Visibility-Aware Adaptative Speed Planner for Human-like Navigation in Roundabouts

Autonomous driving demands the most reliable perception and navigation technologies. These systems should consider both the other agents in the road and the limitations of the on-board sensors. Knowing sensor limitations in real time allows not only to predict the movement of the other agents but also to robustly identify the free space in the road. This paper presents a novel approach that adapts the control of an autonomous vehicle to the real road circumstances in specifically challenging scenarios, i.e., roundabouts. The proposal provides a visibility map that helps the system to calculate collision-free trajectories and to adapt the control techniques to the traffic demands, selecting among comfortable or more ambitious configurations. Tests performed in real traffic have successfully assessed the suitability of the proposed solution.