Energy-Efficient Autonomous Driving Using Cognitive Driver Behavioral Models and Reinforcement Learning

TL;DR

This paper proposes a framework that combines cognitive driver behavior modeling and reinforcement learning to develop energy-efficient autonomous driving policies in mixed traffic environments.

Contribution

It introduces a novel approach integrating cognitive hierarchy theory with reinforcement learning for energy-efficient autonomous vehicle decision-making.

Findings

Effective modeling of human driver behavior

Improved energy efficiency in autonomous driving policies

Enhanced safety and interaction handling

Abstract

Autonomous driving technologies are expected to not only improve mobility and road safety but also bring energy efficiency benefits. In the foreseeable future, autonomous vehicles (AVs) will operate on roads shared with human-driven vehicles. To maintain safety and liveness while simultaneously minimizing energy consumption, the AV planning and decision-making process should account for interactions between the autonomous ego vehicle and surrounding human-driven vehicles. In this chapter, we describe a framework for developing energy-efficient autonomous driving policies on shared roads by exploiting human-driver behavior modeling based on cognitive hierarchy theory and reinforcement learning.