Digital Twin-Aided Municipal Traffic Control

Abstract

Swift advances in computing and artificial intelligence (AI) technologies of late have prompted the increasing applications of digital twins (DiTs) to various sectors for boosting effectiveness and productivity. DiTs have been envisioned to possess immense potential for transforming numerous domains and sectors in the recent report of National Academics due to their powerful real-time decision-making based on modeling and simulating physical systems. This paper deals with a novel design of digital twin-aided municipal traffic control (DiTAT) for best traffic management over a targeted municipal region, based on real-world traffic video imagery gathered by available roadside surveillance cameras. DiTAT analyzes sequences of video frames to extract traffic volume details, including the start time, speed, incoming zone, and outgoing zone of every vehicle in existence. Being DiT-based, DiTAT employs the automated, open-source traffic simulator (SUMO) as the digital twin of the physical roadway configuration over the target region to try various traffic light control settings under the extracted traffic volume details for identifying the most favorable setting. The identified setting is then sent to the physical roadway traffic lights for realization to manage traffic during the next time window, when its resulting traffic is simulated by SUMO again to get the best setting for the subsequent time window reactively. This process repeats continuously window by window, with a bidirectional interplay between SUMO simulation and physical traffic for the target region. DiTAT is demonstrated to lift transport performance under real-world traffic scenarios.