LAP: Fast LAtent Diffusion Planner with Fine-Grained Feature Distillation for Autonomous Driving
By: Jinhao Zhang , Wenlong Xia , Zhexuan Zhou and more
Potential Business Impact:
Drives cars smarter and faster, like a human.
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. We further introduce a fine-grained feature distillation mechanism to guide a better interaction and fusion between the high-level semantic planning space and the vectorized scene context. 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 10 times over previous SOTA approaches.
Similar Papers
LAP: Fast LAtent Diffusion Planner with Fine-Grained Feature Distillation for Autonomous Driving
Robotics
Makes self-driving cars plan faster and smarter.
Latent Diffusion Planning for Imitation Learning
Robotics
Teaches robots to learn from less perfect examples.
Latent Adaptive Planner for Dynamic Manipulation
Robotics
Robots learn to catch moving things like humans.