A Flow-Efficient and Legal-by-Construction Real-Time Traffic Signal Control Platform

TL;DR

This paper presents a real-time traffic signal control platform using Model Predictive Control that improves traffic flow efficiency and guarantees safety constraints, tested on simulated and real intersections.

Contribution

The novel platform integrates Model Predictive Control with constraints to ensure legal and safe traffic signal operations, optimizing flow for arbitrary intersection topologies.

Findings

22% reduction in time loss compared to baseline schedules

Feasible online prediction at less than 2 seconds per prediction

Effective control on both simulated and real traffic data

Abstract

Inefficiencies in traffic flow through an intersection lead to stopping vehicles, unnecessary congestion, and increased accident risk. In this paper, we propose a traffic signal controller platform demonstrating the ability to increase traffic flow for arbitrary intersection topologies. This model uses Model Predictive Control on a Mixed Logical Dynamical system to control the state of independently controlled traffic signals in a single intersection, removing constraints forcing the selection of signals from a set of phases. Further, we use constraints to impose a guarantee on the output of the system to be in the set of permissible actions under constraints including precise yellow timing, minimum inter-lane green transition timing, and selection of signal states with non-conflicting dependencies. We evaluate our model on a simulated 4-way intersection and an intersection in Denmark with true traffic data and a currently implemented timing schedule as a baseline. Our model shows at least 22\% reduction in time loss compared to baseline light schedules, and timing shows that this system can feasibly run online predictions at a frequency faster than 2s/prediction optimizing over a prediction horizon of 25s.