Stochastic co-optimization of speed planning and powertrain control with dynamic probabilistic constraints for safe and ecological driving

Abstract

• Stochastic co-optimization of kinematic states and EMS for CAEVs is developed. • Dynamic probabilistic constraints ensuring driving safety are formulated. • A deep learning model predicting the PDF of preceding vehicle speed is constructed. • An efficient hierarchical solver for the co-optimization problem is designed. Ameliorating energy efficiency and enhancing driving safety are both extremely concerning issues for connected and automated electric vehicles (CAEVs) driving in a random traffic environment. To enhance driving safety and fully coordinate the potential conflict between driving safety and energy efficiency, an adaptive co-optimization method of speed planning and energy management strategy (EMS) with dynamic probabilistic constraints is proposed under the framework of stochastic model predictive control. The dynamic probabilistic constraints are enabled by the proposed composite sequence generation model, which predicts the future speed distribution of the preceding vehicle according to the probability relationship among future speed sequence, historical speed sequence, and macroscopic traffic state of downstream road segments, effectively modeling the macro and micro disturbance from random traffic environment and improving the prediction accuracy by about 10% (along with an over 57% decrease in distribution divergence) compared with pure sequence generation model. Comparison with existing co-optimization methods under the same car-following tasks validates the promising performance of the proposed adaptive co-optimization method, which produces dynamic feasible regions for kinematic states according to downstream traffic state and the driving state of the preceding vehicle, raising the driving safety by 14.81% and retaining the relatively high energy efficiency.