Emergence of Cooperative Automated Driving Control at Roundabouts Using Deep Reinforcement Learning

This study proposes a deep reinforcement learning mechanism to obtain cooperative driving control of autonomous vehicles at a roundabout, one of the intersections without signal control. This study introduces three new mechanisms to the previous model that enable learning the cooperative control: (i) gradual learning by changing the new vehicle departure interval, (ii) utilization of information about the vehicle's destination, and (iii) additional penalty for approaching walls and other vehicles. We conducted simulation experiments to investigate the effectiveness of the proposed methods. The experimental results showed that the proposed methods enable the acquisition of cooperative vehicle control that can safely navigate a roundabout while reducing the collision rate.