Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces

Pejman Iravani, J H Johnson, L Rapanotti

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Robotic systems are characterised by large state and action spaces, which are problematic for learning and adapting techniques. This paper presents a method to alleviate learning dimensionality problems, by classifying similar states and actions into abstract concepts. Unlike previous techniques, concepts are generated based on the robot-environment interaction rather than being arbitrarily imposed. The validity of this method is demonstrated empirically using a real robot platform in a balltargeting task.
LanguageEnglish
Title of host publicationProceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004)
EditorsE Onaindia, S Staab
PublisherIOS Press
Volume109
ISBN (Print)978-1-58603-451-1
StatusPublished - 2004
EventProceedings of the Second Starting AI Researchers Symposium Volume 109 Frontiers in Artificial Intelligence and Applications -
Duration: 1 Jan 2004 → …

Publication series

NameFrontiers in Artificial Intelligence and Applications
PublisherIOS Press

Conference

ConferenceProceedings of the Second Starting AI Researchers Symposium Volume 109 Frontiers in Artificial Intelligence and Applications
Period1/01/04 → …

Fingerprint

Electric grounding
Robots
Robotics

Cite this

Iravani, P., Johnson, J. H., & Rapanotti, L. (2004). Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces. In E. Onaindia, & S. Staab (Eds.), Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004) (Vol. 109). (Frontiers in Artificial Intelligence and Applications). IOS Press.

Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces. / Iravani, Pejman; Johnson, J H; Rapanotti, L.

Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004). ed. / E Onaindia; S Staab. Vol. 109 IOS Press, 2004. (Frontiers in Artificial Intelligence and Applications).

Research output: Chapter in Book/Report/Conference proceedingChapter

Iravani, P, Johnson, JH & Rapanotti, L 2004, Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces. in E Onaindia & S Staab (eds), Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004). vol. 109, Frontiers in Artificial Intelligence and Applications, IOS Press, Proceedings of the Second Starting AI Researchers Symposium Volume 109 Frontiers in Artificial Intelligence and Applications, 1/01/04.
Iravani P, Johnson JH, Rapanotti L. Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces. In Onaindia E, Staab S, editors, Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004). Vol. 109. IOS Press. 2004. (Frontiers in Artificial Intelligence and Applications).
Iravani, Pejman ; Johnson, J H ; Rapanotti, L. / Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces. Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004). editor / E Onaindia ; S Staab. Vol. 109 IOS Press, 2004. (Frontiers in Artificial Intelligence and Applications).
@inbook{b90c87fb84aa46f0ad787dc2a02556ab,
title = "Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces",
abstract = "Robotic systems are characterised by large state and action spaces, which are problematic for learning and adapting techniques. This paper presents a method to alleviate learning dimensionality problems, by classifying similar states and actions into abstract concepts. Unlike previous techniques, concepts are generated based on the robot-environment interaction rather than being arbitrarily imposed. The validity of this method is demonstrated empirically using a real robot platform in a balltargeting task.",
author = "Pejman Iravani and Johnson, {J H} and L Rapanotti",
year = "2004",
language = "English",
isbn = "978-1-58603-451-1",
volume = "109",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
editor = "E Onaindia and S Staab",
booktitle = "Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004)",
address = "Netherlands",

}

TY - CHAP

T1 - Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces

AU - Iravani, Pejman

AU - Johnson, J H

AU - Rapanotti, L

PY - 2004

Y1 - 2004

N2 - Robotic systems are characterised by large state and action spaces, which are problematic for learning and adapting techniques. This paper presents a method to alleviate learning dimensionality problems, by classifying similar states and actions into abstract concepts. Unlike previous techniques, concepts are generated based on the robot-environment interaction rather than being arbitrarily imposed. The validity of this method is demonstrated empirically using a real robot platform in a balltargeting task.

AB - Robotic systems are characterised by large state and action spaces, which are problematic for learning and adapting techniques. This paper presents a method to alleviate learning dimensionality problems, by classifying similar states and actions into abstract concepts. Unlike previous techniques, concepts are generated based on the robot-environment interaction rather than being arbitrarily imposed. The validity of this method is demonstrated empirically using a real robot platform in a balltargeting task.

M3 - Chapter

SN - 978-1-58603-451-1

VL - 109

T3 - Frontiers in Artificial Intelligence and Applications

BT - Proceedings of the Second Starting AI Researchers’ Symposium (STAIRS 2004)

A2 - Onaindia, E

A2 - Staab, S

PB - IOS Press

ER -