Intelligent Transportation Systems (ITS) have emerged to use different technologies to promote safety, convenience, and efficiency of transportation networks. Many applications of ITS depend on the availability of the real-time positioning of the vehicles in the network. In this research, the two open challenges in the field of vehicle localization for ITS are introduced and addressed.

First, in order to have safe and efficient transportation systems, the locations of the vehicles need to be available everywhere in a network. Conventional localization techniques mostly rely on Global Positioning System (GPS) technology which cannot meet the accuracy requirements for all applications in all situations. This work advances the study of vehicle positioning in ITS by introducing an integrated positioning framework which uses several resources including GPS, vehicle-to-infrastructure and vehicle-to-vehicle communications, radio-frequency identification, and dead reckoning. These technologies are used to provide more reliable and accurate location information. The suggested framework fills the gap between the accuracy of the current vehicle localization techniques and the required one for many ITS applications.

Second, different ITS applications have different localization accuracy and latency requirements. A smart positioning algorithm is proposed which enable us to change the positioning accuracy delivered by the algorithm based on different applications. The algorithm utilizes only the most effective resources to achieve the required accuracy, even if more resources are available. In this way, the complexity of the system and the running time decrease while the desired accuracy is obtained. The adjective Smart is selected because the algorithm smartly selects the most effective connection which has the most contribution to vehicle positioning when a connection needs to be added. On the other hand, when a connection should be removed, the algorithm smartly selects the least effective one which has the least contribution to the position estimation.

This study also provides an overview about the positioning requirements for different ITS applications. A close-to-real-world scenario has been developed and simulated in MATLAB to evaluate the performance of the proposed algorithms. The simulation results show that the vehicle can acquire accurate location in different environments using the suggested Integrated framework. Moreover, the advantages of the proposed Smart algorithm in terms of accuracy and running time are presented through a series of comprehensive simulations.