Towards an Intelligent GPS-Based Vehicle Navigation System for Finding Street Parking Lots

Current GPS-based vehicle navigation systems provide drivers with information about the location and the availability of a parking lot near the specified destination. However, this availability information is provided based only on the current state of the parking lot. Therefore, they fail to predict whether the vehicle would be able to get a parking lot when it actually arrives. In this paper, we propose a scientific solution to this problem by utilizing the history and current status of the occupancy/availability. We model the availability of a parking lot by the Poisson process, and propose an intelligent algorithm that allows drivers to choose a parking lot with the maximum probability of getting it. The preliminary experimental results show the utility of the proposed algorithm.