Personalized Automated Braking for One-Pedal Driving in Electric Vehicles Using Model Predictive Control

In this article, we propose an advanced automated braking algorithm, named personalized one-pedal driving (POPD), for electrified vehicles capable of learning a driver’s braking behaviors from collected data through model predictive control (MPC). One-pedal driving (OPD) is becoming one of the necessary features for electric vehicles (EVs), as it increases the amount of energy regeneration over a trip and reduces the driver’s effort on the brake pedal. To mimic a driver’s braking behavior in the MPC’s control design, we consider both headway and perceptual constraints. We have analyzed real-world on-road data from 450 drivers to investigate the constraints’ dependence on a driver. In addition, we introduce a learning framework into the POPD in which the weights of the MPC cost function are optimized using particle swarm optimization (PSO). Moreover, to investigate the impact of prediction accuracy on POPD performance, we have conducted a comparative case study on prediction methods and horizon lengths using real-world driving data. Both open- and closed-loop (human-in-the-loop) simulation results demonstrate the efficacy of the proposed POPD method compared with a benchmark control method, the desired relative distance-based personalized braking (DRD-PB) algorithm. Specifically, the human-in-the-loop results from two drivers show that brake pedal use can be reduced on a specific route by approximately 80%.