Maneuver Planner for Automated Vehicles on Urban Scenarios

This work presents a maneuver planner for automated vehicles, seamlessly integrated with a motion planner, that is able to make tactical decisions to safely navigate in urban environments. The proposed maneuver planner is able to select the most suitable target lane for the ego-vehicle and to manage different regulatory signals like right of way, must stop or pedestrian crossings. The integration with the motion planner allows to select the current maneuver after exploring a reachable set of trajectories, which brings flexibility to the system in complex and dynamic driving scenarios. The architecture was validated on a real vehicle in two urban scenarios with other traffic agents: an intersection with a pedestrian crossing and an overtaking scenario on a two-way road.