Gaussian Mixture Models for Affordance Learning Using Bayesian Networks

Proceedings of: IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems (IROS 2010), October 18-22, 2010, Taipe, TaiwanAffordances are fundamental descriptors of relationships between actions, objects and effects. They provide the means whereby a robot can predict effects, recognize actions, select objects and plan its behavior according to desired goals. This paper approaches the problem of an embodied agent exploring the world and learning these affordances autonomously from its sensory experiences. Models exist for learning the structure and the parameters of a Bayesian Network encoding this knowledge. Although Bayesian Networks are capable of dealing with uncertainty and redundancy, previous work considered complete observability of the discrete sensory data, which may lead to hard errors in the presence of noise. In this paper we consider a probabilistic representation of the sensors by Gaussian Mixture Models (GMMs) and explicitly taking into account the probability distribution contained in each discrete affordance concept, which can lead to a more correct learning.European Community's Seventh Framework ProgramThis work has been partly supported by PTDC/EEAACR/70174/2006, grant SFRH/BPD/48857/2008 from FCT and EU projects HANDLE and FIRST-MM