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

This paper addresses the problem of estimating link flows in a road networkby combining limited traffic volume and vehicle trajectory data. While trafficvolume data from loop detectors have been the common data source for link flowestimation, the detectors only cover a subset of links. Vehicle trajectory datacollected from vehicle tracking sensors are also incorporated these days.However, trajectory data are often sparse in that the observed trajectoriesonly represent a small subset of the whole population, where the exact samplingrate is unknown and may vary over space and time. This study proposes a novelgenerative modelling framework, where we formulate the link-to-link movementsof a vehicle as a sequential decision-making problem using the Markov DecisionProcess framework and train an agent to make sequential decisions to generaterealistic synthetic vehicle trajectories. We use Reinforcement Learning(RL)-based methods to find the best behaviour of the agent, based on whichsynthetic population vehicle trajectories can be generated to estimate linkflows across the whole network. To ensure the generated population vehicletrajectories are consistent with the observed traffic volume and trajectorydata, two methods based on Inverse Reinforcement Learning and ConstrainedReinforcement Learning are proposed. The proposed generative modellingframework solved by either of these RL-based methods is validated by solvingthe link flow estimation problem in a real road network. Additionally, weperform comprehensive experiments to compare the performance with two existingmethods. The results show that the proposed framework has higher estimationaccuracy and robustness under realistic scenarios where certain behaviouralassumptions about drivers are not met or the network coverage and penetrationrate of trajectory data are low.

Estimating Link Flows in Road Networks with Synthetic Trajectory Data Generation: Reinforcement Learning-based Approaches