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

원문 초록

Vision-Language Models (VLMs) have demonstrated significant potential for end-to-end autonomous driving. However, fully exploiting their capabilities for safe and reliable vehicle control remains an open research challenge. To systematically examine advances and limitations of VLMs in driving tasks, 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 and evaluation of 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 nuScenes prediction task, comprehensively assessing metrics such as inference time, computational cost, and predictive accuracy. Illustrative examples highlight that, despite their strong scenario interpretation capabilities, VLMs' practical performance in autonomous driving tasks remains concerning, emphasizing the need for further improvements. The code is available at https://github.com/michigan-traffic-lab/LightEMMA.