Modeling Drivers’ Strategy When Overtaking Cyclists in the Presence of Oncoming Traffic

Overtaking a cyclist on two-lane rural road with oncoming traffic is challenging task for any driver. Failing this can lead to severe injuries or even death because of the potentially high impact speed in possible collision. To avoid rear-end collision cyclist, drivers need make timely and accurate decision about whether steer overtake brake let pass first. If delayed, instance driver distracted, neither braking nor steering may eventually keep from crashing—at that point, rear-ending be safest alternative Active safety systems such as forward warning help being alert avoiding collisions enhanced models reduce activations perceived false positive. In study, we developed model based logistic regression using data test-track experiment. The predict probability confidence while approaching during an overtaking, therefore improve systems. both in-sample out-of-sample evaluation, identified drivers’ intent accuracy (0.99 0.90, respectively). integrated into system leverages deviance actual behavior predicted by allow warnings without compromising acceptance.