Abstract: With the analyses on the advantages and disadvantages of the two typical architectures for intelligent vehicle navigation, an architecture for intelligent vehicle navigation based on activities control is presented. This architecture uses a blackboard to coordinate the interaction between modules, and classifies the activities of the intelligent vehicle into reflecting activity and voluntary activity. The reflecting activity is acti-vated by data and the voluntary activity is selected by the blackboard. The navigation task is accomplished by sequencing these activated activities. Based on the theoretic analyses, simulations are performed and their results show that the vehi-cle can efficiently follow the guide path, avoid obstacles and follow walls and road edges, and finally reach the destination. The experiment for path-guided navigation is carried out and the results are satisfying.

Key words: Architecture, Blackboard, Intelligent vehicle, Navigation