NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving

Ximeng Tao, pardis, Dimitar Filev, Reza Langari, Gaurav Pandey

NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving: 6 upvotes on Hugging Face Daily Papers, #27 of 49 papers on 2026-03-10. Day-by-day upvote history.

Vision-language models (VLMs) have emerged as a promising direction for end-to-end autonomous driving (AD) by jointly modeling visual observations, driving context, and language-based reasoning. However, existing VLM-based systems face a trade-off between high-level reasoning and motion planning: large models offer strong semantic understanding but are costly to adapt for precise control, whereas small VLM models can be fine-tuned efficiently but often exhibit weaker reasoning. We propose NaviDriveVLM, a decoupled framework that separates reasoning from action generation using a large-scale Navigator and a lightweight trainable Driver. This design preserves reasoning ability, reduces training cost, and provides an explicit interpretable intermediate representation for downstream planning. Experiments on the nuScenes benchmark show that NaviDriveVLM outperforms large VLM baselines in end-to-end motion planning.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.