Towards Energy-Efficient Autonomous Driving: A Multi-Objective Reinforcement Learning Approach

Abstract

Dear Editor, With the development of automobile industry and artificial intelligence (AI) domains, autonomous vehicles (AVs) are becoming a reality and promise to revolutionize human mobility [1]–[3]. The decision-making system of AVs is crucial, which is typically required to trade off multiple competing objectives. For example, when determining driving policies, autonomous electric vehicles (AEVs) need to consider two conflicting objectives: transport efficiency and electricity consumption. As one of state-of-the-art AI technologies, reinforcement learning (RL) has demonstrated its potential in a series of challenging tasks. Accordingly, RL has attracted considerable attention from global researchers [4].