Intelligent System Architecture Based on System Theory

Abstract

Intelligent system is a research field that attracts much attention at present. Most of the researches on intelligent system focus on intelligent technology and its application. However, an intelligent system is first of all a system, which means it should have the characteristics of a system. Design of conventional system is mainly function- or task-oriented, and adaptation to environment is passive, static and regular. However, intelligent system is faced with a complex, random and dynamic environment, and has dynamic interaction with the environment. Behind this interaction behavior is a fusion of perception, cognition, and decision-making processes, supported by multi-source information fusion techniques. Therefore, intelligent system design needs to be oriented towards system behavior, where information fusion plays a crucial role in integrating heterogeneous data for coherent situational awareness. This paper will examine intelligent system from the perspective of system behavior characteristics, and put forward a new definition of intelligent system based on information fusion principles. The core feature of intelligent system is intelligence, which relies on advanced fusion algorithms to combine sensory inputs, knowledge, and contextual information. To construct an intelligent system, we develop a framework of five core capabilities, aligning with the traditional Chinese philosophical fusion of knowledge and action – the Unity of Knowledge and Action. Finally, we give a design case of an intelligent system (intelligent vehicle) to demonstrate the practical viability of the proposed architecture and concept, highlighting the role of multi-modal fusion in perception and decision-making.