TY - JOUR AB - One of the most important abilities for an agent's cognitive development in a social environment is the ability to recognize and imitate actions of others. In this paper we describe a cognitive architecture for action recognition and imitation, and present experiments demonstrating its implementation in robots. Inspired by neuroscientific and psychological data, and adopting a ‘simulation theory of mind’ approach, the architecture uses the motor systems of the imitator in a dual role, both for generating actions, and for understanding actions when performed by others. It consists of a distributed system of inverse and forward models that uses prediction accuracy as a means to classify demonstrated actions. The architecture is also shown to be capable of learning new composite actions from demonstration. AU - Demiris,Y AU - Johnson,M DO - 10.1080/09540090310001655129 EP - 243 PY - 2003/// SN - 0954-0091 SP - 231 TI - Distributed, predictive perception of actions: a biologically inspired robotics architecture for imitation and learning T2 - Connection Science UR - http://dx.doi.org/10.1080/09540090310001655129 VL - 15 ER -