Interactive intelligent collision avoidance control: Theory and experiments

This paper presents an adaptive neuro-fuzzy inference system (ANFIS) of Takagi-Sugeno type for collision avoidance via inter-vehicular communication and practical implementation on two scaled down prototype vehicles. The key feature of the control algorithm is that the vehicles on course of an imminent collision communicate with each other and cooperatively take collision evasive maneuvers using a simple master-slave mechanism. The issues related to prototype realization, sensor integration, and practical implementation will be presented. The ANFIS-based algorithm has been extensively tested and validated for various collision scenarios. Experimental results and related issues further extend the understanding and credibility of this novel concept for interactive intelligent collision avoidance of smart ground vehicles.