LightEMMA: Lightweight End-to-End Multimodal Model for Autonomous Driving

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qiao, Zhijie, Li, Haowei, Cao, Zhong, Liu, Henry X.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914034897387520
author Qiao, Zhijie
Li, Haowei
Cao, Zhong
Liu, Henry X.
author_facet Qiao, Zhijie
Li, Haowei
Cao, Zhong
Liu, Henry X.
contents Vision-Language Models (VLMs) have demonstrated significant potential for end-to-end autonomous driving. However, the field still lacks a practical platform that enables dynamic model updates, rapid validation, fair comparison, and intuitive performance assessment. To that end, we introduce LightEMMA, a Lightweight End-to-End Multimodal Model for Autonomous driving. LightEMMA provides a unified, VLM-based autonomous driving framework without ad hoc customizations, enabling easy integration with evolving state-of-the-art commercial and open-source models. We construct twelve autonomous driving agents using various VLMs and evaluate their performance on the challenging nuScenes prediction task, comprehensively assessing computational metrics and providing critical insights. Illustrative examples show that, although VLMs exhibit strong scenario interpretation capabilities, their practical performance in autonomous driving tasks remains a concern. Additionally, increased model complexity and extended reasoning do not necessarily lead to better performance, emphasizing the need for further improvements and task-specific designs. The code is available at https://github.com/michigan-traffic-lab/LightEMMA.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00284
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LightEMMA: Lightweight End-to-End Multimodal Model for Autonomous Driving
Qiao, Zhijie
Li, Haowei
Cao, Zhong
Liu, Henry X.
Robotics
Artificial Intelligence
Vision-Language Models (VLMs) have demonstrated significant potential for end-to-end autonomous driving. However, the field still lacks a practical platform that enables dynamic model updates, rapid validation, fair comparison, and intuitive performance assessment. To that end, we introduce LightEMMA, a Lightweight End-to-End Multimodal Model for Autonomous driving. LightEMMA provides a unified, VLM-based autonomous driving framework without ad hoc customizations, enabling easy integration with evolving state-of-the-art commercial and open-source models. We construct twelve autonomous driving agents using various VLMs and evaluate their performance on the challenging nuScenes prediction task, comprehensively assessing computational metrics and providing critical insights. Illustrative examples show that, although VLMs exhibit strong scenario interpretation capabilities, their practical performance in autonomous driving tasks remains a concern. Additionally, increased model complexity and extended reasoning do not necessarily lead to better performance, emphasizing the need for further improvements and task-specific designs. The code is available at https://github.com/michigan-traffic-lab/LightEMMA.
title LightEMMA: Lightweight End-to-End Multimodal Model for Autonomous Driving
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2505.00284