Embodiment in GLAIR: A grounded layered architecture with integrated reasoning for autonomous agents

Abstract

In order to function robustly in the world, au-tonomous agents need to assimilate concepts for physical entities and relations, grounded in perception and action. They also need to as-similate concepts for perceptual properties like color, shape, and weight, and perhaps even-tually even for nonphysical objects like uni-corns. The process of acquiring concepts that carry meaning in terms of the agent's own physiology we call embodiment. Unlike cur-rent robotic agents, those endowed with em-bodied concepts will more readily understand high level instructions. As a consequence, these robots won't have to be instructed at a