Explanation for Human-on-the-loop: a probabilistic model checking approachNIER
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.
Tue 30 Jun Times are displayed in time zone: (UTC) Coordinated Universal Time change
06:00 - 07:30 | Session 2: Testing, Analysis, Reasoning, and MonitoringSEAMS 2020 at SEAMS Chair(s): Sona GhahremaniHasso Plattner Institute, University of Potsdam | ||
06:00 5mTalk | Leveraging Test Logs for Building a Self-Adaptive Path PlannerNIER SEAMS 2020 Kun LiuPeking University, China, Xiaoyi ZhangNational Institute of Informatics, Japan, Paolo ArcainiNational Institute of Informatics
, Fuyuki IshikawaNational Institute of Informatics, Wenpin JiaoPeking University, China Pre-print Media Attached | ||
06:05 5mTalk | Supporting Viewpoints to Review the Lack of Requirements in Space Systems with Machine LearningExperience SEAMS 2020 Kenji MoriJapan Aerospace Exploration Agency, Japan, Naoko OkuboJapan Aerospace Exploration Agency, Japan, Yasushi UedaJapan Aerospace Exploration Agency, Japan, Masafumi KatahiraJapan Aerospace Exploration Agency, Toshiyuki AmagasaUniversity of Tsukuba, Japan Media Attached | ||
06:10 5mTalk | DATESSO: Self-Adapting Service Composition with Debt-Aware Two Levels Constraint ReasoningTechnicalBest Student Paper SEAMS 2020 Satish KumarUniversity of Birmingham, United Kingdom, Tao ChenLoughborough University, Rami BahsoonUniversity of Birmingham, Rajkumar BuyyaUniversity of Melbourne, Australia DOI Pre-print Media Attached | ||
06:15 5mTalk | Towards Bridging the Gap between Control and Self-Adaptive System PropertiesNIER SEAMS 2020 Javier CamaraUniversity of York, Alessandro Vittorio PapadopoulosMälardalen University, Thomas VogelHumboldt-Universität zu Berlin, Danny WeynsKU Leuven, David GarlanCarnegie Mellon University, Shihong HuangFlorida Atlantic University, Kenji TeiWaseda University / National Institute of Informatics, Japan DOI Pre-print Media Attached | ||
06:20 5mTalk | Explanation for Human-on-the-loop: a probabilistic model checking approachNIER SEAMS 2020 NIANYU LIPeking University, China, Sridhar AdepuSingapore University of Technology and Design, Singapore, Eunsuk KangCarnegie Mellon University, David GarlanCarnegie Mellon University Pre-print Media Attached | ||
06:25 65mOther | Q&A and Discussion (Session 2) SEAMS 2020 |