Dino-Diffusion Modular Designs Bridge the Cross-Domain Gap in Autonomous Parking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |