AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving
This work addresses inefficiencies in autonomous driving systems by enhancing reasoning and action generation, though it is incremental as it builds on existing vision-language model frameworks.
The paper tackles the challenge of integrating vision-language models into end-to-end autonomous driving by proposing AutoMoT, a unified vision-language-action model that uses an asynchronous mixture-of-transformers architecture to improve efficiency and performance. It achieves competitive results on multiple benchmarks and shows that pre-trained VLMs can handle scene understanding with prompting but require fine-tuning for action tasks.
Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either struggle to resolve distribution misalignment between reasoning and action spaces, underexploit the general reasoning capabilities of pretrained VLMs, or incur substantial inference latency during action policy generation, which degrades driving performance. To address these challenges, we propose \OURS in this work, an end-to-end AD framework that unifies reasoning and action generation within a single vision-language-action (VLA) model. Our approach leverages a mixture-of-transformer (MoT) architecture with joint attention sharing, which preserves the general reasoning capabilities of pre-trained VLMs while enabling efficient fast-slow inference through asynchronous execution at different task frequencies. Extensive experiments on multiple benchmarks, under both open- and closed-loop settings, demonstrate that \OURS achieves competitive performance compared to state-of-the-art methods. We further investigate the functional boundary of pre-trained VLMs in AD, examining when AD-tailored fine-tuning is necessary. Our results show that pre-trained VLMs can achieve competitive multi-task scene understanding performance through semantic prompting alone, while fine-tuning remains essential for action-level tasks such as decision-making and trajectory planning. We refer to \href{https://automot-website.github.io/}{Project Page} for the demonstration videos and qualitative results.