English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Forecasting trajectories of human-driven vehicles is a crucial problem inautonomous driving. Trajectory forecasting in the urban area is particularlyhard 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 thetrajectory prediction has been rarely discussed. In this work, we firstidentify the less studied, perhaps overlooked impact of TLs. Second, we presenta novel resolution that is mindful of the impact, inspired by the fact thathuman drives differently depending on signal phase (green, yellow, red) andtiming (elapsed time). Central to the proposed approach is Human Policy Modelswhich model how drivers react to various states of TLs by mapping a sequence ofstates of vehicles and TLs to a subsequent action (acceleration) of thevehicle. We then combine the Human Policy Models with a known transitionfunction (system dynamics) to conduct a sequential prediction; thus ourapproach is viewed as Behavior Cloning. One novelty of our approach is the useof vehicle-to-infrastructure communications to obtain the future states of TLs.We demonstrate the impact of TL and the proposed approach using an ablationstudy for longitudinal trajectory forecasting tasks on real-world driving datarecorded near a signalized intersection. Finally, we propose probabilistic(generative) Human Policy Models which provide probabilistic contexts andcapture competing policies, e.g., pass or stop in the yellow-light dilemmazone.

Impact of Traffic Lights on Trajectory Forecasting of Human-driven Vehicles Near Signalized Intersections