Traffic-Aware Lane Change Advance Warning System for Delay Reduction at Congested Freeway Diverge Areas

Abstract

This paper presents an on-board advance warning system based on a probabilistic prediction model that advises vehicles approaching a freeway diverge area on when to change lanes to reach an off-ramp, with the goal of reducing delay caused by congestion at the diverge area. The prediction model estimates the probability of reaching a goal state on the road using one or multiple lane changes. This estimate is based on several traffic- and driver-related parameters such as the distribution of intervehicle headway distances and lane-changing maneuver duration. For an upcoming off-ramp, the advance warning system utilizes the prediction model to continuously calculate the probability of reaching that off-ramp and advises vehicles to change lanes when the probability drops below a certain threshold. To evaluate the impact of the proposed system on reducing traffic delay at congested freeway diverge areas, it was used in a simulation case study of a two-lane segment of the I-66 interstate highway to advise vehicles taking an off-ramp on when to change lanes. The results indicate that incorporating the proposed system can reduce the average delay by up to 83%—effectively wiping out the congestion in some cases—depending on traffic flow and the ratio of vehicles taking the off-ramp.