Speed Profile Generation Strategy for Efficient Merging of Automated Vehicles on Roundabouts With Realistic Traffic

The capabilities of automated vehicles have increased over the last years, and different driving strategies have shown promising results on a variety of scenarios. However, there are still many challenges to be solved, and handling crowded roundabouts is one of them. This kind of scenario requires both safe and efficient maneuvers from the autonomous driving systems in order to maintain a proper traffic flow. This work presents a strategy to generate different speed profiles for a set of path candidates in order to obtain a merging maneuver according to current traffic scene. The proposed mechanism relies on the use of fictitious accelerations generated by leader and lag vehicles, incorporating by design comfort and safety bounds. The autonomous driving system proposed in this work was tested on realistic driving scenarios collected from public datasets and its performance was compared to human drivers on the same scenarios. The results showed in a variety of situations that the automated vehicle was capable of merging into roundabouts with tight merging gaps while maintaining both comfort and safety constraints.