English

LAP: Fast LAtent Diffusion Planner for Autonomous Driving

Robotics 2026-03-06 v3

Abstract

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.

Keywords

Cite

@article{arxiv.2512.00470,
  title  = {LAP: Fast LAtent Diffusion Planner for Autonomous Driving},
  author = {Jinhao Zhang and Wenlong Xia and Zhexuan Zhou and Haoming Song and Youmin Gong and Jie Mei},
  journal= {arXiv preprint arXiv:2512.00470},
  year   = {2026}
}
R2 v1 2026-07-01T08:00:49.638Z