Supervised dFasArt: A Neuro-Fuzzy Dynamic Architecture of Maneuver Detection in Road Vehicle Collision Avoidance Support Systems.

摘要

The issue of collision avoidance in road vehicles has been investigatedfrom many different points of view. An interesting approachfor Road Vehicle Collision Assistance Support Systems (RVCASS) isbased on the creation of a scene of the vehicles involved in a potentiallyconflictive traffic situation. This paper proposes a neuro-fuzzy approachfor dynamic classification of the vehicles roles in a scene. For thatpurpose, different maneuver state models for longitudinal movements ofroad vehicles have been defined, and a prototype has been equipped withINS (Inertial Navigation Systems) and GPS (Global Positioning System)sensors. Trials with real data show the suitability of the proposed neurofuzzyapproach for solving support to the problem under consideration.