A Novel Framework for Anomaly Detection of Robot Behaviors

Autonomous mobile robots are designed to behave appropriately in changing real-world environments without human intervention. In order to satisfy the requirements of autonomy, robots have to cope with unknown settings and several issues of uncertainties in dynamic, unstructured and complex environments. A first step is to provide a robot with cognitive capabilities and the ability of self-examination to detect behavioral abnormalities. Unfortunately, most existing anomaly detection systems are neither suitable for the domain of robotic behavior nor flexible enough or even well generalizable. In the following article, we introduce a novel anomaly detection framework based on spatial-temporal models for robotic behaviors which is generally applicable for e.g., plan execution monitoring. The introduced framework combines the methodology of Kohonen’s Self-organizing Maps (SOMs) and Probabilistic Graphical Models (PGM) exploiting all advantages of both concepts. The underlying methods of the framework are discussed briefly, whereas the data-driven training of the spatial-temporal model and the reasoning process are described in detail. Finally, the framework is evaluated with different scenarios to emphasize its potential and its high level of generalization and flexibility in robotic application.