Analysis of Vehicle-Following Heterogeneity Using Self-Organizing Feature Maps

Abstract EN

A self-organizing feature map (SOM) was used to represent vehicle-following and to analyze the heterogeneities in vehicle-following behavior.

The SOM was constructed in such a way that the prototype vectors represented vehicle-following stimuli (the follower’s velocity, relative velocity, and gap) while the output signals represented the response (the follower’s acceleration).

Vehicle trajectories collected at a northbound segment of Interstate 80 Freeway at Emeryville, CA, were used to train the SOM.

The trajectory information of two selected pairs of passenger cars was then fed into the trained SOM to identify similar stimuli experienced by the followers.

The observed responses, when the stimuli were classified by the SOM into the same category, were compared to discover the interdriver heterogeneity.

The acceleration profile of another passenger car was analyzed in the same fashion to observe the interdriver heterogeneity.

The distribution of responses derived from data sets of car-following-car and car-following-truck, respectively, was compared to ascertain inter-vehicle-type heterogeneity.