Path planning in outdoor pedestrian settings using 2d digital maps

Ahmed Farid, Takafumi Matsumaru

Research output: Contribution to journalArticle

Abstract

In this article, a framework for planning sidewalkwise paths in data-limited pedestrian environments is presented by visually recognizing city blocks in 2D digital maps (e.g., Google Maps, and OpenStreet Maps) using contour detection, and by then applying graph theory to infer a pedestrian path from start to finish. Two main problems have been identified; first, several locations worldwide (e.g., suburban/rural areas) lack recorded data on street crossings and pedestrian walkways. Second, the continuous process of recording maps (i.e., digital cartography) is, to our current knowledge, manual and has not yet been fully automated in practice. Both issues contribute toward a scaling problem, in which the continuous monitoring and recording of such data at a global scale becomes time and effort consuming. As a result, the purpose of this framework is to produce path plans that do not depend on pre-recorded (e.g., using simultaneous localization and mapping (SLAM)) or data-rich pedestrian maps, thus facilitating navigation for mobile robots and people with visual impairment. Assuming that all roads are crossable, the framework was able to produce pedestrian paths for most locations where data on sidewalks and street crossings were indeed limited at 75% accuracy in our test-set, but certain challenges still remain to attain higher accuracy and to match real-world settings. Additionally, we describe certain works in the literature that describe how to utilize such path plans effectively.

Original languageEnglish
Pages (from-to)464-473
Number of pages10
JournalJournal of Robotics and Mechatronics
Volume31
Issue number3
DOIs
Publication statusPublished - 2019 Jun 1

Fingerprint

Motion planning
Graph theory
Mobile robots
Navigation
Monitoring

Keywords

  • Digital maps
  • Mobile robots
  • Navigation
  • Path planning
  • Pedestrian outdoors

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Path planning in outdoor pedestrian settings using 2d digital maps. / Farid, Ahmed; Matsumaru, Takafumi.

In: Journal of Robotics and Mechatronics, Vol. 31, No. 3, 01.06.2019, p. 464-473.

Research output: Contribution to journalArticle

@article{0e5f32fbcb364d4399071698f8b142be,
title = "Path planning in outdoor pedestrian settings using 2d digital maps",
abstract = "In this article, a framework for planning sidewalkwise paths in data-limited pedestrian environments is presented by visually recognizing city blocks in 2D digital maps (e.g., Google Maps, and OpenStreet Maps) using contour detection, and by then applying graph theory to infer a pedestrian path from start to finish. Two main problems have been identified; first, several locations worldwide (e.g., suburban/rural areas) lack recorded data on street crossings and pedestrian walkways. Second, the continuous process of recording maps (i.e., digital cartography) is, to our current knowledge, manual and has not yet been fully automated in practice. Both issues contribute toward a scaling problem, in which the continuous monitoring and recording of such data at a global scale becomes time and effort consuming. As a result, the purpose of this framework is to produce path plans that do not depend on pre-recorded (e.g., using simultaneous localization and mapping (SLAM)) or data-rich pedestrian maps, thus facilitating navigation for mobile robots and people with visual impairment. Assuming that all roads are crossable, the framework was able to produce pedestrian paths for most locations where data on sidewalks and street crossings were indeed limited at 75{\%} accuracy in our test-set, but certain challenges still remain to attain higher accuracy and to match real-world settings. Additionally, we describe certain works in the literature that describe how to utilize such path plans effectively.",
keywords = "Digital maps, Mobile robots, Navigation, Path planning, Pedestrian outdoors",
author = "Ahmed Farid and Takafumi Matsumaru",
year = "2019",
month = "6",
day = "1",
doi = "10.20965/jrm.2019.p0464",
language = "English",
volume = "31",
pages = "464--473",
journal = "Journal of Robotics and Mechatronics",
issn = "0915-3942",
publisher = "Fuji Technology Press",
number = "3",

}

TY - JOUR

T1 - Path planning in outdoor pedestrian settings using 2d digital maps

AU - Farid, Ahmed

AU - Matsumaru, Takafumi

PY - 2019/6/1

Y1 - 2019/6/1

N2 - In this article, a framework for planning sidewalkwise paths in data-limited pedestrian environments is presented by visually recognizing city blocks in 2D digital maps (e.g., Google Maps, and OpenStreet Maps) using contour detection, and by then applying graph theory to infer a pedestrian path from start to finish. Two main problems have been identified; first, several locations worldwide (e.g., suburban/rural areas) lack recorded data on street crossings and pedestrian walkways. Second, the continuous process of recording maps (i.e., digital cartography) is, to our current knowledge, manual and has not yet been fully automated in practice. Both issues contribute toward a scaling problem, in which the continuous monitoring and recording of such data at a global scale becomes time and effort consuming. As a result, the purpose of this framework is to produce path plans that do not depend on pre-recorded (e.g., using simultaneous localization and mapping (SLAM)) or data-rich pedestrian maps, thus facilitating navigation for mobile robots and people with visual impairment. Assuming that all roads are crossable, the framework was able to produce pedestrian paths for most locations where data on sidewalks and street crossings were indeed limited at 75% accuracy in our test-set, but certain challenges still remain to attain higher accuracy and to match real-world settings. Additionally, we describe certain works in the literature that describe how to utilize such path plans effectively.

AB - In this article, a framework for planning sidewalkwise paths in data-limited pedestrian environments is presented by visually recognizing city blocks in 2D digital maps (e.g., Google Maps, and OpenStreet Maps) using contour detection, and by then applying graph theory to infer a pedestrian path from start to finish. Two main problems have been identified; first, several locations worldwide (e.g., suburban/rural areas) lack recorded data on street crossings and pedestrian walkways. Second, the continuous process of recording maps (i.e., digital cartography) is, to our current knowledge, manual and has not yet been fully automated in practice. Both issues contribute toward a scaling problem, in which the continuous monitoring and recording of such data at a global scale becomes time and effort consuming. As a result, the purpose of this framework is to produce path plans that do not depend on pre-recorded (e.g., using simultaneous localization and mapping (SLAM)) or data-rich pedestrian maps, thus facilitating navigation for mobile robots and people with visual impairment. Assuming that all roads are crossable, the framework was able to produce pedestrian paths for most locations where data on sidewalks and street crossings were indeed limited at 75% accuracy in our test-set, but certain challenges still remain to attain higher accuracy and to match real-world settings. Additionally, we describe certain works in the literature that describe how to utilize such path plans effectively.

KW - Digital maps

KW - Mobile robots

KW - Navigation

KW - Path planning

KW - Pedestrian outdoors

UR - http://www.scopus.com/inward/record.url?scp=85070495227&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070495227&partnerID=8YFLogxK

U2 - 10.20965/jrm.2019.p0464

DO - 10.20965/jrm.2019.p0464

M3 - Article

AN - SCOPUS:85070495227

VL - 31

SP - 464

EP - 473

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

SN - 0915-3942

IS - 3

ER -