C2F-Planner: Interaction-Aware Coarse-to-Fine Planning for Autonomous Vehicles

Abstract

Ensuring safe and socially compliant driving is essential for autonomous vehicle planning. However, one of the significant challenges remains the performance bottleneck caused by interaction uncertainty in complex traffic scenarios. Traditional planning algorithms typically account for all traffic participants, leading to overly generalized predictions and decisions that do not adequately capture essential interactive dynamics. In real-world driving, autonomous vehicles interact primarily with a subset of surrounding agents, whose behaviors are dynamically influenced by the vehicle's decisions. To address this, we propose a novel framework with two key innovations. First, we introduce a supervised learning-based approach that simplifies the complex interaction agents recognition into a classification problem, incorporating a dynamically weighted attention mechanism to identify potential interaction agents accurately. Secondly, we develop a coarse-to-fine decision decoding strategy. Initially, the autonomous driving system makes preliminary coarse decisions based on the scene context. These decisions are then integrated with interaction agents to form multiple cohesive interaction units. Within these units, fine-grained interaction reasoning is employed to predict the future behaviors of interaction agents and refine the ego vehicle's decisions accordingly. Experimental results indicate that our method significantly enhances the accuracy of interaction modelling and the robustness of decision-making in complex scenarios, providing a scalable solution to improve the safety and intelligence of autonomous driving systems. Code available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/JaneFo/C2F-Planner.git</uri>