Sustainable DDPG-based Path Tracking For Connected Autonomous Electric Vehicles in extra-urban scenarios

Abstract

This paper addresses the path-tracking control problem for Connected Autonomous Electric Vehicles (CAEVs) moving in a smart Cooperative Connected Automated Mobility (CCAM) environment, where a smart infrastructure suggests the reference behaviour to achieve. To solve this problem, a novel energy-efficient Deep Deterministic Policy Gradient-based (DDPG) Algorithm, able to minimize its energy consumption while guaranteeing the optimal tracking of the suggested path, is proposed. Specifically, in order to improve the power autonomy and the battery state of charge (SOC), a Comprehensive Power-based Electric Vehicle Consumption Model (CPEM) is exploited for the training of the DDPG agent. The training process confirms the capability of DDPG agent into learning the safe eco-driving policy, while a case of study proves the advantages and the performance of the overall closed-loop of the proposed control strategy.