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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Reddy, Ruturaj, Barua, Hrishav Bakul, Loo, Junn Yong, Nguyen, Thanh Thi, Krishnasamy, Ganesh
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912887122952192
author Reddy, Ruturaj
Barua, Hrishav Bakul
Loo, Junn Yong
Nguyen, Thanh Thi
Krishnasamy, Ganesh
author_facet Reddy, Ruturaj
Barua, Hrishav Bakul
Loo, Junn Yong
Nguyen, Thanh Thi
Krishnasamy, Ganesh
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07339
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RAPiD: Real-time Deterministic Trajectory Planning via Diffusion Behavior Priors for Safe and Efficient Autonomous Driving
Reddy, Ruturaj
Barua, Hrishav Bakul
Loo, Junn Yong
Nguyen, Thanh Thi
Krishnasamy, Ganesh
Artificial Intelligence
Machine Learning
Robotics
I.2.9; I.5.1
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.
title RAPiD: Real-time Deterministic Trajectory Planning via Diffusion Behavior Priors for Safe and Efficient Autonomous Driving
topic Artificial Intelligence
Machine Learning
Robotics
I.2.9; I.5.1
url https://arxiv.org/abs/2602.07339