Successful robot automation requires accurate global localization to support repeatability, task planning, goal specification, and safe operation. However, reliable localization in GNSS-denied environments remains an open problem. Overhead aerial imagery offers a promising solution, but existing approaches primarily target structured urban environments and have been rarely demonstrated in unstructured natural terrain. Limitations of the state-of-the-art include a reliance on models trained for specific environments, as well as difficulty handling repetitive geometries and featureless landscapes commonly found in natural outdoor areas. To overcome these challenges, we present Meridian, a method for matching high-level metric-semantic primitives across aerial images and ground robot RGB-D camera data that achieves accurate global localization and generalizes well across diverse environments, all without any training or algorithmic fine-tuning on area-specific data. We formulate novel consistency metrics to estimate a distribution over robot submap poses and to reject outlier hypotheses in a robust pose graph optimization step for accurate robot trajectory estimation. We demonstrate that our algorithm can localize a ground robot across a wide variety of environments, including an autonomous driving dataset, a park and campus area, and a wilderness camp, with an average optimized trajectory error of 2.4 m over 19 km of ground traversal.

翻译：成功的机器人自动化需要精确的全局定位，以支持可重复性、任务规划、目标指定及安全操作。然而，在GNSS拒止环境中的可靠定位仍是一个开放性问题。高空航空影像提供了有前景的解决方案，但现有方法主要针对结构化城市环境，且极少在非结构化自然地形中得到验证。当前技术的局限性包括依赖于针对特定环境训练的模型，以及难以处理自然户外区域常见的重复几何结构和无特征景观。为应对这些挑战，我们提出Meridian——一种跨航空影像与地面机器人RGB-D相机数据匹配高层度量-语义基元的方法，该方法无需针对区域特定数据进行任何训练或算法微调，即可实现精确的全局定位并在多种环境中良好泛化。我们构建了新颖的一致性度量指标，用于估计机器人子图位姿的分布，并在稳健的位姿图优化步骤中剔除异常假设，从而实现精确的机器人轨迹估计。实验表明，我们的算法可在多样化环境中定位地面机器人（包括自动驾驶数据集、公园与校园区域及野外营地），在19公里地面遍历行程中实现了平均优化轨迹误差2.4米。