Impact of Traffic Lights on Trajectory Forecasting of Human-driven Vehicles Near Signalized Intersections
This work addresses a specific challenge in autonomous driving for urban environments, but it is incremental as it builds on existing behavior cloning methods by adding traffic light considerations.
The paper tackles the problem of forecasting human-driven vehicle trajectories near signalized intersections by addressing the overlooked impact of traffic lights, and it demonstrates that incorporating traffic light states and future information through Human Policy Models improves prediction accuracy in real-world driving data.
Forecasting trajectories of human-driven vehicles is a crucial problem in autonomous driving. Trajectory forecasting in the urban area is particularly hard due to complex interactions with cars and pedestrians, and traffic lights (TLs). Unlike the former that has been widely studied, the impact of TLs on the trajectory prediction has been rarely discussed. In this work, we first identify the less studied, perhaps overlooked impact of TLs. Second, we present a novel resolution that is mindful of the impact, inspired by the fact that human drives differently depending on signal phase (green, yellow, red) and timing (elapsed time). Central to the proposed approach is Human Policy Models which model how drivers react to various states of TLs by mapping a sequence of states of vehicles and TLs to a subsequent action (acceleration) of the vehicle. We then combine the Human Policy Models with a known transition function (system dynamics) to conduct a sequential prediction; thus our approach is viewed as Behavior Cloning. One novelty of our approach is the use of vehicle-to-infrastructure communications to obtain the future states of TLs. We demonstrate the impact of TL and the proposed approach using an ablation study for longitudinal trajectory forecasting tasks on real-world driving data recorded near a signalized intersection. Finally, we propose probabilistic (generative) Human Policy Models which provide probabilistic contexts and capture competing policies, e.g., pass or stop in the yellow-light dilemma zone.