用潜在空间加速自动驾驶规划，一步生成高质量驾驶策略。
LAP: Fast LAtent Diffusion Planner for Autonomous Driving
- 在变分自编码器的潜空间中分离意图与运动细节，实现高效规划。
- 单步去噪生成规划结果，在nuPlan上推理速度提升最多10倍。
- 适合追求高速度高精度的自动驾驶系统研发人员参考。
扩散模型在建模类人驾驶行为方面表现优异，但其迭代采样过程导致延迟高，且直接作用于原始轨迹点会占用大量容量处理低层运动学信息，而非高层多模态语义。为此，我们提出LAtent Planner（LAP），在变分自编码器学习的潜空间中进行规划，将高层意图与低层运动学解耦，使规划器能够捕捉丰富的多模态驾驶策略。为弥合高层语义规划空间与向量化的场景上下文之间的表征差距，我们引入中间特征对齐机制，实现稳健的信息融合。值得注意的是，LAP仅需一次去噪步骤即可生成高质量规划，显著降低计算开销。在大规模nuPlan基准上的广泛评估表明，LAP在基于学习的规划方法中达到当前最优闭环性能，同时相比之前最先进方法推理速度最高提升10倍。
原文摘要 · Abstract (English)
Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces substantial latency, and operating directly on raw trajectory points forces the model to spend capacity on low-level kinematics, rather than high-level multi-modal semantics. To address these limitations, we propose LAtent Planner (LAP), a framework that plans in a VAE-learned latent space that disentangles high-level intents from low-level kinematics, enabling our planner to capture rich, multi-modal driving strategies. To bridge the representational gap between the high-level semantic planning space and the vectorized scene context, we introduce an intermediate feature alignment mechanism that facilitates robust information fusion. Notably, LAP can produce high-quality plans in one single denoising step, substantially reducing computational overhead. Through extensive evaluations on the large-scale nuPlan benchmark, LAP achieves state-of-the-art closed-loop performance among learning-based planning methods, while demonstrating an inference speed-up of at most 10x over previous SOTA approaches.
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。