提出精准轨迹选择框架，提升自动驾驶在复杂场景下的安全规划能力。
DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
- 采用粗到细的候选轨迹过滤策略，逐步缩小最优路径搜索范围。
- 在NAVSIM v1和v2上分别达到93.5%和87.1%的轨迹匹配率，性能领先。
- 适合关注自动驾驶端到端规划与安全性评估的研究者或工程团队。
自动驾驶车辆需在复杂交通环境中安全行驶。基于回归的方法仅模仿单一专家轨迹，难以显式评估预测轨迹的安全性。选择类方法通过生成并评分多个候选轨迹来改善这一问题，但在数千个候选中精确筛选最优解、区分细微但关键的安全差异方面仍面临优化挑战，尤其在罕见复杂场景下。本文提出DriveSuprim，通过粗到细的渐进式候选过滤、基于旋转的增强方法以提升分布外场景鲁棒性，以及自蒸馏训练框架实现训练稳定。该方法在不依赖额外数据的前提下，在NAVSIM v1上取得93.5% PDMS，在NAVSIM v2上达87.1% EPDMS，且在Bench2Drive基准上获得83.02分驾驶得分和60.00%成功率，展现出在多种驾驶场景中的优越规划能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。