Q-Net: Transferable Queue Length Estimation via Kalman-based Neural Networks

2025-09-29

AI Summary

Accurate queue length estimation at signalized intersections remains challenging under partial observability—e.g., incomplete loop detector coverage or sparse floating car data (FCD). To address this, we propose Q-Net: a physics-informed state-space model that jointly fuses loop detector counts and aggregated FCD. Central to Q-Net is KalmanNet, an AI-enhanced Kalman filter that learns the Kalman gain end-to-end, eliminating reliance on manually tuned noise covariance priors. This design ensures both cross-segment spatial transferability and interpretability grounded in traffic dynamics. Evaluated on real-world arterial corridors in Rotterdam, Q-Net reduces RMSE by over 60% compared to state-of-the-art baselines. It significantly improves temporal fidelity in capturing queue evolution, enabling video-free, real-time adaptive traffic signal control.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Estimating queue lengths at signalized intersections remains a challenge in traffic management, especially under partially observed conditions where vehicle flows are not fully captured. This paper introduces Q-Net, a data-efficient and interpretable framework for queue length estimation that performs robustly even when traffic conservation assumptions are violated. Q-Net integrates two widely available and privacy-friendly data sources: (i) vehicle counts from loop detectors near stop lines, and (ii) aggregated floating car data (aFCD), which divides each road section into segments and provides segment-wise average speed measurements. These data sources often differ in spatial and temporal resolution, creating fusion challenges. Q-Net addresses this by employing a tailored state-space model and an AI-augmented Kalman filter, KalmanNet, which learns the Kalman gain from data without requiring prior knowledge of noise covariances or full system dynamics. We build on the vanilla KalmanNet pipeline to decouple measurement dimensionality from section length, enabling spatial transferability across road segments. Unlike black-box models, Q-Net maintains physical interpretability, with internal variables linked to real-world traffic dynamics. Evaluations on main roads in Rotterdam, the Netherlands, demonstrate that Q-Net outperforms baseline methods by over 60% in Root Mean Square Error (RMSE), accurately tracking queue formation and dissipation while correcting aFCD-induced delays. Q-Net also demonstrates strong spatial and temporal transferability, enabling deployment without costly sensing infrastructure like cameras or radar. Additionally, we propose a real-time variant of Q-Net, highlighting its potential for integration into dynamic, queue-based traffic control systems.

Problem

• Estimating queue lengths at signalized intersections under partial observation
• Fusing heterogeneous traffic data sources with different resolutions
• Developing transferable queue estimation without expensive infrastructure

Innovation

• Uses loop detectors and floating car data fusion
• Employs AI-augmented Kalman filter learning gains
• Maintains physical interpretability while enabling transferability