Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends

As deep learning continues to dominate all state-of-the-art computer vision tasks, it is increasingly becoming the essential building blocks for robotic perception. As a result, the research questions concerning the safety and reliability of learning-based perception are gaining increased importance. Although there is an established field that studies safety certification and convergence guarantee of complex software systems for decision-making during design-time, the uncertainty in run-time conditions and the unknown future deployment environments of autonomous systems as well as the complexity of learning-based perception systems make the generalisation of the verification results from design-time to run-time problematic. More attention is starting to shift towards run-time monitoring of performance and reliability of perception systems with several trends emerging in the literature in the face of such a challenge. This paper attempts to identify these trends and summarise the various approaches on the topic.