Fully-Autonomous, Vision-based Traffic Signal Control: From Simulation to Reality.

Ineffective traffic signal control is one of the major causes of congestion in urban road networks. Dynamically changing traffic conditions and live traffic state estimation are fundamental challenges that limit the ability of the existing signal infrastructure in rendering individualized signal control in real-time. We use deep reinforcement learning (DRL) to address these challenges. Due to economic and safety constraints associated with training such agents in the real world, a practical approach is to do so in simulation before deployment. Domain randomisation is an effective technique for bridging thereality gap and ensuring effective transfer of simulation-trained agents to the real world. In this paper, we develop a fully-autonomous, vision-based DRL agent that achieves adaptive signal control in the face of complex, imprecise, and dynamic traffic environments. Our agent uses live visual data (i.e. a stream of real-time RGB footage) from an intersection to extensively perceive and subsequently act upon the traffic environment. Employing domain randomisation, we examine our agent's generalisation capabilities under varying traffic conditions in both the simulation and the real-world environments. In a diverse validation set independent of training data, our traffic control agent reliably adapted to novel traffic situations and demonstrated a positive transfer to previously unseen real intersections despite being trained entirely in simulation.