A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments

Hasan Kivrak; Furkan Cakmak; Hatice Kose; Sirma Yavuz

doi:10.1109/INISTA49547.2020.9194617

A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments

Hasan Kivrak, Furkan Cakmak, Hatice Kose, Sirma Yavuz

Department of Artificial Intelligence and Data Engineering

Istanbul Technical University

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

2 Citations (Scopus)

Abstract

Social robot navigation aims to generate human-friendly paths in human-robot interactive environments. This paper focuses on maintaining humans' physical safety and mental comfort during robot navigation in an unknown dynamic environment. To achieve this goal, we use a variant of a pedestrian model that is particularly developed for low or average density environments. Design decisions on the representation of the obstacle and pedestrian are important for smooth motion planning. Limiting the local obstacles as a region centered at the robot would be taken into consideration has weaknesses in terms of time complexity because a much detailed map has a great number of cells to be evaluated. The study contributes to the theoretical field with extensions such as the development of the obstacle representation model which aims to overcome the computational cost of the current solutions for smooth motion planning which can be a bottleneck for the entire system. The proposed method is tested on a physical mobile robot in hallway scenario both in real-world environment and simulation, and its success is experimentally shown.

Original language	English
Title of host publication	INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings
Editors	Mirjana Ivanovic, Tulay Yildirim, Goce Trajcevski, Costin Badica, Ladjel Bellatreche, Igor Kotenko, Amelia Badica, Burcu Erkmen, Milos Savic
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728167992
DOIs	https://doi.org/10.1109/INISTA49547.2020.9194617
Publication status	Published - Aug 2020
Event	2020 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2020 - Novi Sad, Serbia Duration: 24 Aug 2020 → 26 Aug 2020

Publication series

Name	INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings

Conference

Conference	2020 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2020
Country/Territory	Serbia
City	Novi Sad
Period	24/08/20 → 26/08/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Funding

1Computer Engineering Department, Karabuk University, Karabuk, Turkey [email protected] 2Computer Engineering Department, Istanbul Technical University, Istanbul, Turkey {kivrakh, hatice.kose}@itu.edu.tr 3Computer Engineering Department, Yildiz Technical University, Istanbul, Turkey {fcakmak, smyavuz}@yildiz.edu.tr *This work is supported by The Scientific and Technological Research Council of Turkey (TUBITAK) under the Grant number 118E214, and Yildiz Technical University Scientific Research Project, Project No: FDK-2017-3044 978-1-7281-6799-2/20/$31.00 ©c 2020 IEEE

Funders	Funder number
TUBITAK	118E214
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu
Yildiz Teknik Üniversitesi	FDK-2017-3044 978-1-7281-6799-2/20

Keywords

human-robot interaction
mobile service robots
socially aware robot navigation

Access to Document

10.1109/INISTA49547.2020.9194617

Cite this

Kivrak, H., Cakmak, F., Kose, H., & Yavuz, S. (2020). A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments. In M. Ivanovic, T. Yildirim, G. Trajcevski, C. Badica, L. Bellatreche, I. Kotenko, A. Badica, B. Erkmen, & M. Savic (Eds.), INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings Article 9194617 (INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INISTA49547.2020.9194617

Kivrak, Hasan ; Cakmak, Furkan ; Kose, Hatice et al. / A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments. INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings. editor / Mirjana Ivanovic ; Tulay Yildirim ; Goce Trajcevski ; Costin Badica ; Ladjel Bellatreche ; Igor Kotenko ; Amelia Badica ; Burcu Erkmen ; Milos Savic. Institute of Electrical and Electronics Engineers Inc., 2020. (INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings).

@inproceedings{fc3ff0de960b4ac28bee7c4ea9e17db8,

title = "A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments",

abstract = "Social robot navigation aims to generate human-friendly paths in human-robot interactive environments. This paper focuses on maintaining humans' physical safety and mental comfort during robot navigation in an unknown dynamic environment. To achieve this goal, we use a variant of a pedestrian model that is particularly developed for low or average density environments. Design decisions on the representation of the obstacle and pedestrian are important for smooth motion planning. Limiting the local obstacles as a region centered at the robot would be taken into consideration has weaknesses in terms of time complexity because a much detailed map has a great number of cells to be evaluated. The study contributes to the theoretical field with extensions such as the development of the obstacle representation model which aims to overcome the computational cost of the current solutions for smooth motion planning which can be a bottleneck for the entire system. The proposed method is tested on a physical mobile robot in hallway scenario both in real-world environment and simulation, and its success is experimentally shown.",

keywords = "human-robot interaction, mobile service robots, socially aware robot navigation",

author = "Hasan Kivrak and Furkan Cakmak and Hatice Kose and Sirma Yavuz",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2020 ; Conference date: 24-08-2020 Through 26-08-2020",

year = "2020",

month = aug,

doi = "10.1109/INISTA49547.2020.9194617",

language = "English",

series = "INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings",

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

editor = "Mirjana Ivanovic and Tulay Yildirim and Goce Trajcevski and Costin Badica and Ladjel Bellatreche and Igor Kotenko and Amelia Badica and Burcu Erkmen and Milos Savic",

booktitle = "INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings",

address = "United States",

}

Kivrak, H, Cakmak, F, Kose, H & Yavuz, S 2020, A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments. in M Ivanovic, T Yildirim, G Trajcevski, C Badica, L Bellatreche, I Kotenko, A Badica, B Erkmen & M Savic (eds), INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings., 9194617, INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings, Institute of Electrical and Electronics Engineers Inc., 2020 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2020, Novi Sad, Serbia, 24/08/20. https://doi.org/10.1109/INISTA49547.2020.9194617

A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments. / Kivrak, Hasan; Cakmak, Furkan; Kose, Hatice et al.
INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings. ed. / Mirjana Ivanovic; Tulay Yildirim; Goce Trajcevski; Costin Badica; Ladjel Bellatreche; Igor Kotenko; Amelia Badica; Burcu Erkmen; Milos Savic. Institute of Electrical and Electronics Engineers Inc., 2020. 9194617 (INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings).

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

TY - GEN

T1 - A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments

AU - Kivrak, Hasan

AU - Cakmak, Furkan

AU - Kose, Hatice

AU - Yavuz, Sirma

PY - 2020/8

Y1 - 2020/8

N2 - Social robot navigation aims to generate human-friendly paths in human-robot interactive environments. This paper focuses on maintaining humans' physical safety and mental comfort during robot navigation in an unknown dynamic environment. To achieve this goal, we use a variant of a pedestrian model that is particularly developed for low or average density environments. Design decisions on the representation of the obstacle and pedestrian are important for smooth motion planning. Limiting the local obstacles as a region centered at the robot would be taken into consideration has weaknesses in terms of time complexity because a much detailed map has a great number of cells to be evaluated. The study contributes to the theoretical field with extensions such as the development of the obstacle representation model which aims to overcome the computational cost of the current solutions for smooth motion planning which can be a bottleneck for the entire system. The proposed method is tested on a physical mobile robot in hallway scenario both in real-world environment and simulation, and its success is experimentally shown.

AB - Social robot navigation aims to generate human-friendly paths in human-robot interactive environments. This paper focuses on maintaining humans' physical safety and mental comfort during robot navigation in an unknown dynamic environment. To achieve this goal, we use a variant of a pedestrian model that is particularly developed for low or average density environments. Design decisions on the representation of the obstacle and pedestrian are important for smooth motion planning. Limiting the local obstacles as a region centered at the robot would be taken into consideration has weaknesses in terms of time complexity because a much detailed map has a great number of cells to be evaluated. The study contributes to the theoretical field with extensions such as the development of the obstacle representation model which aims to overcome the computational cost of the current solutions for smooth motion planning which can be a bottleneck for the entire system. The proposed method is tested on a physical mobile robot in hallway scenario both in real-world environment and simulation, and its success is experimentally shown.

KW - human-robot interaction

KW - mobile service robots

KW - socially aware robot navigation

UR - http://www.scopus.com/inward/record.url?scp=85092005567&partnerID=8YFLogxK

U2 - 10.1109/INISTA49547.2020.9194617

DO - 10.1109/INISTA49547.2020.9194617

M3 - Conference contribution

AN - SCOPUS:85092005567

T3 - INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings

BT - INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings

A2 - Ivanovic, Mirjana

A2 - Yildirim, Tulay

A2 - Trajcevski, Goce

A2 - Badica, Costin

A2 - Bellatreche, Ladjel

A2 - Kotenko, Igor

A2 - Badica, Amelia

A2 - Erkmen, Burcu

A2 - Savic, Milos

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2020

Y2 - 24 August 2020 through 26 August 2020

ER -

Kivrak H, Cakmak F, Kose H, Yavuz S. A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments. In Ivanovic M, Yildirim T, Trajcevski G, Badica C, Bellatreche L, Kotenko I, Badica A, Erkmen B, Savic M, editors, INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9194617. (INISTA 2020 - 2020 International Conference on INnovations in Intelligent SysTems and Applications, Proceedings). doi: 10.1109/INISTA49547.2020.9194617

A multilevel mapping based pedestrian model for social robot navigation tasks in unknown human environments

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this