Autonomous vehicles must navigate safely in complex driving environments. Imitating a single expert trajectory, as in regression-based approaches, usually does not explicitly assess the safety of the predicted trajectory. Selection-based methods address this by generating and scoring multiple trajectory candidates and predicting the safety score for each. However, they face optimization challenges in precisely selecting the best option from thousands of candidates and distinguishing subtle but safety-critical differences, especially in rare and challenging scenarios. We propose DriveSuprim to overcome these challenges and advance the selection-based paradigm through a coarse-to-fine paradigm for progressive candidate filtering, a rotation-based augmentation method to improve robustness in out-of-distribution scenarios, and a self-distillation framework to stabilize training. DriveSuprim achieves state-of-the-art performance, reaching 93.5% PDMS in NAVSIM v1 and 87.1% EPDMS in NAVSIM v2 without extra data, with 83.02 Driving Score and 60.00 Success Rate on the Bench2Drive benchmark, demonstrating superior planning capabilities in various driving scenarios.

翻译：自动驾驶车辆必须在复杂的驾驶环境中安全导航。基于回归的方法通过模仿单一专家轨迹，通常无法显式评估预测轨迹的安全性。基于选择的方法通过生成并评分多个轨迹候选，并为每个候选预测安全分数来解决这一问题。然而，这些方法在从数千个候选轨迹中精确选择最优选项、区分细微但安全关键差异方面面临优化挑战，尤其是在罕见和具有挑战性的场景中。为克服这些挑战并推进基于选择的范式，我们提出了DriveSuprim，其包含：用于渐进式候选过滤的由粗到精范式、提升分布外场景鲁棒性的基于旋转的数据增强方法，以及稳定训练的自蒸馏框架。DriveSuprim实现了最先进的性能，在无额外数据的情况下，于NAVSIM v1中达到93.5% PDMS，在NAVSIM v2中达到87.1% EPDMS，并在Bench2Drive基准测试中获得83.02驾驶分数和60.00成功率，展现了在各种驾驶场景中卓越的规划能力。