Predictive kinetic energy management for an add‐on driver assistance eco‐driving of heavy vehicles

Abstract

This study presents a radar‐based predictive kinetic energy management (PKEM) framework that is applicable as an add‐on driver assistance module for a heavy vehicle with an internal combustion engine powertrain. The proposed framework attempts to minimise fuel consumption by estimating the motion of the leading vehicle from radar information and optimising the inputs to the ego vehicle in a predictive manner. The PKEM framework consists of a driver‐pedal pre‐filter, an interacting multiple model radar‐based filter and predictor of traffic object states, and a non‐linear model predictive controller. The framework is integrated with established human‐driver car‐following models representing various driving styles and evaluated over a set of standardised driving cycles. The authors found that the energy‐saving benefits can be as much as 23% over the baseline driver‐only case with minimal compromises on travel time in urban environments, while the benefits are nearly negligible on the highway cycle. The results included also show the potential trade‐offs in accommodating driver‐desired inputs.

Safety Filtering for Reinforcement Learning-based Adaptive Cruise Control

“…In addition to the reward shaping approach, the conventional PID ACC is used as a baseline which, like in the case of RL, is designed by dividing the control into phases for the in range and out of range conditions (Canale and Malan, 2003). The traction torque T t request is given by PID controller and an optimal gear is chosen based on the gear with the lowest fuel rate given the desired traction torque and vehicle velocity (Yoon et al, 2020;Kerbel et al, 2022).…”

Safe Reinforcement Learning for an Energy-Efficient Driver Assistance System

“…As typical commercial routes include frequent stopping and starting along with various required speeds, the ACC approach may be cumbersome for a driver to use. In Yoon et al (2020), a driver assistance implementation is proposed that uses radar information and motion models to directly modulate the torque request to the powertrain/braking system. To this end, an MPC scheme is employed to optimize traction/braking torque/power while tracking the driver's desired acceleration and maintaining a safe distance to a leading vehicle.…”