Forecasting Short to Mid-Length Speed Trajectories of Preceding Vehicle Using V2X Connectivity for Eco-Driving of Electric Vehicles
- 6 April 2021
- journal article
- research article
- Published by SAE International in SAE International Journal of Advances and Current Practices in Mobility
- Vol. 3 (4), 1801-1809
- https://doi.org/10.4271/2021-01-0431
Abstract
In recent studies, optimal control has shown promise as a strategy for enhancing the energy efficiency of connected autonomous vehicles. To maximize optimization performance, it is important to accurately predict constraints, especially separation from a vehicle in front. This paper proposes a novel prediction method for forecasting the trajectory of the nearest preceding car. The proposed predictor is designed to produce short to medium-length speed trajectories using a locally weighted polynomial regression algorithm. The polynomial coefficients are trained by using two types of information: (1) vehicle-to-vehicle (V2V) messages transmitted by multiple preceding vehicles and (2) vehicle-to-infrastructure (V2I) information broadcast by roadside equipment. The predictor’s performance was tested in a multi-vehicle traffic simulation platform, RoadRunner, previously developed by Argonne National Laboratory. The simulation results show that the proposed predictor’s improved predictions can reduce energy consumption by 5% over eco-driving with the baseline predictor.This publication has 17 references indexed in Scilit:
- Saving fuel using wireless vehicle-to-vehicle communicationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Ecological Adaptive Cruise Controller for Plug-In Hybrid Electric Vehicles Using Nonlinear Model Predictive ControlIEEE Transactions on Intelligent Transportation Systems, 2015
- Short Term Prediction of a Vehicle's Velocity Trajectory Using ITSSAE International Journal of Passenger Cars - Electronic and Electrical Systems, 2015
- Dynamic Traffic Feedback Data Enabled Energy Management in Plug-in Hybrid Electric VehiclesIEEE Transactions on Control Systems Technology, 2014
- Comparison of parametric and non-parametric approaches for vehicle speed predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Validating Volt PHEV Model with Dynamometer Test Data Using AutonomieSAE International Journal of Passenger Cars - Mechanical Systems, 2013
- Model Predictive Control of Vehicles on Urban Roads for Improved Fuel EconomyIEEE Transactions on Control Systems Technology, 2012
- Congested traffic states in empirical observations and microscopic simulationsPhysical Review E, 2000
- Locally Weighted LearningPublished by Springer Science and Business Media LLC ,1997
- A behavioural car-following model for computer simulationTransportation Research Part B: Methodological, 1981