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

arXiv: https://arxiv.org/abs/2602.04821 · HTML: https://mlsanity.com/paper/2602.04821/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 35 of its 87 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 30 of 35)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Conformal prediction beyond exchangeability](https://mlsanity.com/paper/2202.13415/) (2022)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Discrete Graph Structure Learning for Forecasting Multiple Time Series](https://mlsanity.com/paper/2101.06861/) (2021)
- [A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems](https://mlsanity.com/paper/1705.01292/) (2017)
- [Adaptive Conformal Predictions for Time Series](https://mlsanity.com/paper/2202.07282/) (2022)
- [Lyapunov-based Safe Policy Optimization for Continuous Control](https://mlsanity.com/paper/1901.10031/) (2019)
- [Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selection](https://mlsanity.com/paper/1610.02351/) (2016)
- [Conservative Safety Critics for Exploration](https://mlsanity.com/paper/2010.14497/) (2020)
- [Safe Testing](https://mlsanity.com/paper/1906.07801/) (2019)
- [Uncertainty Aware Semi-Supervised Learning on Graph Data](https://mlsanity.com/paper/2010.12783/) (2020)
- [Conformal Prediction using Conditional Histograms](https://mlsanity.com/paper/2105.08747/) (2021)
- [Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting](https://mlsanity.com/paper/2105.04100/) (2021)
- [Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version](https://mlsanity.com/paper/2203.15737/) (2022)
- [Constrained Policy Optimization via Bayesian World Models](https://mlsanity.com/paper/2201.09802/) (2022)
- [Worst Cases Policy Gradients](https://mlsanity.com/paper/1911.03618/) (2019)
- [How Powerful is Graph Convolution for Recommendation?](https://mlsanity.com/paper/2108.07567/) (2021)
- [Improving Conditional Coverage via Orthogonal Quantile Regression](https://mlsanity.com/paper/2106.00394/) (2021)
- [Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting](https://mlsanity.com/paper/1707.01926/) (2017)
- [Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control](https://mlsanity.com/paper/2112.10107/) (2021)
- [Online Rules for Control of False Discovery Rate and False Discovery Exceedance](https://mlsanity.com/paper/1603.09000/) (2016)
- [AdaPT: An interactive procedure for multiple testing with side information](https://mlsanity.com/paper/1609.06035/) (2016)
- [Online false discovery rate control for anomaly detection in time series](https://mlsanity.com/paper/2112.03196/) (2021)
- [WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning](https://mlsanity.com/paper/2411.05420/) (2024)
- [Conditional calibration for false discovery rate control under dependence](https://mlsanity.com/paper/2007.10438/) (2020)
- [A unified treatment of multiple testing with prior knowledge using the p-filter](https://mlsanity.com/paper/1703.06222/) (2017)

## Abstract (arXiv)

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.