Automatic path learning of an autonomous vehicle

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

The automation level and flexibility of an autonomous test vehicle was increased by developing a teaching method that enables the vehicle to enter a partially unknown office environment, to learn its path automatically and to repeat it.The method was based on a coarse task description, consisting of simple motion primitives described by a motion control language developed for mobile robots.Natural landmarks were utilized as beacons to reduce the accumulative error in the estimates of position and heading maintained by dead reckoning navigation.The beacons were detected by ultrasonic sensors mounted on the vehicle.Distance travelled was measured by optical encoders and heading by a fibre optical gyroscope.Real-time obstacle avoidance was developed as basic ability to manoeuvre in a coarsely known environment.When the perceived obstacle was avoided, the vehicle was able to rejoin the original reference path.Obstacles were detected by a laser scanner based on a time-of-flight principle.The test results were encouraging and considered as a good base for further research and development in the field of autonomous navigation in a coarsely known environment.
Original languageEnglish
Title of host publicationSTeP 2000 : Millennium of Artificial Intelligence
Subtitle of host publication'AI of today' : symposium on applications
EditorsHeikki Hyötyniemi
Place of PublicationEspoo
Volume2
Publication statusPublished - 2000
MoE publication typeA4 Article in a conference publication
Event9th Finnish Artificial Intelligence Conference - Espoo, Finland
Duration: 28 Aug 200030 Aug 2000
Conference number: 9

Publication series

SeriesPublications of the Finnish Artificial Intelligence Society. Conference Series
Volume16
ISSN1238-4658

Conference

Conference9th Finnish Artificial Intelligence Conference
CountryFinland
CityEspoo
Period28/08/0030/08/00

Fingerprint

Navigation
Ultrasonic sensors
Gyroscopes
Motion control
Collision avoidance
Mobile robots
Optical fibers
Teaching
Automation
Lasers

Cite this

Blom, M., Kaarmila, P., & Lehtinen, H. (2000). Automatic path learning of an autonomous vehicle. In H. Hyötyniemi (Ed.), STeP 2000 : Millennium of Artificial Intelligence: 'AI of today' : symposium on applications (Vol. 2). Espoo. Publications of the Finnish Artificial Intelligence Society. Conference Series, Vol.. 16
Blom, Marko ; Kaarmila, Petri ; Lehtinen, Hannu. / Automatic path learning of an autonomous vehicle. STeP 2000 : Millennium of Artificial Intelligence: 'AI of today' : symposium on applications. editor / Heikki Hyötyniemi. Vol. 2 Espoo, 2000. (Publications of the Finnish Artificial Intelligence Society. Conference Series, Vol. 16).
@inproceedings{facaf9dd2bca4b17bb6a816af1e8d28c,
title = "Automatic path learning of an autonomous vehicle",
abstract = "The automation level and flexibility of an autonomous test vehicle was increased by developing a teaching method that enables the vehicle to enter a partially unknown office environment, to learn its path automatically and to repeat it.The method was based on a coarse task description, consisting of simple motion primitives described by a motion control language developed for mobile robots.Natural landmarks were utilized as beacons to reduce the accumulative error in the estimates of position and heading maintained by dead reckoning navigation.The beacons were detected by ultrasonic sensors mounted on the vehicle.Distance travelled was measured by optical encoders and heading by a fibre optical gyroscope.Real-time obstacle avoidance was developed as basic ability to manoeuvre in a coarsely known environment.When the perceived obstacle was avoided, the vehicle was able to rejoin the original reference path.Obstacles were detected by a laser scanner based on a time-of-flight principle.The test results were encouraging and considered as a good base for further research and development in the field of autonomous navigation in a coarsely known environment.",
author = "Marko Blom and Petri Kaarmila and Hannu Lehtinen",
note = "Project: A9SU00020",
year = "2000",
language = "English",
isbn = "951-22-5128-0",
volume = "2",
series = "Publications of the Finnish Artificial Intelligence Society. Conference Series",
editor = "Heikki Hy{\"o}tyniemi",
booktitle = "STeP 2000 : Millennium of Artificial Intelligence",

}

Blom, M, Kaarmila, P & Lehtinen, H 2000, Automatic path learning of an autonomous vehicle. in H Hyötyniemi (ed.), STeP 2000 : Millennium of Artificial Intelligence: 'AI of today' : symposium on applications. vol. 2, Espoo, Publications of the Finnish Artificial Intelligence Society. Conference Series, vol. 16, 9th Finnish Artificial Intelligence Conference , Espoo, Finland, 28/08/00.

Automatic path learning of an autonomous vehicle. / Blom, Marko; Kaarmila, Petri; Lehtinen, Hannu.

STeP 2000 : Millennium of Artificial Intelligence: 'AI of today' : symposium on applications. ed. / Heikki Hyötyniemi. Vol. 2 Espoo, 2000. (Publications of the Finnish Artificial Intelligence Society. Conference Series, Vol. 16).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Automatic path learning of an autonomous vehicle

AU - Blom, Marko

AU - Kaarmila, Petri

AU - Lehtinen, Hannu

N1 - Project: A9SU00020

PY - 2000

Y1 - 2000

N2 - The automation level and flexibility of an autonomous test vehicle was increased by developing a teaching method that enables the vehicle to enter a partially unknown office environment, to learn its path automatically and to repeat it.The method was based on a coarse task description, consisting of simple motion primitives described by a motion control language developed for mobile robots.Natural landmarks were utilized as beacons to reduce the accumulative error in the estimates of position and heading maintained by dead reckoning navigation.The beacons were detected by ultrasonic sensors mounted on the vehicle.Distance travelled was measured by optical encoders and heading by a fibre optical gyroscope.Real-time obstacle avoidance was developed as basic ability to manoeuvre in a coarsely known environment.When the perceived obstacle was avoided, the vehicle was able to rejoin the original reference path.Obstacles were detected by a laser scanner based on a time-of-flight principle.The test results were encouraging and considered as a good base for further research and development in the field of autonomous navigation in a coarsely known environment.

AB - The automation level and flexibility of an autonomous test vehicle was increased by developing a teaching method that enables the vehicle to enter a partially unknown office environment, to learn its path automatically and to repeat it.The method was based on a coarse task description, consisting of simple motion primitives described by a motion control language developed for mobile robots.Natural landmarks were utilized as beacons to reduce the accumulative error in the estimates of position and heading maintained by dead reckoning navigation.The beacons were detected by ultrasonic sensors mounted on the vehicle.Distance travelled was measured by optical encoders and heading by a fibre optical gyroscope.Real-time obstacle avoidance was developed as basic ability to manoeuvre in a coarsely known environment.When the perceived obstacle was avoided, the vehicle was able to rejoin the original reference path.Obstacles were detected by a laser scanner based on a time-of-flight principle.The test results were encouraging and considered as a good base for further research and development in the field of autonomous navigation in a coarsely known environment.

M3 - Conference article in proceedings

SN - 951-22-5128-0

VL - 2

T3 - Publications of the Finnish Artificial Intelligence Society. Conference Series

BT - STeP 2000 : Millennium of Artificial Intelligence

A2 - Hyötyniemi, Heikki

CY - Espoo

ER -

Blom M, Kaarmila P, Lehtinen H. Automatic path learning of an autonomous vehicle. In Hyötyniemi H, editor, STeP 2000 : Millennium of Artificial Intelligence: 'AI of today' : symposium on applications. Vol. 2. Espoo. 2000. (Publications of the Finnish Artificial Intelligence Society. Conference Series, Vol. 16).