Intersection Control Optimization for Automated Vehicles Using Genetic Algorithm

Abstract

With wireless communication and autonomous vehicle control capabilities, automated vehicle technology has the potential to improve the performance of an intersection. The objective of this research was to develop an intersection control algorithm that can jointly optimize the system performance and the trajectory of every single vehicle. An optimization algorithm was developed for a four-approach intersection with the consideration of turning movements and a full set of possible phases under a 1% automated vehicle environment. The intersection controller makes decisions on the vehicle passing sequence using a genetic algorithm–based optimization method, and at the same time it calculates the optimal vehicle trajectories. The optimization process repeats over a time horizon to process continually arriving vehicles. The performance of the proposed algorithm was assessed in various scenario-based simulation experiments and the results were compared with the actuated signal control. It was concluded that the proposed algorithm is able to reduce the intersection average travel time delay by 16.3% to 79.3%, depending on the demand scenario.