Genetic algorithm for shortest driving time in intelligent transportation systems

The route guidance system, which provides driving advice based on traffic information about an origin and a destination, has become very popular along with the advancement of handheld devices and the global position system. Since the accuracy and efficiency of route guidance depend on the accuracy of the traffic conditions, the route guidance system needs to include more variables in calculation, such as real time traffic flows and allowable vehicle speeds. As variables considered by the route guidance system increase, the cost to compute multiplies. As handheld devices have limited resources, it is not feasible to use them to compute the exact optimal solutions by some well-known algorithm, such as the Dijkstra's algorithm, which is usually used to find the shortest path with a map of reasonable numbers of vertices. To solve this problem, we propose to use the genetic algorithm to alleviate the rising computational cost. We use the genetic algorithm to find the shortest time in driving with diverse scenarios of real traffic conditions and varying vehicle speeds. The effectiveness of the genetic algorithm is clearly demonstrated when applied on a real map of modern city with very large vertex numbers.