OBELISC: Oscillator-Based Modelling and Control Using Efficient Neural Learning for Intelligent Road Traffic Signal Calculation

Traffic congestion poses serious challenges to urban infrastructures through the unpredictable dynamical loading of their vehicular arteries. Despite the advances in traffic light control systems, the problem of optimal traffic signal timing is still resistant to straightforward solutions. Fundamentally nonlinear, traffic flows exhibit both locally periodic dynamics and globally coupled correlations under deep uncertainty. This paper introduces Oscillator-Based modelling and control using Efficient neural Learning for Intelligent road traffic Signal Calculation (OBELISC), an end-to-end system capable of modelling the cyclic dynamics of traffic flow and robustly compensate for uncertainty while still keeping the system feasible for real-world deployments. To achieve this goal, the system employs an efficient representation of the traffic flows and their dynamics in populations of spiking neural networks. Such a computation and learning framework enables OBELISC to model and control the complex dynamics of traffic flows in order to dynamically adapt the green light phase. In order to emphasize the advantages of the proposed system, an extensive experimental evaluation on real-world data completes the study.