{"ID":2835186,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00470","arxiv_id":"2512.00470","title":"LAP: Fast LAtent Diffusion Planner for Autonomous Driving","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.","short_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 mul...","url_abs":"https://arxiv.org/abs/2512.00470","url_pdf":"https://arxiv.org/pdf/2512.00470v3","authors":"[\"Jinhao Zhang\",\"Wenlong Xia\",\"Zhexuan Zhou\",\"Haoming Song\",\"Youmin Gong\",\"Jie Mei\"]","published":"2025-11-29T12:45:05Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Diffusion Model\",\"Variational Autoencoder\"]","has_code":false}