RAPiD: Real-time Deterministic Trajectory Planning via Diffusion Behavior Priors for Safe and Efficient Autonomous Driving

TL;DR

RAPiD introduces a deterministic, efficient trajectory planning method for autonomous driving by distilling a diffusion-based planner into a fast policy, enhancing safety, efficiency, and generalization in complex driving scenarios.

Contribution

The paper presents RAPiD, a novel framework that converts diffusion-based trajectory planning into a real-time deterministic policy using score-regularized optimization and safety-focused supervision.

Findings

Achieves 8x speedup over diffusion baselines.

Demonstrates state-of-the-art generalization on interPlan benchmark.

Maintains competitive performance in complex driving scenarios.

Abstract

Diffusion-based trajectory planners have demonstrated strong capability for modeling the multimodal nature of human driving behavior, but their reliance on iterative stochastic sampling poses critical challenges for real-time, safety-critical deployment. In this work, we present RAPiD, a deterministic policy extraction framework that distills a pretrained diffusion-based planner into an efficient policy while eliminating diffusion sampling. Using score-regularized policy optimization, we leverage the score function of a pre-trained diffusion planner as a behavior prior to regularize policy learning. To promote safety and passenger comfort, the policy is optimized using a critic trained to imitate a predictive driver controller, providing dense, safety-focused supervision beyond conventional imitation learning. Evaluations demonstrate that RAPiD achieves competitive performance on closed-loop nuPlan scenarios with an 8x speedup over diffusion baselines, while achieving state-of-the-art generalization among learning-based planners on the interPlan benchmark. The official website of this work is: https://github.com/ruturajreddy/RAPiD.