Learning based semantic segmentation for robot navigation in outdoor environment

Janice Lin; Wen June Wang; Sheng Kai Huang; Hsiang Chieh Chen

doi:10.1109/IFSA-SCIS.2017.8023347

Learning based semantic segmentation for robot navigation in outdoor environment

Janice Lin, Wen June Wang, Sheng Kai Huang, Hsiang Chieh Chen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

22 Scopus citations

Abstract

This work presents a vision-based navigation control strategy for a wheeled robot traveling outside. The main achievements contain road detection with deep learning and navigation control scheme of a robot. A deep convolutional neural network is first employed to perform pixel-wise segmentation and thus to find road regions. Next, a fuzzy controller is designed for commanding a robot's activities including movement and speed. Experimental results verify the essential capability of navigation by using a deep architecture of convolutional network. In brief, the proposed approach certainly reaches autonomous traveling with collision avoiding and wayfinding functionalities.

Original language	English
Title of host publication	IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509049172
DOIs	https://doi.org/10.1109/IFSA-SCIS.2017.8023347
State	Published - 30 Aug 2017
Event	17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017 - Otsu, Japan Duration: 27 Jun 2017 → 30 Jun 2017

Publication series

Name	IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems

Conference

Conference	17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017
Country/Territory	Japan
City	Otsu
Period	27/06/17 → 30/06/17

Keywords

convolutional neural network
deep learning
fuzzy control
robot navigation

Access to Document

10.1109/IFSA-SCIS.2017.8023347

An intelligent partner for the blind(1/3)
Wang, W.-J. (PI)
1/11/16 → 31/10/17
Project: Research

Cite this

Lin, J., Wang, W. J., Huang, S. K., & Chen, H. C. (2017). Learning based semantic segmentation for robot navigation in outdoor environment. In IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems Article 8023347 (IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IFSA-SCIS.2017.8023347

Lin, Janice ; Wang, Wen June ; Huang, Sheng Kai et al. / Learning based semantic segmentation for robot navigation in outdoor environment. IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems. Institute of Electrical and Electronics Engineers Inc., 2017. (IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems).

@inproceedings{0790a8f0120048e4879dcf3acfbca768,

title = "Learning based semantic segmentation for robot navigation in outdoor environment",

abstract = "This work presents a vision-based navigation control strategy for a wheeled robot traveling outside. The main achievements contain road detection with deep learning and navigation control scheme of a robot. A deep convolutional neural network is first employed to perform pixel-wise segmentation and thus to find road regions. Next, a fuzzy controller is designed for commanding a robot's activities including movement and speed. Experimental results verify the essential capability of navigation by using a deep architecture of convolutional network. In brief, the proposed approach certainly reaches autonomous traveling with collision avoiding and wayfinding functionalities.",

keywords = "convolutional neural network, deep learning, fuzzy control, robot navigation",

author = "Janice Lin and Wang, {Wen June} and Huang, {Sheng Kai} and Chen, {Hsiang Chieh}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017 ; Conference date: 27-06-2017 Through 30-06-2017",

year = "2017",

month = aug,

day = "30",

doi = "10.1109/IFSA-SCIS.2017.8023347",

language = "???core.languages.en_GB???",

series = "IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems",

}

Lin, J, Wang, WJ, Huang, SK & Chen, HC 2017, Learning based semantic segmentation for robot navigation in outdoor environment. in IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems., 8023347, IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, Institute of Electrical and Electronics Engineers Inc., 17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017, Otsu, Japan, 27/06/17. https://doi.org/10.1109/IFSA-SCIS.2017.8023347

Learning based semantic segmentation for robot navigation in outdoor environment. / Lin, Janice; Wang, Wen June; Huang, Sheng Kai et al.
IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems. Institute of Electrical and Electronics Engineers Inc., 2017. 8023347 (IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning based semantic segmentation for robot navigation in outdoor environment

AU - Lin, Janice

AU - Wang, Wen June

AU - Huang, Sheng Kai

AU - Chen, Hsiang Chieh

PY - 2017/8/30

Y1 - 2017/8/30

N2 - This work presents a vision-based navigation control strategy for a wheeled robot traveling outside. The main achievements contain road detection with deep learning and navigation control scheme of a robot. A deep convolutional neural network is first employed to perform pixel-wise segmentation and thus to find road regions. Next, a fuzzy controller is designed for commanding a robot's activities including movement and speed. Experimental results verify the essential capability of navigation by using a deep architecture of convolutional network. In brief, the proposed approach certainly reaches autonomous traveling with collision avoiding and wayfinding functionalities.

AB - This work presents a vision-based navigation control strategy for a wheeled robot traveling outside. The main achievements contain road detection with deep learning and navigation control scheme of a robot. A deep convolutional neural network is first employed to perform pixel-wise segmentation and thus to find road regions. Next, a fuzzy controller is designed for commanding a robot's activities including movement and speed. Experimental results verify the essential capability of navigation by using a deep architecture of convolutional network. In brief, the proposed approach certainly reaches autonomous traveling with collision avoiding and wayfinding functionalities.

KW - convolutional neural network

KW - deep learning

KW - fuzzy control

KW - robot navigation

UR - http://www.scopus.com/inward/record.url?scp=85030867294&partnerID=8YFLogxK

U2 - 10.1109/IFSA-SCIS.2017.8023347

DO - 10.1109/IFSA-SCIS.2017.8023347

M3 - 會議論文篇章

AN - SCOPUS:85030867294

T3 - IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems

BT - IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th Joint World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems, IFSA-SCIS 2017

Y2 - 27 June 2017 through 30 June 2017

ER -

Lin J, Wang WJ, Huang SK, Chen HC. Learning based semantic segmentation for robot navigation in outdoor environment. In IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems. Institute of Electrical and Electronics Engineers Inc. 2017. 8023347. (IFSA-SCIS 2017 - Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems). doi: 10.1109/IFSA-SCIS.2017.8023347

Learning based semantic segmentation for robot navigation in outdoor environment

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

An intelligent partner for the blind(1/3)

Cite this