Learning Vehicle Cooperative Lane-changing Behavior from Observed Trajectories in the NGSIM Dataset

Abstract

Lane-changing intention prediction has long been a hot topic in autonomous driving scenarios. However, none of the existing literature has taken both the vehicle’s trajectory history and neighbor information into consideration when making the predictions. We propose a socially-aware LSTM algorithm in real world scenarios to solve this intention prediction problem, taking advantage of both vehicle past trajectories and their neighbor’s current states. Simulation results show that these two components can lead not only to higher accuracy, but also to lower lane-changing prediction time, which plays an important role in potentially improving the autonomous vehicle’s overall performance.