RCS: An Intelligent Agent Architecture

RCS (Real-time Control System) is an intelligent agent architecture designed to enable any level of intelligent behavior, up to and including human levels of performance. RCS was inspired 30 years ago by a theoretical model of the cerebellum, the portion of the brain responsible for fine motor coordination and control of conscious motions. It was originally designed for sensory-interactive goaldirected control of laboratory manipulators. Over three decades, it has evolved into a real-time control architecture for intelligent machine tools, factory automation systems, and intelligent autonomous vehicles. In this paper, we describe the 4D/RCS architecture, how it relates to other popular intelligent agent architectures, how it addresses the three most significant theoretical arguments against intelligent agent architectures, and its underlying engineering methodology. Interest in intelligent agent architectures has grown rapidly over the past two decades as a result of a confluence of three important events