Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zixuan, Zhang, Hengyuan, Chen, Ting-Hsuan, Guo, Yuliang, Paz, David, Huang, Xinyu, Ren, Liu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918167021879296
author Wu, Zixuan
Zhang, Hengyuan
Chen, Ting-Hsuan
Guo, Yuliang
Paz, David
Huang, Xinyu
Ren, Liu
author_facet Wu, Zixuan
Zhang, Hengyuan
Chen, Ting-Hsuan
Guo, Yuliang
Paz, David
Huang, Xinyu
Ren, Liu
contents Parking is a critical pillar of driving safety. While recent end-to-end (E2E) approaches have achieved promising in-domain results, robustness under domain shifts (e.g., weather and lighting changes) remains a key challenge. Rather than relying on additional data, in this paper, we propose Dino-Diffusion Parking (DDP), a domain-agnostic autonomous parking pipeline that integrates visual foundation models with diffusion-based planning to enable generalized perception and robust motion planning under distribution shifts. We train our pipeline in CARLA at regular setting and transfer it to more adversarial settings in a zero-shot fashion. Our model consistently achieves a parking success rate above 90% across all tested out-of-distribution (OOD) scenarios, with ablation studies confirming that both the network architecture and algorithmic design significantly enhance cross-domain performance over existing baselines. Furthermore, testing in a 3D Gaussian splatting (3DGS) environment reconstructed from a real-world parking lot demonstrates promising sim-to-real transfer.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20335
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parking
Wu, Zixuan
Zhang, Hengyuan
Chen, Ting-Hsuan
Guo, Yuliang
Paz, David
Huang, Xinyu
Ren, Liu
Robotics
Computer Vision and Pattern Recognition
Parking is a critical pillar of driving safety. While recent end-to-end (E2E) approaches have achieved promising in-domain results, robustness under domain shifts (e.g., weather and lighting changes) remains a key challenge. Rather than relying on additional data, in this paper, we propose Dino-Diffusion Parking (DDP), a domain-agnostic autonomous parking pipeline that integrates visual foundation models with diffusion-based planning to enable generalized perception and robust motion planning under distribution shifts. We train our pipeline in CARLA at regular setting and transfer it to more adversarial settings in a zero-shot fashion. Our model consistently achieves a parking success rate above 90% across all tested out-of-distribution (OOD) scenarios, with ablation studies confirming that both the network architecture and algorithmic design significantly enhance cross-domain performance over existing baselines. Furthermore, testing in a 3D Gaussian splatting (3DGS) environment reconstructed from a real-world parking lot demonstrates promising sim-to-real transfer.
title Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parking
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.20335