Terrain Classification for Outdoor Autonomous Robots using 2D Laser Scans.: Robot perception for dirt road navigation

Morten Rufus Blas; Søren Riisgaard; Ole Ravn; Nils Axel Andersen; Mogens Blanke; Jens Christian Andersen

Terrain Classification for Outdoor Autonomous Robots using 2D Laser Scans. Robot perception for dirt road navigation

Morten Rufus Blas, Søren Riisgaard, Ole Ravn, Nils Axel Andersen, Mogens Blanke, Jens Christian Andersen

Technical University of Denmark

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

327 Downloads (Pure)

Abstract

Interpreting laser data to allow autonomous robot navigation on paved as well as dirt roads using a fixed angle 2D laser scanner is a daunting task. This paper introduces an algorithm for terrain classification that fuses four distinctly different classifiers: raw height, step size, slope, and roughness. Input is a single 2D laser scan and output is a classification of each laser scan range reading. The range readings are classified as either returning from an obstacle (not traversable) or from traversable ground. Experimental results are shown and discussed from the implementation done with a department developed Medium Mobile Robot and tests conducted in a national park environment

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Informatics in Control, Automation and Robotics.
Publication date	2005
Pages	347-351
ISBN (Print)	972-8865-30-9
Publication status	Published - 2005
Event	2nd International Conference on Informatics in Control, Automation and Robotics - Barcelona, Spain Duration: 14 Sept 2005 → 17 Sept 2005 Conference number: 2

Conference

Conference	2nd International Conference on Informatics in Control, Automation and Robotics
Number	2
Country/Territory	Spain
City	Barcelona
Period	14/09/2005 → 17/09/2005

Keywords

Terrain classification
Obstacle detection
Road following
Laser scanner
Classifier fusion

Access to Document

Terrain categorisation using 2D laser scanner finalFinal published version, 229 KB

OpenUrl availability

Full text

Cite this

@inproceedings{e9b56dcdc2bc4b6aaa7b5b2715b390e2,

title = "Terrain Classification for Outdoor Autonomous Robots using 2D Laser Scans.: Robot perception for dirt road navigation",

abstract = "Interpreting laser data to allow autonomous robot navigation on paved as well as dirt roads using a fixed angle 2D laser scanner is a daunting task. This paper introduces an algorithm for terrain classification that fuses four distinctly different classifiers: raw height, step size, slope, and roughness. Input is a single 2D laser scan and output is a classification of each laser scan range reading. The range readings are classified as either returning from an obstacle (not traversable) or from traversable ground. Experimental results are shown and discussed from the implementation done with a department developed Medium Mobile Robot and tests conducted in a national park environment",

keywords = "Terrain classification, Obstacle detection, Road following, Laser scanner, Classifier fusion",

author = "{Rufus Blas}, Morten and S{\o}ren Riisgaard and Ole Ravn and Andersen, {Nils Axel} and Mogens Blanke and Andersen, {Jens Christian}",

year = "2005",

language = "English",

isbn = "972-8865-30-9",

pages = "347--351",

booktitle = "Proceedings of the 2nd International Conference on Informatics in Control, Automation and Robotics.",

note = "2nd International Conference on Informatics in Control, Automation and Robotics, ICINCO 2005 ; Conference date: 14-09-2005 Through 17-09-2005",

}

Rufus Blas, M, Riisgaard, S, Ravn, O , Andersen, NA , Blanke, M & Andersen, JC 2005, Terrain Classification for Outdoor Autonomous Robots using 2D Laser Scans. Robot perception for dirt road navigation. in Proceedings of the 2nd International Conference on Informatics in Control, Automation and Robotics.. pp. 347-351, 2nd International Conference on Informatics in Control, Automation and Robotics, Barcelona, Spain, 14/09/2005.

Terrain Classification for Outdoor Autonomous Robots using 2D Laser Scans. Robot perception for dirt road navigation. / Rufus Blas, Morten; Riisgaard, Søren; Ravn, Ole et al.
Proceedings of the 2nd International Conference on Informatics in Control, Automation and Robotics.. 2005. p. 347-351.

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

TY - GEN

T1 - Terrain Classification for Outdoor Autonomous Robots using 2D Laser Scans.

T2 - 2nd International Conference on Informatics in Control, Automation and Robotics

AU - Rufus Blas, Morten

AU - Riisgaard, Søren

AU - Ravn, Ole

AU - Andersen, Nils Axel

AU - Blanke, Mogens

AU - Andersen, Jens Christian

N1 - Conference code: 2

PY - 2005

Y1 - 2005

N2 - Interpreting laser data to allow autonomous robot navigation on paved as well as dirt roads using a fixed angle 2D laser scanner is a daunting task. This paper introduces an algorithm for terrain classification that fuses four distinctly different classifiers: raw height, step size, slope, and roughness. Input is a single 2D laser scan and output is a classification of each laser scan range reading. The range readings are classified as either returning from an obstacle (not traversable) or from traversable ground. Experimental results are shown and discussed from the implementation done with a department developed Medium Mobile Robot and tests conducted in a national park environment

AB - Interpreting laser data to allow autonomous robot navigation on paved as well as dirt roads using a fixed angle 2D laser scanner is a daunting task. This paper introduces an algorithm for terrain classification that fuses four distinctly different classifiers: raw height, step size, slope, and roughness. Input is a single 2D laser scan and output is a classification of each laser scan range reading. The range readings are classified as either returning from an obstacle (not traversable) or from traversable ground. Experimental results are shown and discussed from the implementation done with a department developed Medium Mobile Robot and tests conducted in a national park environment

KW - Terrain classification

KW - Obstacle detection

KW - Road following

KW - Laser scanner

KW - Classifier fusion

M3 - Article in proceedings

SN - 972-8865-30-9

SP - 347

EP - 351

BT - Proceedings of the 2nd International Conference on Informatics in Control, Automation and Robotics.

Y2 - 14 September 2005 through 17 September 2005

ER -