Real-Time Smart Navigation and the Genetic Approach to Vehicle Routing

In 2050, nearly 70% of the global population will be living in large cities (UN, 2014). Among the grave problems that institutions, companies and researchers are summoned to face, pollution and traffic management are particularly challenging. This huge aggregation of people and vehicles, in fact, is already causing serious trouble to sustainable lifestyle, health and environment, so that mobility management becomes a crucial application field (EC, JRC, IPTS, 2014). Besides the economic impact, in fact, urban mobility accounts for 30% of energy consumption and 70% of transport pollution, and the increasing urban concentration in large cities is making the problem more and more difficult. In this scenario, smart mobility is bound to play an increasingly focal role: private travelers, commercial users and the public sector are continually searching faster route planning services. In line with the Smart Navigation paradigm, in addition, the best path can vary as traffic conditions vary and updates should be indicated in real-time. Since traffic conditions are strongly time-variant, this feature can be achieved through the constant monitoring of road conditions, so as to provide the user with possible updates of routes previously suggested. Several factors contribute to smart navigators efficiency; three issues are here considered. Firstly, a communication infrastructure for managing traffic and vehicular mobility. Secondly, enabling communication technologies and strategies. Lastly, route planning algorithms suitable for the real-time case.

[1]  Hitoshi Kanoh,et al.  Dynamic route planning for car navigation systems using virus genetic algorithms , 2007, Int. J. Knowl. Based Intell. Eng. Syst..

[2]  Kalannagari Viswanath,et al.  Modified Distance Regularized Level Set Segmentation Based Analysis for Kidney Stone Detection , 2015, Int. J. Rough Sets Data Anal..

[3]  Lin Zhang,et al.  Cooperative Sensing and Compression in Vehicular Sensor Networks for Urban Monitoring , 2010, 2010 IEEE International Conference on Communications.

[4]  Philippe Bonnifait,et al.  Real-Time Implementation of a GIS-Based Localization System for Intelligent Vehicles , 2007, EURASIP J. Embed. Syst..

[5]  Richard E. Korf,et al.  Real-Time Heuristic Search , 1990, Artif. Intell..

[6]  Nathan S. Netanyahu,et al.  PHA*: Finding the Shortest Path with A* in An Unknown Physical Environment , 2011, J. Artif. Intell. Res..

[7]  Panagiotis Papadimitratos,et al.  Vehicular communication systems: Enabling technologies, applications, and future outlook on intelligent transportation , 2009, IEEE Communications Magazine.

[8]  Yassin Elhillali,et al.  Embedded Localization and Communication System Designed for Intelligent Guided Transports , 2007, EURASIP J. Embed. Syst..

[9]  A R Al-Ali,et al.  A Mobile GPRS-Sensors Array for Air Pollution Monitoring , 2010, IEEE Sensors Journal.

[10]  Gianni Pasolini,et al.  SHINE: Simulation platform for Heterogeneous Interworking Networks , 2006, 2006 IEEE International Conference on Communications.

[11]  Weilie Yi,et al.  Dynamic distributed genetic algorithms , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[12]  Hu Wei,et al.  Combined Prediction Research of City Traffic Flow Based On Genetic Algorithm , 2007, 2007 8th International Conference on Electronic Measurement and Instruments.