Improvement of the 2D SLAM system using Kinect sensor for indoor mapping

Muhammad Fahmi Abdul Ghani, Khairul Salleh Mohamed Sahari, Loo Chu Kiong

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

6 Citations (Scopus)

Abstract

Simultaneous localization and mapping (SLAM) is an important system for making fully autonomous robot navigation system. A robot must have a good understanding of the environment for navigation. Mobile robot using fixed laser range finder can only detect obstacle on a particular plane level. This may lead to missing of important obstacles that are both above or below the laser scan level. This will cause the map generated to be inaccurate and collision may happen during autonomous navigation. The Microsoft Kinect sensor can replace a laser range finder in a mobile robot as a low cost alternative while providing 3D data. Using depth image data from Kinect, the obstacles between ground surface and 500mm high are projected to horizontal surface, and converted to laser scan data. This will include the entire obstacles that the robot might collide into. Simulations and experiments have been conducted to test out the method in SLAM process in an indoor environment. Both simulation and experimental results show that the proposed method is capable of getting more detailed map compared to the normal 2D map.

Original languageEnglish
Title of host publication2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages776-781
Number of pages6
ISBN (Electronic)9781479959556
DOIs
Publication statusPublished - 18 Feb 2014
Event2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014 - Kitakyushu, Japan
Duration: 03 Dec 201406 Dec 2014

Other

Other2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014
CountryJapan
CityKitakyushu
Period03/12/1406/12/14

Fingerprint

Range finders
Lasers
Sensors
Robots
Mobile robots
Navigation
Navigation systems
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Ghani, M. F. A., Mohamed Sahari, K. S., & Kiong, L. C. (2014). Improvement of the 2D SLAM system using Kinect sensor for indoor mapping. In 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014 (pp. 776-781). [7044753] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCIS-ISIS.2014.7044753
Ghani, Muhammad Fahmi Abdul ; Mohamed Sahari, Khairul Salleh ; Kiong, Loo Chu. / Improvement of the 2D SLAM system using Kinect sensor for indoor mapping. 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 776-781
@inproceedings{7cc6716623b84deda36f7a261430357c,
title = "Improvement of the 2D SLAM system using Kinect sensor for indoor mapping",
abstract = "Simultaneous localization and mapping (SLAM) is an important system for making fully autonomous robot navigation system. A robot must have a good understanding of the environment for navigation. Mobile robot using fixed laser range finder can only detect obstacle on a particular plane level. This may lead to missing of important obstacles that are both above or below the laser scan level. This will cause the map generated to be inaccurate and collision may happen during autonomous navigation. The Microsoft Kinect sensor can replace a laser range finder in a mobile robot as a low cost alternative while providing 3D data. Using depth image data from Kinect, the obstacles between ground surface and 500mm high are projected to horizontal surface, and converted to laser scan data. This will include the entire obstacles that the robot might collide into. Simulations and experiments have been conducted to test out the method in SLAM process in an indoor environment. Both simulation and experimental results show that the proposed method is capable of getting more detailed map compared to the normal 2D map.",
author = "Ghani, {Muhammad Fahmi Abdul} and {Mohamed Sahari}, {Khairul Salleh} and Kiong, {Loo Chu}",
year = "2014",
month = "2",
day = "18",
doi = "10.1109/SCIS-ISIS.2014.7044753",
language = "English",
pages = "776--781",
booktitle = "2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Ghani, MFA, Mohamed Sahari, KS & Kiong, LC 2014, Improvement of the 2D SLAM system using Kinect sensor for indoor mapping. in 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014., 7044753, Institute of Electrical and Electronics Engineers Inc., pp. 776-781, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014, Kitakyushu, Japan, 03/12/14. https://doi.org/10.1109/SCIS-ISIS.2014.7044753

Improvement of the 2D SLAM system using Kinect sensor for indoor mapping. / Ghani, Muhammad Fahmi Abdul; Mohamed Sahari, Khairul Salleh; Kiong, Loo Chu.

2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 776-781 7044753.

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

TY - GEN

T1 - Improvement of the 2D SLAM system using Kinect sensor for indoor mapping

AU - Ghani, Muhammad Fahmi Abdul

AU - Mohamed Sahari, Khairul Salleh

AU - Kiong, Loo Chu

PY - 2014/2/18

Y1 - 2014/2/18

N2 - Simultaneous localization and mapping (SLAM) is an important system for making fully autonomous robot navigation system. A robot must have a good understanding of the environment for navigation. Mobile robot using fixed laser range finder can only detect obstacle on a particular plane level. This may lead to missing of important obstacles that are both above or below the laser scan level. This will cause the map generated to be inaccurate and collision may happen during autonomous navigation. The Microsoft Kinect sensor can replace a laser range finder in a mobile robot as a low cost alternative while providing 3D data. Using depth image data from Kinect, the obstacles between ground surface and 500mm high are projected to horizontal surface, and converted to laser scan data. This will include the entire obstacles that the robot might collide into. Simulations and experiments have been conducted to test out the method in SLAM process in an indoor environment. Both simulation and experimental results show that the proposed method is capable of getting more detailed map compared to the normal 2D map.

AB - Simultaneous localization and mapping (SLAM) is an important system for making fully autonomous robot navigation system. A robot must have a good understanding of the environment for navigation. Mobile robot using fixed laser range finder can only detect obstacle on a particular plane level. This may lead to missing of important obstacles that are both above or below the laser scan level. This will cause the map generated to be inaccurate and collision may happen during autonomous navigation. The Microsoft Kinect sensor can replace a laser range finder in a mobile robot as a low cost alternative while providing 3D data. Using depth image data from Kinect, the obstacles between ground surface and 500mm high are projected to horizontal surface, and converted to laser scan data. This will include the entire obstacles that the robot might collide into. Simulations and experiments have been conducted to test out the method in SLAM process in an indoor environment. Both simulation and experimental results show that the proposed method is capable of getting more detailed map compared to the normal 2D map.

UR - http://www.scopus.com/inward/record.url?scp=84988269553&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988269553&partnerID=8YFLogxK

U2 - 10.1109/SCIS-ISIS.2014.7044753

DO - 10.1109/SCIS-ISIS.2014.7044753

M3 - Conference contribution

SP - 776

EP - 781

BT - 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ghani MFA, Mohamed Sahari KS, Kiong LC. Improvement of the 2D SLAM system using Kinect sensor for indoor mapping. In 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 776-781. 7044753 https://doi.org/10.1109/SCIS-ISIS.2014.7044753