Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning

TL;DR

This paper introduces STREAM-RL, a comprehensive framework for urban traffic control that combines uncertainty-aware forecasting, anomaly detection, and safe reinforcement learning with theoretical guarantees, improving safety and efficiency.

Contribution

It presents three novel algorithms for uncertainty modeling, distribution-free coverage, and safe policy learning, integrating them into a unified traffic management system with formal guarantees.

Findings

Achieves 91.4% coverage efficiency in traffic prediction.

Controls FDR at 4.1% under dependence.

Improves safety rate to 95.2% over standard methods.

Abstract

Urban traffic management demands systems that simultaneously predict future conditions, detect anomalies, and take safe corrective actions -- all while providing reliability guarantees. We present STREAM-RL, a unified framework that introduces three novel algorithmic contributions: (1) PU-GAT+, an Uncertainty-Guided Adaptive Conformal Forecaster that uses prediction uncertainty to dynamically reweight graph attention via confidence-monotonic attention, achieving distribution-free coverage guarantees; (2) CRFN-BY, a Conformal Residual Flow Network that models uncertainty-normalized residuals via normalizing flows with Benjamini-Yekutieli FDR control under arbitrary dependence; and (3) LyCon-WRL+, an Uncertainty-Guided Safe World-Model RL agent with Lyapunov stability certificates, certified Lipschitz bounds, and uncertainty-propagated imagination rollouts. To our knowledge, this is the first framework to propagate calibrated uncertainty from forecasting through anomaly detection to safe policy learning with end-to-end theoretical guarantees. Experiments on multiple real-world traffic trajectory data demonstrate that STREAM-RL achieves 91.4\% coverage efficiency, controls FDR at 4.1\% under verified dependence, and improves safety rate to 95.2\% compared to 69\% for standard PPO while achieving higher reward, with 23ms end-to-end inference latency.