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

Traffic signal control is safety-critical for our daily life. Roughlyone-quarter of road accidents in the U.S. happen at intersections due toproblematic signal timing, urging the development of safety-orientedintersection control. However, existing studies on adaptive traffic signalcontrol using reinforcement learning technologies have focused mainly onminimizing traffic delay but neglecting the potential exposure to unsafeconditions. We, for the first time, incorporate road safety standards asenforcement to ensure the safety of existing reinforcement learning methods,aiming toward operating intersections with zero collisions. We have proposed asafety-enhanced residual reinforcement learning method (SafeLight) and employedmultiple optimization techniques, such as multi-objective loss function andreward shaping for better knowledge integration. Extensive experiments areconducted using both synthetic and real-world benchmark datasets. Results showthat our method can significantly reduce collisions while increasing trafficmobility.

SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control