Visible to the public Explanations for Human-on-the-loop: A Probabilistic Model Checking ApproachConflict Detection Enabled

TitleExplanations for Human-on-the-loop: A Probabilistic Model Checking Approach
Publication TypeConference Paper
Year of Publication2020
AuthorsLi, Nianyu, Adepu, Sridhar, Kang, Eunsuk, Garlan, David
Conference NameIn Proceedings of the 15th International Symposium on Software Engineering for Adaptive and Self-managing Systems (SEAMS) - Virtual
Date Published06/2020
Conference LocationSeoul, South Korea
Keywords2020: July, CMU, explainable software, model checking, Self-adaptation.
Abstract

Many self-adaptive systems benefit from human involvement and oversight, where a human operator can provide expertise not available to the system and can detect problems that the system is unaware of. One way of achieving this is by placing the human operator on the loop - i.e., providing supervisory oversight and intervening in the case of questionable adaptation decisions. To make such interaction effective, explanation is sometimes helpful to allow the human to understand why the system is making certain decisions and calibrate confidence from the human perspective. However, explanations come with costs in terms of delayed actions and the possibility that a human may make a bad judgement. Hence, it is not always obvious whether explanations will improve overall utility and, if so, what kinds of explanation to provide to the operator. In this work, we define a formal framework for reasoning about explanations of adaptive system behaviors and the conditions under which they are warranted. Specifically, we characterize explanations in terms of explanation content, effect, and cost. We then present a dynamic adaptation approach that leverages a probabilistic reasoning technique to determine when the explanation should be used in order to improve overall system utility.

Citation Keynode-68823

Other available formats:

Li_Explanations_for_Human_Loop_Garlan.pdf
AttachmentTaxonomyKindSize
Li_Explanations_for_Human_Loop_Garlan.pdfPDF document1.03 MBDownloadPreview
AttachmentSize
bytes