting foot-end-point is more reliable and efficient than detecting the human body. Finally, the tracking performance of the mobile robot is demonstrated with a human motion along an 'L' shape course.

AB - This paper proposes a predictive control for an efficient human following robot using Kinect sensor. Especially, this research is focused on detecting of foot-end-point and foot-vector instead of human body which can be occluded easily by the obstacles. Recognition of the foot-end-point by the Kinect sensor is reliable since the two feet images can be utilized, which increases the detection possibility of the human motion. Depth image features and a decision tree have been utilized to estimate the foot endpoint precisely. A tracking point average algorithm is also adopted in this research to estimate the location of foot accurately. Using the continuous locations of foot, the human motion trajectory is estimated to guide the mobile robot along a smooth path to the human. It is verified through the experiments that detecting foot-end-point is more reliable and efficient than detecting the human body. Finally, the tracking performance of the mobile robot is demonstrated with a human motion along an 'L' shape course.

KW - Foot vector

KW - Human following robot

KW - Kinect sensor

KW - Tracking performance

UR - http://www.scopus.com/inward/record.url?scp=84922976239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922976239&partnerID=8YFLogxK

U2 - 10.5302/J.ICROS.2014.14.0019

DO - 10.5302/J.ICROS.2014.14.0019

M3 - Article

VL - 20

SP - 957

EP - 963

JO - Journal of Institute of Control, Robotics and Systems

JF - Journal of Institute of Control, Robotics and Systems

SN - 1976-5622

IS - 9

ER -