DA-Nav：方向感知的城市规模视觉语言导航
DA-Nav: Direction-Aware City-Scale Vision-Language Navigation
浏览论文内容
中文总结 AI 辅助
研究城市规模户外导航难题，提出DA-Nav框架，利用商业导航工具方向指示，经思维链推理实现轨迹恢复，引入ReDA数据集。实验表明其在未见环境成功率高，优于现有方法，还能适应多种机器人实现稳定户外导航。
中文摘要 AI 辅助
城市规模的户外导航目前因严重依赖密集地图或昂贵的导航监督而受阻。在这项工作中，我们引入了一种利用商业导航工具（如谷歌地图）的方向指示的新范式。为弥合商业指示与可执行导航行动之间的差距，同时通过稳健的轨迹恢复减轻长期误差积累，我们提出了DA-Nav，一种方向感知视觉语言导航框架，将导航重新表述为以自我为中心的二维图像平面上的离散空间定位问题。为实现轨迹恢复，DA-Nav采用了包括偏差评估、行动预测和目标网格选择的思维链推理过程。我们还引入了ReDA数据集，提供方向感知指示和恢复轨迹以增强空间定位并支持思维链恢复推理。在CARLA中的大量实验表明，DA-Nav在未见城市环境中成功率达56.16%，优于现有方法且恢复能力更强。此外，无需微调，DA-Nav可无缝适应四足和人形机器人，在复杂现实世界环境中实现稳定的千米级闭环户外导航。
英文摘要
City-scale outdoor navigation is currently hindered by the heavy reliance on dense maps or costly navigation supervision. In this work, we introduce a novel paradigm for leveraging directional instructions from commercial navigation tools (e.g., Google Maps). To bridge the gap between commercial instructions and executable navigation actions, while mitigating long-horizon error accumulation through robust trajectory recovery, we propose DA-Nav, a Direction-Aware vision-language Navigation framework that reformulates navigation as a discrete spatial grounding problem on the egocentric 2D image plane. To achieve trajectory recovery, DA-Nav employs a Chain-of-Thought (CoT) reasoning process encompassing deviation assessment, action prediction, and target grid selection. We further introduce ReDA, a dataset that provides direction-aware instructions and recovery trajectories to enhance spatial grounding and support CoT recovery reasoning. Extensive experiments in CARLA demonstrate that DA-Nav achieves a high success rate of 56.16% in unseen urban environments, outperforming existing State-of-The-Art (SoTA) methods while maintaining a substantially stronger recovery capability. Furthermore, without fine-tuning, DA-Nav seamlessly adapts to both quadruped and humanoid robots, enabling stable kilometer-scale closed-loop outdoor navigation in complex real world environments.
发表机构
- School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）
- Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
- State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所人工智能安全国家重点实验室）
- National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
- School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
- XYZ Embodied AI（XYZ具身人工智能）
机构由 AI 辅助整理，请以论文原文为准。
