Computationally efficient algorithm for vision-based simultaneous localization and mapping of mobile robots

Chen Chien Hsu, Cheng Kai Yang, Yi Hsing Chien, Yin Tien Wang, Wei Yen Wang, Chiang Heng Chien

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Purpose: FastSLAM is a popular method to solve the problem of simultaneous localization and mapping (SLAM). However, when the number of landmarks present in real environments increases, there are excessive comparisons of the measurement with all the existing landmarks in each particle. As a result, the execution speed will be too slow to achieve the objective of real-time navigation. Thus, this paper aims to improve the computational efficiency and estimation accuracy of conventional SLAM algorithms. Design/methodology/approach: As an attempt to solve this problem, this paper presents a computationally efficient SLAM (CESLAM) algorithm, where odometer information is considered for updating the robot's pose in particles. When a measurement has a maximum likelihood with the known landmark in the particle, the particle state is updated before updating the landmark estimates. Findings: Simulation results show that the proposed CESLAM can overcome the problem of heavy computational burden while improving the accuracy of localization and mapping building. To practically evaluate the performance of the proposed method, a Pioneer 3-DX robot with a Kinect sensor is used to develop an RGB-D-based computationally efficient visual SLAM (CEVSLAM) based on Speeded-Up Robust Features (SURF). Experimental results confirm that the proposed CEVSLAM system is capable of successfully estimating the robot pose and building the map with satisfactory accuracy. Originality/value: The proposed CESLAM algorithm overcomes the problem of the time-consuming process because of unnecessary comparisons in existing FastSLAM algorithms. Simulations show that accuracy of robot pose and landmark estimation is greatly improved by the CESLAM. Combining CESLAM and SURF, the authors establish a CEVSLAM to significantly improve the estimation accuracy and computational efficiency. Practical experiments by using a Kinect visual sensor show that the variance and average error by using the proposed CEVSLAM are smaller than those by using the other visual SLAM algorithms.

Original languageEnglish
Pages (from-to)1217-1239
Number of pages23
JournalEngineering Computations (Swansea, Wales)
Volume34
Issue number4
DOIs
Publication statusPublished - 2017

Fingerprint

Mobile robots
Robots
Computational efficiency
Sensors
Maximum likelihood
Navigation
Experiments

Keywords

  • FastSLAM
  • Simultaneous localization and mapping
  • SLAM
  • SURF
  • Visual SLAM

ASJC Scopus subject areas

  • Software
  • Engineering(all)
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Computationally efficient algorithm for vision-based simultaneous localization and mapping of mobile robots. / Hsu, Chen Chien; Yang, Cheng Kai; Chien, Yi Hsing; Wang, Yin Tien; Wang, Wei Yen; Chien, Chiang Heng.

In: Engineering Computations (Swansea, Wales), Vol. 34, No. 4, 2017, p. 1217-1239.

Research output: Contribution to journalArticle

Hsu, Chen Chien ; Yang, Cheng Kai ; Chien, Yi Hsing ; Wang, Yin Tien ; Wang, Wei Yen ; Chien, Chiang Heng. / Computationally efficient algorithm for vision-based simultaneous localization and mapping of mobile robots. In: Engineering Computations (Swansea, Wales). 2017 ; Vol. 34, No. 4. pp. 1217-1239.
@article{225d6ae59cd74d70a8081a9452434e47,
title = "Computationally efficient algorithm for vision-based simultaneous localization and mapping of mobile robots",
abstract = "Purpose: FastSLAM is a popular method to solve the problem of simultaneous localization and mapping (SLAM). However, when the number of landmarks present in real environments increases, there are excessive comparisons of the measurement with all the existing landmarks in each particle. As a result, the execution speed will be too slow to achieve the objective of real-time navigation. Thus, this paper aims to improve the computational efficiency and estimation accuracy of conventional SLAM algorithms. Design/methodology/approach: As an attempt to solve this problem, this paper presents a computationally efficient SLAM (CESLAM) algorithm, where odometer information is considered for updating the robot's pose in particles. When a measurement has a maximum likelihood with the known landmark in the particle, the particle state is updated before updating the landmark estimates. Findings: Simulation results show that the proposed CESLAM can overcome the problem of heavy computational burden while improving the accuracy of localization and mapping building. To practically evaluate the performance of the proposed method, a Pioneer 3-DX robot with a Kinect sensor is used to develop an RGB-D-based computationally efficient visual SLAM (CEVSLAM) based on Speeded-Up Robust Features (SURF). Experimental results confirm that the proposed CEVSLAM system is capable of successfully estimating the robot pose and building the map with satisfactory accuracy. Originality/value: The proposed CESLAM algorithm overcomes the problem of the time-consuming process because of unnecessary comparisons in existing FastSLAM algorithms. Simulations show that accuracy of robot pose and landmark estimation is greatly improved by the CESLAM. Combining CESLAM and SURF, the authors establish a CEVSLAM to significantly improve the estimation accuracy and computational efficiency. Practical experiments by using a Kinect visual sensor show that the variance and average error by using the proposed CEVSLAM are smaller than those by using the other visual SLAM algorithms.",
keywords = "FastSLAM, Simultaneous localization and mapping, SLAM, SURF, Visual SLAM",
author = "Hsu, {Chen Chien} and Yang, {Cheng Kai} and Chien, {Yi Hsing} and Wang, {Yin Tien} and Wang, {Wei Yen} and Chien, {Chiang Heng}",
year = "2017",
doi = "10.1108/EC-05-2015-0123",
language = "English",
volume = "34",
pages = "1217--1239",
journal = "Engineering Computations",
issn = "0264-4401",
publisher = "Emerald Group Publishing Ltd.",
number = "4",

}

TY - JOUR

T1 - Computationally efficient algorithm for vision-based simultaneous localization and mapping of mobile robots

AU - Hsu, Chen Chien

AU - Yang, Cheng Kai

AU - Chien, Yi Hsing

AU - Wang, Yin Tien

AU - Wang, Wei Yen

AU - Chien, Chiang Heng

PY - 2017

Y1 - 2017

N2 - Purpose: FastSLAM is a popular method to solve the problem of simultaneous localization and mapping (SLAM). However, when the number of landmarks present in real environments increases, there are excessive comparisons of the measurement with all the existing landmarks in each particle. As a result, the execution speed will be too slow to achieve the objective of real-time navigation. Thus, this paper aims to improve the computational efficiency and estimation accuracy of conventional SLAM algorithms. Design/methodology/approach: As an attempt to solve this problem, this paper presents a computationally efficient SLAM (CESLAM) algorithm, where odometer information is considered for updating the robot's pose in particles. When a measurement has a maximum likelihood with the known landmark in the particle, the particle state is updated before updating the landmark estimates. Findings: Simulation results show that the proposed CESLAM can overcome the problem of heavy computational burden while improving the accuracy of localization and mapping building. To practically evaluate the performance of the proposed method, a Pioneer 3-DX robot with a Kinect sensor is used to develop an RGB-D-based computationally efficient visual SLAM (CEVSLAM) based on Speeded-Up Robust Features (SURF). Experimental results confirm that the proposed CEVSLAM system is capable of successfully estimating the robot pose and building the map with satisfactory accuracy. Originality/value: The proposed CESLAM algorithm overcomes the problem of the time-consuming process because of unnecessary comparisons in existing FastSLAM algorithms. Simulations show that accuracy of robot pose and landmark estimation is greatly improved by the CESLAM. Combining CESLAM and SURF, the authors establish a CEVSLAM to significantly improve the estimation accuracy and computational efficiency. Practical experiments by using a Kinect visual sensor show that the variance and average error by using the proposed CEVSLAM are smaller than those by using the other visual SLAM algorithms.

AB - Purpose: FastSLAM is a popular method to solve the problem of simultaneous localization and mapping (SLAM). However, when the number of landmarks present in real environments increases, there are excessive comparisons of the measurement with all the existing landmarks in each particle. As a result, the execution speed will be too slow to achieve the objective of real-time navigation. Thus, this paper aims to improve the computational efficiency and estimation accuracy of conventional SLAM algorithms. Design/methodology/approach: As an attempt to solve this problem, this paper presents a computationally efficient SLAM (CESLAM) algorithm, where odometer information is considered for updating the robot's pose in particles. When a measurement has a maximum likelihood with the known landmark in the particle, the particle state is updated before updating the landmark estimates. Findings: Simulation results show that the proposed CESLAM can overcome the problem of heavy computational burden while improving the accuracy of localization and mapping building. To practically evaluate the performance of the proposed method, a Pioneer 3-DX robot with a Kinect sensor is used to develop an RGB-D-based computationally efficient visual SLAM (CEVSLAM) based on Speeded-Up Robust Features (SURF). Experimental results confirm that the proposed CEVSLAM system is capable of successfully estimating the robot pose and building the map with satisfactory accuracy. Originality/value: The proposed CESLAM algorithm overcomes the problem of the time-consuming process because of unnecessary comparisons in existing FastSLAM algorithms. Simulations show that accuracy of robot pose and landmark estimation is greatly improved by the CESLAM. Combining CESLAM and SURF, the authors establish a CEVSLAM to significantly improve the estimation accuracy and computational efficiency. Practical experiments by using a Kinect visual sensor show that the variance and average error by using the proposed CEVSLAM are smaller than those by using the other visual SLAM algorithms.

KW - FastSLAM

KW - Simultaneous localization and mapping

KW - SLAM

KW - SURF

KW - Visual SLAM

UR - http://www.scopus.com/inward/record.url?scp=85021787284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021787284&partnerID=8YFLogxK

U2 - 10.1108/EC-05-2015-0123

DO - 10.1108/EC-05-2015-0123

M3 - Article

VL - 34

SP - 1217

EP - 1239

JO - Engineering Computations

JF - Engineering Computations

SN - 0264-4401

IS - 4

ER -