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

Pejman Iravani, J H Johnson, L Rapanotti

Research output: Chapter or section in a book/report/conference proceedingChapter or section

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.
Original 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
Publication 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

Dive into the research topics of 'Application of concept grounding techniques to reduce dimensionality in sensory-motor spaces'. Together they form a unique fingerprint.

Cite this