Reinforcement Learning-Enabled Decision-Making Strategies for a Vehicle-Cyber-Physical-System in Connected Environment
This work addresses decision-making for autonomous vehicles in connected environments, but it is incremental as it uses existing RL methods without introducing new techniques.
The paper tackled the decision-making problem for autonomous vehicles in a connected environment by applying Q-learning and Dyna reinforcement learning algorithms to derive strategies, analyzing their performance in safety and efficiency.
As a typical vehicle-cyber-physical-system (V-CPS), connected automated vehicles attracted more and more attention in recent years. This paper focuses on discussing the decision-making (DM) strategy for autonomous vehicles in a connected environment. First, the highway DM problem is formulated, wherein the vehicles can exchange information via wireless networking. Then, two classical reinforcement learning (RL) algorithms, Q-learning and Dyna, are leveraged to derive the DM strategies in a predefined driving scenario. Finally, the control performance of the derived DM policies in safety and efficiency is analyzed. Furthermore, the inherent differences of the RL algorithms are embodied and discussed in DM strategies.