Uncertainty-Aware Coordinated Multi-Ramp Metering Based on an Action-Conditioned Traffic Prediction Operator Under Sparse Observations
Abstract
Coordinated multi-ramp metering (CRM) is an important approach to mitigating freeway congestion, but sparse observations in practice complicate the state estimation and model calibration required by predictive control. This study develops an Action-Conditioned Traffic Prediction Operator (ATPO) driven by sparse, heterogeneous observations and candidate multi-ramp actions, and embeds it in an uncertainty-aware CRM framework (ATPOUCRM). ATPO forms a four-channel history from the density and speed measurements of fixed detectors and probe vehicles and their separate observation masks. Queries at future spatiotemporal points attend to all valid historical observations before incorporating upstream mainline demand and on-ramp queue information. Candidate metering actions condition the latent field through feature-wise linear modulation, a spatial Fourier operator, and a causal temporal kernel. The operator produces action-conditioned predictive distributions of future density and speed throughout the corridor; a bootstrap ensemble additionally characterizes disagreement among models. Using these predictions, ATPOUCRM primarily minimizes expected total time spent, including mainline travel and on-ramp waiting, while penalizing predictive uncertainty near merge areas. It uses the cross-entropy method to search candidate actions and applies a safety filter before execution. For five-minute global traffic state prediction on a simulated 7-km freeway corridor, ATPO achieves root mean square errors of 2.54 veh/km/lane, 4.56 km/h, and 0.76 veh*h for density, speed, and total time spent over the forecast horizon, respectively, outperforming the comparison methods. Across 100 control scenarios, ATPOUCRM reduces mean total time spent by 26.17% relative to no control. ATPO also generates predictions on finer spatiotemporal grids without retraining.
Related
- Coordinated coronagraphic observations from Proba-3 and Aditya-L1: Investigating coronal mass ejection energetics in the inner corona
- SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference
- SteelAgent: LLM-Orchestrated, Physics-Informed Steel Property Prediction with Audited Generalization and Calibrated Uncertainty
- ELMO: An Uncertainty-Aware Simulation-to-Surrogate Workflow for Fast Pedestal Linear-Stability Prediction
- Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
BibTeX
@misc{yu2026uncertaintyaware,
title = {{Uncertainty-Aware Coordinated Multi-Ramp Metering Based on an Action-Conditioned Traffic Prediction Operator Under Sparse Observations}},
author = {Hongxin Yu and Fengyue Jin and Tao Jiang and Yibing Wang and Klaus Bogenberger and Jingqiu Guo and Lihui Zhang},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01270},
eprint = {2611.01270},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01270},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Uncertainty-Aware Coordinated Multi-Ramp Metering Based on an Action-Conditioned Traffic Prediction Operator Under Sparse Observations
AU - Hongxin Yu
AU - Fengyue Jin
AU - Tao Jiang
AU - Yibing Wang
AU - Klaus Bogenberger
AU - Jingqiu Guo
AU - Lihui Zhang
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01270
UR - https://arxiv.org/abs/2611.01270
AB - Coordinated multi-ramp metering (CRM) is an important approach to mitigating freeway congestion, but sparse observations in practice complicate the state estimation and model calibration required by predictive control. This study develops an Action-Conditioned Traffic Prediction Operator (ATPO) driven by sparse, heterogeneous observations and candidate multi-ramp actions, and embeds it in an uncertainty-aware CRM framework (ATPOUCRM). ATPO forms a four-channel history from the density and speed measurements of fixed detectors and probe vehicles and their separate observation masks. Queries at future spatiotemporal points attend to all valid historical observations before incorporating upstream mainline demand and on-ramp queue information. Candidate metering actions condition the latent field through feature-wise linear modulation, a spatial Fourier operator, and a causal temporal kernel. The operator produces action-conditioned predictive distributions of future density and speed throughout the corridor; a bootstrap ensemble additionally characterizes disagreement among models. Using these predictions, ATPOUCRM primarily minimizes expected total time spent, including mainline travel and on-ramp waiting, while penalizing predictive uncertainty near merge areas. It uses the cross-entropy method to search candidate actions and applies a safety filter before execution. For five-minute global traffic state prediction on a simulated 7-km freeway corridor, ATPO achieves root mean square errors of 2.54 veh/km/lane, 4.56 km/h, and 0.76 veh*h for density, speed, and total time spent over the forecast horizon, respectively, outperforming the comparison methods. Across 100 control scenarios, ATPOUCRM reduces mean total time spent by 26.17% relative to no control. ATPO also generates predictions on finer spatiotemporal grids without retraining.
ER -