Artificial intelligence approach for optimizing traffic signal timings on urban road network

Abstract

Artificial intelligence techniques were applied to a traffic control problem on an urban road network and a method that optimizes signal timings was proposed. The method is separated into two processes, a training process and an optimization process. In the training process, two types of neural network model were used; a multilayer model and a Kohonen feature map model. The former model formed an input-output relationship between the timings and the objective function. The latter model improved the computational efficiency and the estimation precision. In the optimization process, to avoid the entrapment into a local minimum, two artificial intelligence methods were used; a Cauchy machine and a genetic algorithm. Signal timings were adjusted so as to minimize the total weighted sum of delay time and stop frequencies. The solutions were compared with those by a conventional method. The results here indicated that the AI models were useful for establishing advanced traffic control systems.<>