Abstract
We present a framework for autonomous behaviour in vision based artificial cognitive systems by imitation through coupled percept-action (stimulus and response) exemplars. Attributed Relational Graphs (ARGs) are used as a symbolic representation of scene information (percepts). A measure of similarity between ARGs is implemented with the use of a graph isomorphism algorithm and is used to hierarchically group the percepts. By hierarchically grouping percept exemplars into progressively more general models coupled to progressively more general Gaussian action models, we attempt to model the percept space and create a direct mapping to associated actions. The system is built on a simulated shape sorter puzzle that represents a robust vision system. Spatio temporal hypothesis exploration is performed ef- ficiently in a Bayesian framework using a particle filter to propagate game play over time.