A Decision-Making Model of Left-Turn Behavior for Autonomous Vehicles at Urban Intersections Using a Single-Vehicle Scenario

A left-turn decision-making model that considers information about surrounding vehicles at complex urban intersections is critical for the development of autonomous vehicles. Here, we propose an approach of developing algorithms for left-turn tactical-level decision-making to ensure autonomous vehicles can cross intersections safely. We collected trajectories data were at intersections. Then, a GPR model was trained to predict the trajectories of oncoming straight vehicles. After that, we proposed a conflict resolution method for left-turn behavior of autonomous vehicles at urban intersections and a driving action selection method that considers multiple factors, such as safety, efficiency, comfort and altruism. Finally, we built a simulation and verification platform for algorithm. The reliability and effectiveness of the tactical-level decision-making model was verified by both simulations and real road experiments. The results from this study can provide a theoretical basis for the in-depth study of left-turn driving decision-making in complex and uncertain intersection environments.