Predicting Affordances from Gist

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper presents an incremental learning mechanism to create associations between the affordances provided by the environment and its gist. The proposed model aims at helping the agent on the prioritisation of its perceptual resources, and consequently on visual attention. The focus on affordances, rather than on objects, enables a self-supervised learning mechanism without assuming the existence of symbolic object representations, thus facilitating its integration on a developmental framework. The focus on affordances also contributes to our understanding on the role of sensorimotor coordination on the organisation of adaptive behaviour. Promising results are obtained with a physical experiment on a natural environment, where a camera was handled as if it was being carried by an actual robot performing obstacle avoidance, trail following and wandering behaviours.
Original languageUnknown
Title of host publicationLecture Notes in Computer Science
Pages325-334
Volume6226
DOIs
Publication statusPublished - 1 Jan 2010
Event11th International Conference on Simulation of Adaptive Behavior -
Duration: 1 Jan 2010 → …

Conference

Conference11th International Conference on Simulation of Adaptive Behavior
Period1/01/10 → …

Cite this

Barata Oliveira, J. A., & DEE Group Author (2010). Predicting Affordances from Gist. In Lecture Notes in Computer Science (Vol. 6226, pp. 325-334) https://doi.org/10.1007/978-3-642-15193-4_31