A System-Level View on Out-of-Distribution Data in Robotics
It addresses reliability issues for learning-enabled robotics in open-world autonomy, but is incremental as it builds on existing ML paradigms.
The paper tackles the problem of out-of-distribution (OOD) data compromising learned components in robotic systems, arguing for a system-level approach to assess robot competence in OOD conditions to guide future research.
When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important challenge on the path towards trustworthy learning-enabled open-world autonomy. In this paper, we aim to demystify the topic of OOD data and its associated challenges in the context of data-driven robotic systems, drawing connections to emerging paradigms in the ML community that study the effect of OOD data on learned models in isolation. We argue that as roboticists, we should reason about the overall \textit{system-level} competence of a robot as it operates in OOD conditions. We highlight key research questions around this system-level view of OOD problems to guide future research toward safe and reliable learning-enabled autonomy.