The Use of Genetic Algorithm for Traffic Light and Pedestrian Crossing Control

Summary The increase in urban traffic has resulted in traffic congestions, long travel times and increase hazards to pedestrians due to inefficient traffic light controls. These scenarios necessitate the use of new methods in the design of traffic light control for vehicles and pedestrian crossings. In a conventional traffic light controller, the traffic lights change at constant cycle times which are clearly not optimal. The preset cycle time regardless of the dynamic traffic load only adds to the problem. It would be more feasible and sensible to pass more vehicles at the green interval if there are fewer vehicles waiting behind the red lights or vice versa. We apply the genetic algorithm technology in the traffic control system and pedestrian crossing to provide intelligent green interval responses based on dynamic traffic load inputs, thereby overcoming the inefficiencies of the conventional traffic controllers. We apply such technology to a four-way, two-lane junction based on two sets of parameters: vehicles and pedestrians queues behind a red light and number of vehicles and pedestrians that passes through a green light. The algorithms dynamically optimize the red and green times to control the flow of both the vehicles and the pedestrians. To represent a typical traffic flow system, we use the Cellular Automata for modeling vehicular motion behind the traffic lights. We developed an algorithm to model the situation of a four-way two-lane junction based on this technology. We compare the performance between the genetic algorithms controller and a conventional fixed time controller and the results show that the genetic algorithms controller performs better than the fixed-time controller.