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

Traditional traffic optimization solutions assume that the graph structure ofroad networks is static, missing opportunities for further traffic flowoptimization. We are interested in optimizing traffic flows as a new type ofgraph-based problem, where the graph structure of a road network can adapt totraffic conditions in real time. In particular, we focus on the dynamicconfiguration of traffic-lane directions, which can help balance the usage oftraffic lanes in opposite directions. The rise of connected autonomous vehiclesoffers an opportunity to apply this type of dynamic traffic optimization at alarge scale. The existing techniques for optimizing lane-directions are howevernot suitable for dynamic traffic environments due to their high computationalcomplexity and the static nature.  In this paper, we propose an efficient traffic optimization solution, calledCoordinated Learning-based Lane Allocation (CLLA), which is suitable fordynamic configuration of lane-directions. CLLA consists of a two-layermulti-agent architecture, where the bottom-layer agents use a machine learningtechnique to find a suitable configuration of lane-directions around individualroad intersections. The lane-direction changes proposed by the learning agentsare then coordinated at a higher level to reduce the negative impact of thechanges on other parts of the road network. Our experimental results show thatCLLA can reduce the average travel time significantly in congested roadnetworks. We believe our method is general enough to be applied to other typesof networks as well.

Dynamic Graph Configuration with Reinforcement Learning for Connected Autonomous Vehicle Trajectories