A Traffic Prediction-Based Individualized Driver Warning System to Reduce Red Light Violations

TL;DR

This work tackles red-light violations by delivering individualized driver warnings guided by real-time traffic prediction. The framework combines a traffic-prediction module with a model predictive control (MPC) optimizer to compute optimal braking commands and a color-coded in-vehicle display to convey graded guidance, continuously updating as conditions evolve. Key contributions include a formal MPC formulation with a flexible driver model, obstacle/green-yellow-red constraints, and slack variables to guarantee feasibility, validated through extensive simulations and on-road tests that show reduced peak deceleration (up to 72.2%) and smoother, safer approaches to intersections. The results suggest practical impact in reducing red-light running while maintaining traffic flow, with future work focusing on data-driven driver models and broader field validation across intersections and driver populations.

Abstract

Red light violation is a major cause of traffic collisions and resulting injuries and fatalities. Despite extensive prior work to reduce red light violations, they continue to be a major problem in practice, partly because existing systems suffer from the flaw of providing the same guidance to all drivers. As a result, some violations are avoided, but other drivers ignore or respond inappropriately to red light running systems, resulting in safety issues overall. We show a method of providing accurate warnings to individual drivers to avoid the broad guidance approach of most existing systems. Recognizing if a driver will run red lights is highly dependent on signal phase and timing, traffic conditions along the road, and individual driver behaviour, the proposed warning system contains three parts: a traffic prediction algorithm, an individual warning signal optimizer, and a driver warning display. The traffic prediction algorithm predicts future traffic states along the road towards the signalized intersections using the latest traffic conditions obtained through vehicle-to-vehicle and vehicle-to-infrastructure communications. Then, an optimization problem is formulated to compute the optimal warning signal based on predicted traffic states and driver reaction model. Finally, the optimal warning signal is shown on the display screen to advise driver on how much braking is needed to avoid running the red light. The system continuously updates the latest warning signal as the vehicle is approaching the intersection. Both numerical simulated driving scenarios and real-world road tests are used to demonstrate the proposed algorithm's performance under different conditions by comparing with previous work on red light running warning system. The results show that the system provides more effective and accurate warning signals to drivers, helping them avoid running red lights.

Figures (16)

• Figure 1: The structure of the proposed red light running warning system (RLRWS).
• Figure 2: Warning signal visualization.
• Figure 3: Modeled network with the ego vehicle shown in green and all other vehicles in yellow.
• Figure 4: Comparison between the proposed warning algorithm and the baseline approach for simulation 1. In the first three sub-figures, blue and purple lines indicate vehicle's states using the proposed algorithm and SUMO default controller, respectively. The last sub-figure displays the warning signals of our system and baseline approach.
• Figure 5: Comparison between the proposed warning algorithm and the baseline approach for simulation 2. In the first three sub-figures, blue and purple lines indicate vehicle's states using the proposed algorithm and SUMO default controller, respectively. The last sub-figure displays the warning signals of our system and baseline approach.