Space-Time Graph Planner for Unsignalized Intersections with CAVs

Emerging autonomous intersection management systems control the entry order and trajectory for connected and autonomous vehicles ready to traverse a road intersection. They aim to compute trajectories that are safe and optimal in order to reduce congestion, environmental impact, and to cut travel time. We propose a novel approach for computing the fastest waypoint trajectory using search in a discretized space-time graph that produces collision-free paths with variable vehicle speeds complying with traffic rules and vehicle dynamics constraints. The resulting trajectories allow high levels of intersection sharing, high evacuation rate, with a low algorithm runtime even with large scenarios with 1200 vehicles (5.5 s on a laptop).