Residual Policy Learning for Powertrain Control

TL;DR

This paper introduces a residual policy learning approach for powertrain control that enhances eco-driving strategies by providing residual actions to default controllers, improving fuel efficiency and adaptability in simulated scenarios.

Contribution

The paper presents a residual policy learning method for powertrain control that outperforms traditional baseline policies and offers a practical alternative to training RL agents from scratch.

Findings

RPL agent learns improved residual policies quickly.

RPL outperforms baseline policies in fuel efficiency.

RL agent eventually surpasses RPL in some measures.

Abstract

Eco-driving strategies have been shown to provide significant reductions in fuel consumption. This paper outlines an active driver assistance approach that uses a residual policy learning (RPL) agent trained to provide residual actions to default power train controllers while balancing fuel consumption against other driver-accommodation objectives. Using previous experiences, our RPL agent learns improved traction torque and gear shifting residual policies to adapt the operation of the powertrain to variations and uncertainties in the environment. For comparison, we consider a traditional reinforcement learning (RL) agent trained from scratch. Both agents employ the off-policy Maximum A Posteriori Policy Optimization algorithm with an actor-critic architecture. By implementing on a simulated commercial vehicle in various car-following scenarios, we find that the RPL agent quickly learns significantly improved policies compared to a baseline source policy but in some measures not as good as those eventually possible with the RL agent trained from scratch.