HP³: Hierarchical Prediction-Pretrained Planning for Unprotected Left Turn

Trajectory planning for unprotected left turns poses a significant challenge in autonomous driving. Reinforcement learning (RL) offers potential, but existing methods often rely on scenario-specific state representations, limiting their adaptability. This paper introduces Hierarchical Prediction-Pretrained Planning (HP<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup>), a generalizable hierarchical RL framework designed for unprotected left turns. HP<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> leverages historical trajectories of all vehicles and complete map information to achieve versatile state representation and generalizable scene understanding. Its two-layer architecture predicts semantic behavior (upper layer) and generates corresponding trajectories (lower layer). A scene encoder comprehends trajectories and roads, while a trajectory decoder outputs sequential points. To accelerate convergence, we pretrain the main network on a modified trajectory prediction dataset. Evaluation on a CARLA-based map with complex, unprotected left-turn intersections demonstrates HP<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup>’s superiority over rule-based and simple RL-based methods, highlighting the effectiveness of our pretraining approach for this critical autonomous driving task.