关键词: 空地协同, 数据集构建, 特殊障碍物检测, 通行性策略

Abstract: The recognition and handling of special obstacles are critical to ensuring the safe operation of ground equipment in air–ground collaborative scenarios. To address the lack of data samples in unstructured environments, a detection dataset comprising 33,124 images was developed, featuring a wide range of typical special obstacles to support recognition tasks in complex scenes. A comprehensive evaluation metric integrating category information and localization accuracy is designed to enhance the objectivity and reliability of algorithm performance comparisons. Additionally, a passability analysis method is proposed, which combines physical characteristics with environmental semantics to guide path planning for unmanned ground systems. Experimental results demonstrate that the proposed dataset and evaluation framework significantly improve detection accuracy, and the method effectively identifies typical obstacles such as potholes and water surfaces in unstructured environments.

Key words: ground-air collaboration, dataset construction, special obstacle detection, passability strategy