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

A realistic long-term microscopic traffic simulator is necessary forunderstanding how microscopic changes affect traffic patterns at a largerscale. Traditional simulators that model human driving behavior with heuristicrules often fail to achieve accurate simulations due to real-world trafficcomplexity. To overcome this challenge, researchers have turned to neuralnetworks, which are trained through imitation learning from human driverdemonstrations. However, existing learning-based microscopic simulators oftenfail to generate stable long-term simulations due to the \textit{covariateshift} issue. To address this, we propose a history-masked multi-agentimitation learning method that removes all vehicles' historical trajectoryinformation and applies perturbation to their current positions duringlearning. We apply our approach specifically to the urban traffic simulationproblem and evaluate it on the real-world large-scale pNEUMA dataset, achievingbetter short-term microscopic and long-term macroscopic similarity toreal-world data than state-of-the-art baselines.

Long-term Microscopic Traffic Simulation with History-Masked Multi-agent Imitation Learning