Saved in:
Bibliographic Details
Main Authors: Guo, Zilong, Luo, Yi, Sha, Long, Wang, Dongxu, Wang, Panqu, Xu, Chenyang, Yang, Yi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.02659
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918134857859072
author Guo, Zilong
Luo, Yi
Sha, Long
Wang, Dongxu
Wang, Panqu
Xu, Chenyang
Yang, Yi
author_facet Guo, Zilong
Luo, Yi
Sha, Long
Wang, Dongxu
Wang, Panqu
Xu, Chenyang
Yang, Yi
contents End-to-end autonomous driving has drawn tremendous attention recently. Many works focus on using modular deep neural networks to construct the end-to-end archi-tecture. However, whether using powerful large language models (LLM), especially multi-modality Vision Language Models (VLM) could benefit the end-to-end driving tasks remain a question. In our work, we demonstrate that combining end-to-end architectural design and knowledgeable VLMs yield impressive performance on the driving tasks. It is worth noting that our method only uses a single camera and is the best camera-only solution across the leaderboard, demonstrating the effectiveness of vision-based driving approach and the potential for end-to-end driving tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02659
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
Guo, Zilong
Luo, Yi
Sha, Long
Wang, Dongxu
Wang, Panqu
Xu, Chenyang
Yang, Yi
Computer Vision and Pattern Recognition
Robotics
End-to-end autonomous driving has drawn tremendous attention recently. Many works focus on using modular deep neural networks to construct the end-to-end archi-tecture. However, whether using powerful large language models (LLM), especially multi-modality Vision Language Models (VLM) could benefit the end-to-end driving tasks remain a question. In our work, we demonstrate that combining end-to-end architectural design and knowledgeable VLMs yield impressive performance on the driving tasks. It is worth noting that our method only uses a single camera and is the best camera-only solution across the leaderboard, demonstrating the effectiveness of vision-based driving approach and the potential for end-to-end driving tasks.
title 2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2509.02659