DriveVLN：面向自动驾驶的无地图视觉语言导航
DriveVLN: Towards Mapless Vision-and-Language Navigation in Autonomous Driving
将视觉语言导航（VLN）从室内逐步指令扩展到自动驾驶的无地图点对点导航，提出基于自然语言描述和视觉线索（路标、地标、文字指示）的导航任务，并构建CARLA仿真引擎支持大规模训练与闭环评测，为语言驱动的自动驾驶提供新基准。
原文依据 DriveVLN employs visual and linguistic priors to guide vehicles toward destinations based solely on concise natural-language descriptions, without access to predefined maps or routes.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动驾驶近期取得了实质性进展，在大多数真实环境中实现了可靠性能。然而，现有算法仍严重依赖高精地图，导致其在室内停车场等无地图场景中失效。这些限制阻碍了无缝的点到点导航，并制约了自动驾驶系统的更广泛部署。为解决这一挑战，我们提出DriveVLN，一项将视觉语言导航（VLN）扩展到自动驾驶的新任务。DriveVLN利用视觉和语言先验，仅基于简洁的自然语言描述引导车辆驶向目的地，无需预定义地图或路线。与传统VLN依赖室内环境中详细的逐步指令不同，DriveVLN要求模型基于多样化的视觉线索和历史信息（包括标志、地标和文字指示）生成导航信息。我们进一步开发了一个基于CARLA的仿真引擎，包含200多个由真实道路扫描重建的逼真场景，支持大规模训练和闭环评估。通过在真实数据上进行监督微调，随后在仿真中进行强化学习，建立了一个基线模型。综合实验表明，DriveVLN有效连接了基于地图和无地图驾驶，为复杂真实环境中统一的、语言驱动的自动驾驶导航提供了新基础。
英文原文摘要 1483 字符
Autonomous driving has made substantial progress recently, achieving reliable performance in most real-world environments. However, existing algorithms still depend heavily on high-definition maps, making them ineffective in mapless scenarios such as indoor parking lots. These limitations hinder seamless point-to-point navigation and restrict the broader deployment of the autonomous driving system.To address this challenge, we propose DriveVLN, a new task that extends Vision-and-Language Navigation (VLN) to autonomous driving. DriveVLN employs visual and linguistic priors to guide vehicles toward destinations based solely on concise natural-language descriptions, without access to predefined maps or routes. Unlike conventional VLN, which relies on detailed step-wise instructions in indoor environments, DriveVLN requires models to produce navigation information based on diverse visual cues and history, including signs, landmarks, and textual indicators.We further develop a CARLA-based simulation engine comprising over 200 realistic scenes reconstructed from real road scans, enabling large-scale training and closed-loop evaluation. A baseline model is established through supervised fine-tuning on real data, followed by reinforcement learning in simulation.Comprehensive experiments show that DriveVLN effectively bridges map-based and mapless driving, providing a new foundation for unified, language-driven autonomous navigation in complex real-world environments.