Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6936228 | Transportation Research Part C: Emerging Technologies | 2017 | 24 Pages |
Abstract
Numerical experiments are performed on various scenarios containing different proportions of trained strategic agents, agents with random strategies and non strategic agents, to test the robustness and adaptability to new environments and varying network conditions. The methodology is also compared against existing approaches and real world data. The outcome of the experiments suggest that this work-in-progress already produces encouraging results in terms of accuracy and computational efficiency. This indicates that the proposed approach has the potential to provide better tools to investigate and forecast drivers' choice behaviours. Eventually these tools can improve the delivery and efficiency of traffic information to the drivers.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science Applications
Authors
Johan Barthélemy, Timoteo Carletti,