Toward vision-based intelligent navigator: its concept and prototype

This paper proposes a novel concept of intelligent navigator that can give the driver timely advice on safe and efficient driving. From both the current traffic condition obtained from visual data and the driver’s goal and preference in driving, it autonomously generates advice and give it to the driver. Not only operational level advice, such as emergency braking due to an abrupt deceleration of the front vehicle, but also tactical level advice, such as lane changing due to the congested situation ahead, can be generated. Two main components of the intelligent navigator, the advice generation system and the road scene recognition system, are explained. A Three-level reasoning architecture is proposed for generating advice in dynamic and uncertain traffic environments. On-line experiments using the prototype system show the potential feasibility of the proposed concept. Keywords—ITS, intelligent navigator, visual recognition of traffic scene, hierarchical reasoning architecture.