27 June 2023 in IEEE Transactions on Intelligent Transportation Systems
The connected automated vehicles (CAVs) are envisioned to be implemented most likely on electric vehicles, while traditional fuel-powered manually-driven vehicles (MVs) would probably still dominate the automobile market in the next decade. In this context, this paper addresses urban eco-driving of CAVs in mixed traffic and heterogeneous power conditions. The paper aims to develop a practical and deployable eco-driving strategy for CAVs in mixed traffic flow of CAVs and MVs under realistic and complex traffic conditions. Several typical eco-driving scenarios were studied in detail. In a nutshell, the eco-driving strategy for each CAV was determined by solving a typical two-point boundary value problem with minimum electric energy consumption in urban traffic conditions with small market penetration rates (MPRs) of CAVs. A rolling-horizon scheme was applied to implement the eco-driving strategy to handle uncertain/unpredictable disturbances of preceding MVs and the interference of junction queues to the eco-driving maneuvers of CAVs. The paper also studied how eco-driving for electrified CAVs would affect MVs’ fuel consumptions. Simulation studies were carried out on urban arterial roads of multiple signalized intersections in various scenarios of demand and MPR to verify the energy savings effect of the proposed eco-driving strategy. The results showed that via eco-driving electrified CAVs each had a potential of reducing energy consumption by 40%-61%, meanwhile leading to 5%-34% fuel savings on average for each following MV. Further issues concerning the energy saving mechanism of electrified CAVs, impacts of MVs cut-in from adjacent lanes, and passenger comfort were also examined.
15 December 2021 in IEEE Transactions on Intelligent Transportation Systems
Three filtering-based approaches to freeway traffic state estimation are studied using measurements from connected vehicles and also a minimum number of fixed detectors. These approaches are: Method 1 based on EKF and the second-order traffic flow model METANET, Methods 2 and 3 based on KF and the conservation equation that is driven by mean speed data of connected vehicles under a speed-uniformity assumption. Each method is capable of estimating segment traffic flow variables (speeds, densities, and flows) as well as segment market penetration rates (MPRs) of connected vehicles. The three methods are evaluated and compared in depth using NGSIM data with respect to their traffic state estimator design, data requirements, capabilities, limitations in the mixed sensing case. Recommendations are given about the choice of methods over the range of MPR.
22 December 2025 in IEEE Transactions on Intelligent Transportation Systems
Traffic state estimation (TSE) lays the foundation for freeway traffic monitoring and control. This paper develops a novel freeway traffic state estimator based on physics-informed deep learning (PIDL), whereby the deep-learning neural network is guided with physical laws of traffic. The innovative features of this work are as follows. In the data-driven aspect, the representation capability of neural networks is enhanced by introducing a nonlinear expansion layer, an attention mechanism, and a point-weighting mechanism. In traffic flow modeling aspect, a neural network is designed for the adaptive identification of model parameters. Additionally, a ramp flow self-learning neural network is constructed in consideration of system observability. This study employs four macroscopic traffic flow models LWR, ARZ, JWZ and PW to design PIDL-based traffic state estimators. Field-data evaluations and comparative analyses are conducted with respect to an urban expressway of 17.5 km. The results show that the designed PIDL traffic state estimators are able to simultaneously achieve traffic state estimation, ramp flow estimation, and adaptive identification of model parameters. The PIDL estimators outperform a number of baseline estimators, and are least sensitive to the number of input sensors and missing data. It is also discovered that the effectiveness of PIDL hinges on the appropriate tuning of the imbedded physical model as well as accurate boundary condition inputs, and failure to meet these requirements may lead to performance degradation.