Wavelet-based feature extraction for behavior recognition in mobile robots

Xin Jin, Kushal Mukherjee, Shalabh Gupta, Asok Ray

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

Abstract

This paper introduces a dynamic data-driven method for behavior recognition in mobile robots. The core concept of the paper is built upon the principle of symbolic dynamic filtering (SDF) that is used to extract relevant information in complex dynamical systems. The objective here is to identify the robot behavior from time-series data of piezoelectric sensor signals from the pressure sensitive floor in a laboratory environment. A symbolic feature extraction method is presented by partitioning of two-dimensional wavelet images of sensor time-series data. The K-nearest neighbors (k-NN) algorithm is used to identify the patterns extracted by SDF. The proposed method is validated by experimentation on a networked robotics test bed to detect and identify the type and motion profile of mobile robots.

Original languageEnglish (US)
Title of host publicationASME 2010 Dynamic Systems and Control Conference, DSCC2010
Pages875-882
Number of pages8
DOIs
StatePublished - Dec 1 2010
EventASME 2010 Dynamic Systems and Control Conference, DSCC2010 - Cambridge, MA, United States
Duration: Sep 12 2010Sep 15 2010

Publication series

NameASME 2010 Dynamic Systems and Control Conference, DSCC2010
Volume1

Other

OtherASME 2010 Dynamic Systems and Control Conference, DSCC2010
CountryUnited States
CityCambridge, MA
Period9/12/109/15/10

Fingerprint

Mobile robots
Feature extraction
Time series
Sensors
Dynamical systems
Robotics
Robots

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Jin, X., Mukherjee, K., Gupta, S., & Ray, A. (2010). Wavelet-based feature extraction for behavior recognition in mobile robots. In ASME 2010 Dynamic Systems and Control Conference, DSCC2010 (pp. 875-882). (ASME 2010 Dynamic Systems and Control Conference, DSCC2010; Vol. 1). https://doi.org/10.1115/DSCC2010-4059
Jin, Xin ; Mukherjee, Kushal ; Gupta, Shalabh ; Ray, Asok. / Wavelet-based feature extraction for behavior recognition in mobile robots. ASME 2010 Dynamic Systems and Control Conference, DSCC2010. 2010. pp. 875-882 (ASME 2010 Dynamic Systems and Control Conference, DSCC2010).
@inproceedings{3d7e30b1bd5d486b8b1dabe8d97a8d82,
title = "Wavelet-based feature extraction for behavior recognition in mobile robots",
abstract = "This paper introduces a dynamic data-driven method for behavior recognition in mobile robots. The core concept of the paper is built upon the principle of symbolic dynamic filtering (SDF) that is used to extract relevant information in complex dynamical systems. The objective here is to identify the robot behavior from time-series data of piezoelectric sensor signals from the pressure sensitive floor in a laboratory environment. A symbolic feature extraction method is presented by partitioning of two-dimensional wavelet images of sensor time-series data. The K-nearest neighbors (k-NN) algorithm is used to identify the patterns extracted by SDF. The proposed method is validated by experimentation on a networked robotics test bed to detect and identify the type and motion profile of mobile robots.",
author = "Xin Jin and Kushal Mukherjee and Shalabh Gupta and Asok Ray",
year = "2010",
month = "12",
day = "1",
doi = "10.1115/DSCC2010-4059",
language = "English (US)",
isbn = "9780791844175",
series = "ASME 2010 Dynamic Systems and Control Conference, DSCC2010",
pages = "875--882",
booktitle = "ASME 2010 Dynamic Systems and Control Conference, DSCC2010",

}

Jin, X, Mukherjee, K, Gupta, S & Ray, A 2010, Wavelet-based feature extraction for behavior recognition in mobile robots. in ASME 2010 Dynamic Systems and Control Conference, DSCC2010. ASME 2010 Dynamic Systems and Control Conference, DSCC2010, vol. 1, pp. 875-882, ASME 2010 Dynamic Systems and Control Conference, DSCC2010, Cambridge, MA, United States, 9/12/10. https://doi.org/10.1115/DSCC2010-4059

Wavelet-based feature extraction for behavior recognition in mobile robots. / Jin, Xin; Mukherjee, Kushal; Gupta, Shalabh; Ray, Asok.

ASME 2010 Dynamic Systems and Control Conference, DSCC2010. 2010. p. 875-882 (ASME 2010 Dynamic Systems and Control Conference, DSCC2010; Vol. 1).

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

TY - GEN

T1 - Wavelet-based feature extraction for behavior recognition in mobile robots

AU - Jin, Xin

AU - Mukherjee, Kushal

AU - Gupta, Shalabh

AU - Ray, Asok

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper introduces a dynamic data-driven method for behavior recognition in mobile robots. The core concept of the paper is built upon the principle of symbolic dynamic filtering (SDF) that is used to extract relevant information in complex dynamical systems. The objective here is to identify the robot behavior from time-series data of piezoelectric sensor signals from the pressure sensitive floor in a laboratory environment. A symbolic feature extraction method is presented by partitioning of two-dimensional wavelet images of sensor time-series data. The K-nearest neighbors (k-NN) algorithm is used to identify the patterns extracted by SDF. The proposed method is validated by experimentation on a networked robotics test bed to detect and identify the type and motion profile of mobile robots.

AB - This paper introduces a dynamic data-driven method for behavior recognition in mobile robots. The core concept of the paper is built upon the principle of symbolic dynamic filtering (SDF) that is used to extract relevant information in complex dynamical systems. The objective here is to identify the robot behavior from time-series data of piezoelectric sensor signals from the pressure sensitive floor in a laboratory environment. A symbolic feature extraction method is presented by partitioning of two-dimensional wavelet images of sensor time-series data. The K-nearest neighbors (k-NN) algorithm is used to identify the patterns extracted by SDF. The proposed method is validated by experimentation on a networked robotics test bed to detect and identify the type and motion profile of mobile robots.

UR - http://www.scopus.com/inward/record.url?scp=79958210013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958210013&partnerID=8YFLogxK

U2 - 10.1115/DSCC2010-4059

DO - 10.1115/DSCC2010-4059

M3 - Conference contribution

AN - SCOPUS:79958210013

SN - 9780791844175

T3 - ASME 2010 Dynamic Systems and Control Conference, DSCC2010

SP - 875

EP - 882

BT - ASME 2010 Dynamic Systems and Control Conference, DSCC2010

ER -

Jin X, Mukherjee K, Gupta S, Ray A. Wavelet-based feature extraction for behavior recognition in mobile robots. In ASME 2010 Dynamic Systems and Control Conference, DSCC2010. 2010. p. 875-882. (ASME 2010 Dynamic Systems and Control Conference, DSCC2010). https://doi.org/10.1115/DSCC2010-4059