提出迭代候选规划框架，让自动驾驶更准更快
iPad: Iterative Proposal-centric End-to-End Autonomous Driving
- 以候选规划为中心，通过迭代注意力优化决策
- 在NAVSIM和CARLA上达到顶尖性能，效率更高
- 轻量辅助任务提升规划质量，适合实际部署
端到端自动驾驶系统通过减少信息损失和误差累积，展现出提升出行安全与效率的巨大潜力。然而，现有方法大多直接基于密集鸟瞰图（BEV）特征生成规划，导致效率低下且规划感知不足。为此，我们提出迭代候选规划框架iPad，将一组候选未来规划作为特征提取和辅助任务的核心。核心是ProFormer，一种通过候选锚定注意力机制迭代优化规划及其关联特征的BEV编码器，有效融合多视角图像数据。此外，引入两个轻量级、候选中心的辅助任务——地图构建与预测，以极小计算开销提升规划质量。在NAVSIM和CARLA Bench2Drive基准上的大量实验表明，iPad在性能上达到当前最优，同时显著优于先前领先方法的效率。
原文摘要 · Abstract (English)
End-to-end (E2E) autonomous driving systems offer a promising alternative to traditional modular pipelines by reducing information loss and error accumulation, with significant potential to enhance both mobility and safety. However, most existing E2E approaches directly generate plans based on dense bird's-eye view (BEV) grid features, leading to inefficiency and limited planning awareness. To address these limitations, we propose iterative Proposal-centric autonomous driving (iPad), a novel framework that places proposals - a set of candidate future plans - at the center of feature extraction and auxiliary tasks. Central to iPad is ProFormer, a BEV encoder that iteratively refines proposals and their associated features through proposal-anchored attention, effectively fusing multi-view image data. Additionally, we introduce two lightweight, proposal-centric auxiliary tasks - mapping and prediction - that improve planning quality with minimal computational overhead. Extensive experiments on the NAVSIM and CARLA Bench2Drive benchmarks demonstrate that iPad achieves state-of-the-art performance while being significantly more efficient than prior leading methods.
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。