Ad hoc link traversal time prediction

Drivers able to use link traversal time predictions can use this information to choose better routes. Such anticipatory vehicle routing bases routing decisions on link traversal times likely to be experienced by the vehicle instead of historic or real time link traversal times. However, generating such link traversal times is a challenge. This paper describes a multi-agent system in which road agents and vehicle agents cooperate to provide ad hoc link traversal times for the routes the vehicle agents intend to follow. Road agents use observations to learn a model of the road they represent and combine this model with information obtained from vehicle agents to predict future link traversal times. Two such models are described in this paper, namely a polynomial model and an artificial neural network. Both models are evaluated based on a microscopic traffic simulation. The predictions obtained using both models are analyzed and compared with the actual observed link traversal times to estimate the accuracy of the predictions.

[1]  Robert L. Smith,et al.  Link travel time prediction for decentralized route guidance architectures , 2000, IEEE Trans. Intell. Transp. Syst..

[2]  Eric Horvitz,et al.  Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service , 2005, UAI.

[3]  Helbing,et al.  Congested traffic states in empirical observations and microscopic simulations , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[4]  Patrick Weber,et al.  OpenStreetMap: User-Generated Street Maps , 2008, IEEE Pervasive Computing.

[5]  Tom Holvoet,et al.  Maintaining a distributed symbiotic relationship using delegate MultiAgent systems , 2010, Proceedings of the 2010 Winter Simulation Conference.

[6]  F. Kluegl,et al.  Decision dynamics in a traffic scenario , 2000 .

[7]  Ramin Yasdi.  Prediction of Road Traffic using a Neural Network Approach , 1999, Neural Computing & Applications.

[8]  Danny Weyns,et al.  A Decentralized Approach for Anticipatory Vehicle Routing Using Delegate Multiagent Systems , 2011, IEEE Transactions on Intelligent Transportation Systems.

[9]  Dirk Helbing,et al.  General Lane-Changing Model MOBIL for Car-Following Models , 2007 .

[10]  Tom Holvoet,et al.  GridLock: A microscopic traffic simulation platform , 2011 .

[11]  Shian-Shyong Tseng,et al.  Collaborative real-time traffic information generation and sharing framework for the intelligent transportation system , 2010, Inf. Sci..