An odometry-free approach for simultaneous localization and online hybrid map building

Wei Hong Chin, Chu Kiong Loo, Yuichiro Toda, Naoyuki Kubota

Research output: Contribution to journalArticle

Abstract

In this article, we propose a new approach for mobile robot localization and hybrid map building simultaneously without using any odometry hardware system. The proposed method termed as Genetic Bayesian ARAM comprises two main components: (1) steady-state genetic algorithm (SSGA) for self-localization and occupancy grid map building and (2) Bayesian Adaptive Resonance Associative Memory (ARAM) for online topological map building. The model of the explored environment is formed as a hybrid representation, both topological and grid based, and it is incrementally constructed during the exploration process. During occupancy map building, the robot-estimated self-position is updated by SSGA. At the same time, the robot-estimated self-position is transmitted to Bayesian ARAM for topological map building and localization. The effectiveness of our proposed approach is validated by a number of standardized benchmark datasets and real experimental results carried on the mobile robot. Benchmark datasets are used to verify the proposed method capable of generating topological map in different environment conditions. Real robot experiment to verify the proposed method can be implemented in real world.

Original languageEnglish
Article number68
JournalFrontiers Robotics AI
Volume3
Issue numberNOV
DOIs
Publication statusPublished - Nov 1 2016
Externally publishedYes

Fingerprint

Robots
Data storage equipment
Mobile robots
Genetic algorithms
Hardware
Experiments

Keywords

  • Bayesian
  • Genetic algorithm
  • Hybrid map
  • Mobile robot
  • Navigation
  • SLAM
  • Topological map

ASJC Scopus subject areas

  • Computer Science Applications
  • Artificial Intelligence

Cite this

An odometry-free approach for simultaneous localization and online hybrid map building. / Chin, Wei Hong; Loo, Chu Kiong; Toda, Yuichiro; Kubota, Naoyuki.

In: Frontiers Robotics AI, Vol. 3, No. NOV, 68, 01.11.2016.

Research output: Contribution to journalArticle

Chin, Wei Hong ; Loo, Chu Kiong ; Toda, Yuichiro ; Kubota, Naoyuki. / An odometry-free approach for simultaneous localization and online hybrid map building. In: Frontiers Robotics AI. 2016 ; Vol. 3, No. NOV.
@article{9b23ca8611bd4f2eabdb4d5451d76df1,
title = "An odometry-free approach for simultaneous localization and online hybrid map building",
abstract = "In this article, we propose a new approach for mobile robot localization and hybrid map building simultaneously without using any odometry hardware system. The proposed method termed as Genetic Bayesian ARAM comprises two main components: (1) steady-state genetic algorithm (SSGA) for self-localization and occupancy grid map building and (2) Bayesian Adaptive Resonance Associative Memory (ARAM) for online topological map building. The model of the explored environment is formed as a hybrid representation, both topological and grid based, and it is incrementally constructed during the exploration process. During occupancy map building, the robot-estimated self-position is updated by SSGA. At the same time, the robot-estimated self-position is transmitted to Bayesian ARAM for topological map building and localization. The effectiveness of our proposed approach is validated by a number of standardized benchmark datasets and real experimental results carried on the mobile robot. Benchmark datasets are used to verify the proposed method capable of generating topological map in different environment conditions. Real robot experiment to verify the proposed method can be implemented in real world.",
keywords = "Bayesian, Genetic algorithm, Hybrid map, Mobile robot, Navigation, SLAM, Topological map",
author = "Chin, {Wei Hong} and Loo, {Chu Kiong} and Yuichiro Toda and Naoyuki Kubota",
year = "2016",
month = "11",
day = "1",
doi = "10.3389/frobt.2016.00068",
language = "English",
volume = "3",
journal = "Frontiers Robotics AI",
issn = "2296-9144",
publisher = "Frontiers Media S. A.",
number = "NOV",

}

TY - JOUR

T1 - An odometry-free approach for simultaneous localization and online hybrid map building

AU - Chin, Wei Hong

AU - Loo, Chu Kiong

AU - Toda, Yuichiro

AU - Kubota, Naoyuki

PY - 2016/11/1

Y1 - 2016/11/1

N2 - In this article, we propose a new approach for mobile robot localization and hybrid map building simultaneously without using any odometry hardware system. The proposed method termed as Genetic Bayesian ARAM comprises two main components: (1) steady-state genetic algorithm (SSGA) for self-localization and occupancy grid map building and (2) Bayesian Adaptive Resonance Associative Memory (ARAM) for online topological map building. The model of the explored environment is formed as a hybrid representation, both topological and grid based, and it is incrementally constructed during the exploration process. During occupancy map building, the robot-estimated self-position is updated by SSGA. At the same time, the robot-estimated self-position is transmitted to Bayesian ARAM for topological map building and localization. The effectiveness of our proposed approach is validated by a number of standardized benchmark datasets and real experimental results carried on the mobile robot. Benchmark datasets are used to verify the proposed method capable of generating topological map in different environment conditions. Real robot experiment to verify the proposed method can be implemented in real world.

AB - In this article, we propose a new approach for mobile robot localization and hybrid map building simultaneously without using any odometry hardware system. The proposed method termed as Genetic Bayesian ARAM comprises two main components: (1) steady-state genetic algorithm (SSGA) for self-localization and occupancy grid map building and (2) Bayesian Adaptive Resonance Associative Memory (ARAM) for online topological map building. The model of the explored environment is formed as a hybrid representation, both topological and grid based, and it is incrementally constructed during the exploration process. During occupancy map building, the robot-estimated self-position is updated by SSGA. At the same time, the robot-estimated self-position is transmitted to Bayesian ARAM for topological map building and localization. The effectiveness of our proposed approach is validated by a number of standardized benchmark datasets and real experimental results carried on the mobile robot. Benchmark datasets are used to verify the proposed method capable of generating topological map in different environment conditions. Real robot experiment to verify the proposed method can be implemented in real world.

KW - Bayesian

KW - Genetic algorithm

KW - Hybrid map

KW - Mobile robot

KW - Navigation

KW - SLAM

KW - Topological map

UR - http://www.scopus.com/inward/record.url?scp=85061907080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061907080&partnerID=8YFLogxK

U2 - 10.3389/frobt.2016.00068

DO - 10.3389/frobt.2016.00068

M3 - Article

AN - SCOPUS:85061907080

VL - 3

JO - Frontiers Robotics AI

JF - Frontiers Robotics AI

SN - 2296-9144

IS - NOV

M1 - 68

ER -