Gaussian learning‐based fuzzy predictive cruise control for improving safety and economy of connected vehicles. Issue 5 (19th March 2020)

• Record Type: Journal Article
• Authors: He, Defeng; Peng, Binbin
• Is Part Of: IET intelligent transport systems. Volume 14:Issue 5(2020)
• Page Start: 346
• Page End: 355
• Publication Date: 2020-03-19
• Subjects: optimal control -- fuel economy -- velocity control -- road vehicles -- Gaussian processes -- regression analysis -- adaptive control -- fuzzy set theory -- predictive control -- learning (artificial intelligence); vehicle‐following scenario -- Gaussian process regression model -- preceding vehicle -- prediction horizon -- fuzzy decision method -- fuzzy predictive cruise controller -- constrained receding horizon optimal control problem -- cost function -- acceleration prediction -- safety -- connected vehicles -- adaptive cruise control problem -- Gaussian learning‐based fuzzy predictive cruise control approach -- CarSim/Simulink co‐simulation; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2019.0452
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : This study considers an adaptive cruise control problem of connected vehicles in the vehicular ad‐hoc network and proposes a Gaussian learning‐based fuzzy predictive cruise control approach to enhance the fuel efficiency and safety of the connected vehicles in a vehicle‐following scenario. First, a Gaussian process regression model is introduced and trained with real data to estimate the future acceleration of the preceding vehicle over the prediction horizon. Moreover, with assessing traffic scenarios, the weights characterising the importance of individual performance are adjusted by a fuzzy decision method in real time. Then a fuzzy predictive cruise controller is obtained by online solving a constrained receding horizon optimal control problem with a changing cost function and acceleration prediction of the preceding vehicle. Finally, through CarSim/Simulink co‐simulation, it is shown that the proposed approach has an improvement in fuel economy and safety compared with conventional predictive cruise control algorithms.