A Neural-Fuzzy Framework for Modeling Car-following Behavior

A general framework is introduced to model driver behavior from real car-following data acquired on Swedish roads using an advanced instrumented vehicle. In early research, the data was classified into different car-following regimes based on fuzzy clustering methods and knowledge obtained from video analysis. In this paper, we propose a multi-regime framework based on the statistical property in each regime and mathematical models adopted in those regimes. This framework is an extension of TSK fuzzy inference system and can be expressed by a neural-fuzzy system. Genetic algorithm (GA) is designed as the main learning method for this system. In practice, this model structure illustrates human knowledge of car-following in a more understandable manner and can be rather flexible as the regime parameters and model forms may vary according to the application context.