Appearance-Based Localization of Mobile Robots Using Group LASSO Regression

Huan N. Do, Jongeun Choi, Chae Young Lim, Tapabrata Maiti

Research output: Contribution to journalArticle

Abstract

Appearance-based localization is a robot self-navigation technique that integrates visual appearance and kinematic information. To analyze the visual appearance, we need to build a regression model based on extracted visual features from raw images as predictors to estimate the robot's location in two-dimensional (2D) coordinates. Given the training data, our first problem is to find the optimal subset of the features that maximize the localization performance. To achieve appearance-based localization of a mobile robot, we propose an integrated localization model that consists of two main components: the group least absolute shrinkage and selection operator (LASSO) regression and sequential Bayesian filtering. We project the output of the LASSO regression onto the kinematics of the mobile robot via sequential Bayesian filtering. In particular, we examine two candidates for the Bayesian estimator: the extended Kalman filter (EKF) and particle filter (PF). Our method is implemented in both indoor mobile robot and outdoor vehicle equipped with an omnidirectional camera. The results validate the effectiveness of our proposed approach.

Original languageEnglish
Article number091016
JournalJournal of Dynamic Systems, Measurement and Control, Transactions of the ASME
Volume140
Issue number9
DOIs
Publication statusPublished - 2018 Sep 1

Fingerprint

robots
shrinkage
Mobile robots
regression analysis
operators
Kinematics
Robots
Extended Kalman filters
kinematics
Navigation
Cameras
Kalman filters
navigation
estimators
set theory
vehicles
education
cameras
filters
output

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Information Systems
  • Instrumentation
  • Mechanical Engineering
  • Computer Science Applications

Cite this

@article{767369c82f2b4183a8ca8697222634cc,
title = "Appearance-Based Localization of Mobile Robots Using Group LASSO Regression",
abstract = "Appearance-based localization is a robot self-navigation technique that integrates visual appearance and kinematic information. To analyze the visual appearance, we need to build a regression model based on extracted visual features from raw images as predictors to estimate the robot's location in two-dimensional (2D) coordinates. Given the training data, our first problem is to find the optimal subset of the features that maximize the localization performance. To achieve appearance-based localization of a mobile robot, we propose an integrated localization model that consists of two main components: the group least absolute shrinkage and selection operator (LASSO) regression and sequential Bayesian filtering. We project the output of the LASSO regression onto the kinematics of the mobile robot via sequential Bayesian filtering. In particular, we examine two candidates for the Bayesian estimator: the extended Kalman filter (EKF) and particle filter (PF). Our method is implemented in both indoor mobile robot and outdoor vehicle equipped with an omnidirectional camera. The results validate the effectiveness of our proposed approach.",
author = "Do, {Huan N.} and Jongeun Choi and Lim, {Chae Young} and Tapabrata Maiti",
year = "2018",
month = "9",
day = "1",
doi = "10.1115/1.4039286",
language = "English",
volume = "140",
journal = "Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME",
issn = "0022-0434",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "9",

}

Appearance-Based Localization of Mobile Robots Using Group LASSO Regression. / Do, Huan N.; Choi, Jongeun; Lim, Chae Young; Maiti, Tapabrata.

In: Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME, Vol. 140, No. 9, 091016, 01.09.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Appearance-Based Localization of Mobile Robots Using Group LASSO Regression

AU - Do, Huan N.

AU - Choi, Jongeun

AU - Lim, Chae Young

AU - Maiti, Tapabrata

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Appearance-based localization is a robot self-navigation technique that integrates visual appearance and kinematic information. To analyze the visual appearance, we need to build a regression model based on extracted visual features from raw images as predictors to estimate the robot's location in two-dimensional (2D) coordinates. Given the training data, our first problem is to find the optimal subset of the features that maximize the localization performance. To achieve appearance-based localization of a mobile robot, we propose an integrated localization model that consists of two main components: the group least absolute shrinkage and selection operator (LASSO) regression and sequential Bayesian filtering. We project the output of the LASSO regression onto the kinematics of the mobile robot via sequential Bayesian filtering. In particular, we examine two candidates for the Bayesian estimator: the extended Kalman filter (EKF) and particle filter (PF). Our method is implemented in both indoor mobile robot and outdoor vehicle equipped with an omnidirectional camera. The results validate the effectiveness of our proposed approach.

AB - Appearance-based localization is a robot self-navigation technique that integrates visual appearance and kinematic information. To analyze the visual appearance, we need to build a regression model based on extracted visual features from raw images as predictors to estimate the robot's location in two-dimensional (2D) coordinates. Given the training data, our first problem is to find the optimal subset of the features that maximize the localization performance. To achieve appearance-based localization of a mobile robot, we propose an integrated localization model that consists of two main components: the group least absolute shrinkage and selection operator (LASSO) regression and sequential Bayesian filtering. We project the output of the LASSO regression onto the kinematics of the mobile robot via sequential Bayesian filtering. In particular, we examine two candidates for the Bayesian estimator: the extended Kalman filter (EKF) and particle filter (PF). Our method is implemented in both indoor mobile robot and outdoor vehicle equipped with an omnidirectional camera. The results validate the effectiveness of our proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=85046542046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046542046&partnerID=8YFLogxK

U2 - 10.1115/1.4039286

DO - 10.1115/1.4039286

M3 - Article

VL - 140

JO - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

JF - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

SN - 0022-0434

IS - 9

M1 - 091016

ER -