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

Reference:

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

Related documents:

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.

Export

Actions (login required)