A Knowledge-based System for Redundant and Multi Sensing in Intelligent Robots

An intelligent robot is considered as consisting of five components: mechanisms, computer planner, computer controller, sensory systems, and knowledge-base systems. This paper discusses various aspects of robotic sensing and the need for sensor science, and introduces the design of sensory knowledge base and the knowledge-based system approach to redundant and multi sensing. The top level of the knowledge base consists of sensors, algorithms, processor, integration, and analysis. The goals for redundant and multi sensing are explained. The architecture for redundant and multi sensing system is discussed. For achieving information integration in systems with redundant sensors, we suggest Boolean fusion, probabilistic fusion, and Markov renewal analysis in addition to geometrical fusion.