A non-parametric Bayesian framework for traffic-state estimation at signalized intersections

Abstract

An accurate and practical traffic-state estimation (TSE) method for signalized intersections plays an important role for real-time operations to facilitate efficient traffic management. This paper presents a generalized modeling framework for estimating traffic states at signalized intersections. The framework is non-parametric and data-driven, without the requirement on explicit models of traffic. Additionally, in principle, any type of data source together with any type of signal controller can be incorporated with the proposed framework. The Bayesian filter (BF) approach is the core of the framework and introduces a recursive state estimation process. The required transition and measurement models of the BFs are trained using Gaussian process (GP) regression models with respect to a set of historical data. A Gaussian process model uses kernel functions to describe the proximity among data points, and the hyper-parameters adopted in the GP model are optimized according to the training data. In addition to the detailed derivation of the integration of BFs and GP regression models, an algorithm based on the extended Kalman filter is presented for real-time traffic estimation. The effectiveness of the proposed framework is demonstrated through several numerical experiments using data generated in microscopic traffic simulations. Both fixed-location data (i.e., loop detector) and mobile data (i.e., connected vehicle) are examined with the framework. As a result, the method performs well for the tested traffic conditions. In particular, the estimator provides a competitive estimation accuracy merely using the position information of a small portion of vehicles at the intersection. The approach is suitable for a short-term estimation requirement, which is normally a challenging task in traffic control and operations.

Una revisión sistemática de literatura sobre implementaciones de sistemas de control de tráfico

“…Algoritmos y métodos utilizados en sistemas de control de semaforización REFERENCIA ALGORITMO MÉTODO DESCRIPCIÓN (Yuan et al, 2021); (Jin & Ma, 2019) Bayesian Filter…”

“…Los autores hacen observaciones de su aceptable eficiencia en sistemas de semáforos tradicionales, no obstante, debido a esto su adaptabilidad en situaciones muy complejas no es la mejor. (Yuan et al, 2021); (Jin & Ma, 2019) Gaussian Process Eficiente…”

Probabilistic traffic density estimation using measurements from Unmanned Aerial Vehicles

“…Gaussian process (GP) models have been utilised in the literature for transportation related tasks. A recent work has proposed a data-driven approach for TSE for signalized intersections using a Bayesian filtering approach with the use of GPs to represent the state space model of the traffic dynamics and a large amount of historical data [13]. The study was focused on a single four-legged signalized intersection and data were obtained from either loop detectors or connected vehicles.…”

A Combinatorial Approach for Nonparametric Short-Term Estimation of Queue Lengths using Probe Vehicles

“…In this paper, we focused on the review of nonparametric ones. Jin and Ma presented a study on a nonparametric Bayesian method for traffic state estimation (Jin and Ma (2019)). In their study, they developed a generalized modeling framework for estimating traffic states at signalized intersections.…”