Less is More: 自動運転のための軽量かつ強力な視覚言語モデル
Less is More: Lean yet Powerful Vision-Language Model for Autonomous Driving
自動運転を言語問題として捉え、視覚言語モデルを用いて前視カメラ入力から直接軌道を予測する一段階エンドツーエンドフレームワークMax-V1を提案。nuScenesで30%以上の性能向上を達成。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sheng Yang, Tong Zhan, Guancheng Chen, Yanfeng Lu, Jian Wang
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
In this work, we reconceptualize autonomous driving as a generalized language problem and formulate the trajectory planning task as next waypoint prediction. We introduce Max-V1, a novel framework for one-stage end-to-end autonomous driving, named in tribute to the renowned Dutch racing driver Max Verstappen. Our framework presents a single-pass generation paradigm that aligns with the inherent sequentiality of driving. This approach leverages the generative capacity of the Vision-Language Model (VLM) to enable end-to-end trajectory prediction directly from front-view camera input. The efficacy of this method is underpinned by a principled supervision strategy derived from statistical modeling. This provides a well-defined learning objective, which makes the framework highly amenable to mastering complex driving policies through imitation learning from large-scale expert demonstrations. Empirically, our method achieves state-of-the-art performance on the nuScenes dataset, delivering an overall improvement of over 30% compared to prior baselines. Furthermore, it exhibits superior generalization performance on cross-domain datasets acquired from diverse vehicles, demonstrating notable potential for cross-vehicle robustness and adaptability. With these empirical strengths, this work introduces a model that enables fundamental driving behaviors, laying the foundation for the development of more capable self-driving agents. Code will be available upon publication.
