Dueling Deep Q Network for Highway Decision Making in Autonomous Vehicles: A Case Study

Abstract

This work optimizes the highway decision making strategy of autonomous vehicles by using deep reinforcement learning (DRL). First, the highway driving environment is built, wherein the ego vehicle, surrounding vehicles, and road lanes are included. Then, the overtaking decision-making problem of the automated vehicle is formulated as an optimal control problem. Then relevant control actions, state variables, and optimization objectives are elaborated. Finally, the deep Q-network is applied to derive the intelligent driving policies for the ego vehicle. Simulation results reveal that the ego vehicle could safely and efficiently accomplish the driving task after learning and training.

arXiv comment5 pages, 6 figures

References in corpus (4)

• Dueling Network Architectures for Deep Reinforcement Learning
• Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving
• Hierarchical Reinforcement Learning for Self-Driving Decision-Making without Reliance on Labeled Driving Data
• Reinforcement Learning-Enabled Decision-Making Strategies for a Vehicle-Cyber-Physical-System in Connected Environment