Research on Classification of Intelligent Robotic Architecture

摘要

It is a hot issue that how to determine the appropriate architecture for building an Intelligent Robot System (IRS). The architecture includes information processing and control system, which ensures reasonable coordination, openness, and scalability of robotic system. Unlike the architecture of computer, the design of a robotic system is so complex that it is difficult to seek systematic analysis methods due to its interdisciplinary nature despite it has built and experimented popularly. The typical reference architecture in the past 30 years are classified and summed up systematically in this paper from the AI robotics and systems analysis perspective. And then the new integrated approaches of conceptual and open physical design model for IRS are presented. In addition, six new common principles for designing architecture of IRS are proposed exploringly on the basis of previous classified research. These methodologies will provide some design guidelines for continuing to refine and improve the existing IRS. Finally, the rationality and feasibility of using these methods is concluded.