In order for robots to safely navigate in unseen scenarios using learning-based methods, it is important to accurately detect out-of-training-distribution (OoD) situations online. Recently, Gaussian process state-space models (GPSSMs) have proven useful to discriminate unexpected observations by comparing them against probabilistic predictions. However, the capability for the model to correctly distinguish between in- and out-of-training distribution observations hinges on the accuracy of these predictions, primarily affected by the class of functions the GPSSM kernel can represent. In this paper, we propose (i) a novel approach to embed existing domain knowledge in the kernel and (ii) an OoD online runtime monitor, based on receding-horizon predictions. Domain knowledge is assumed given as a dataset collected either in simulation or using a nominal model. Numerical results show that the informed kernel yields better regression quality with smaller datasets, as compared to standard kernel choices. We demonstrate the effectiveness of the OoD monitor on a real quadruped navigating an indoor setting, which reliably classifies previously unseen terrains.

翻译：为使机器人能够借助基于学习的方法在未知场景中安全导航，在线准确检测训练分布外（OoD）情况至关重要。近期，高斯过程状态空间模型（GPSSM）通过将观测值与概率预测结果进行对比，被证实可有效区分意外观测。然而，该模型正确区分训练分布内与分布外观测值的能力取决于这些预测的准确性，而预测准确性主要受GPSSM核函数所能表示的函数类别影响。本文提出：（i）一种将现有领域知识嵌入核函数的新方法；（ii）基于后退时域预测的在线OoD运行时监测器。假设领域知识以数据集形式提供，该数据集可通过仿真或标称模型采集。数值结果表明，与标准核函数选择相比，信息增强型核函数能在更小数据集上实现更优的回归质量。我们通过一个在室内环境中导航的真实四足机器人验证了OoD监测器的有效性，该监测器能可靠分类此前未见过的地形。