arXiv:2509.24725v4 Announce Type: replace 
Abstract: Estimating queue lengths at signalized intersections is a long-standing challenge in traffic management. Partial observability of vehicle flows complicates this task despite the availability of two privacy-preserving data sources: (i) aggregated vehicle counts from loop detectors near stop lines, and (ii) aggregated floating car data (aFCD) that provide segment-wise average speed measurements. However, how to integrate these sources with differing spatial and temporal resolutions for queue length estimation is rather unclear. Addressing this question, we present Q-Net: a queue estimation framework built upon a state-space formulation. This design addresses key challenges in queue modeling, such as violations of traffic conservation assumptions. Q-Net follows the Kalman predict-update structure and maintains physical interpretability in both the state evolution and measurement models. Q-Net uses an AI-augmented Kalman filter to learn time-varying gain dynamics from data. The framework supports real-time implementation and improves spatial transferability by grouping aFCD measurements into fixed-size local groups, making the number of learnable parameters independent of section length. Evaluations on urban main roads in Rotterdam, the Netherlands, show that Q-Net outperforms baseline methods, tracks queue formation and dissipation accurately, and mitigates aFCD-induced delays. By combining data efficiency, interpretability, real-time applicability, and spatial transferability, Q-Net makes accurate queue length estimation possible without costly sensing infrastructure like cameras or radar.

تم تقديم إطار عمل جديد يسمى Q-Net لتقدير أطوال الطوابير عند التقاطعات المضيئة، حيث يتناول التحديات المتعلقة بالتحكم الجزئي في تدفقات المركبات. يدمج هذا الإطار مصدرين للبيانات يحافظان على الخصوصية: عدادات المركبات المجمعة من كاشفات الحلقة وبيانات السيارات العائمة المجمعة، مع استخدام هيكل التنبؤ-التحديث لكالمان لنمذجة الطوابير بشكل فعال.

Se ha presentado un nuevo marco llamado Q-Net para estimar las longitudes de las colas en intersecciones semafóricas, abordando los desafíos relacionados con la observabilidad parcial de los flujos de vehículos. Este marco integra dos fuentes de datos que preservan la privacidad: conteos de vehículos agregados de detectores de bucle y datos de coches flotantes agregados, utilizando una estructura de predicción-actualización de Kalman para una modelización efectiva de las colas.

Un nouveau cadre nommé Q-Net a été introduit pour estimer les longueurs de file d'attente aux intersections signalées, abordant les défis liés à l'observabilité partielle des flux de véhicules. Ce cadre intègre deux sources de données préservant la vie privée : des comptages de véhicules agrégés provenant de détecteurs en boucle et des données de voitures flottantes agrégées, tout en utilisant une structure de prévision-mise à jour de Kalman pour un modélisation efficace des files d'attente.

A new framework named Q-Net has been introduced for estimating queue lengths at signalized intersections, addressing challenges related to partial observability of vehicle flows. This framework integrates two privacy-preserving data sources: aggregated vehicle counts from loop detectors and aggregated floating car data, while utilizing a Kalman predict-update structure for effective queue modeling.