{"type":"ScholarlyArticle","title":"Using Platform Models for a Guided Explanatory Diagnosis Generation for Mobile Robots","authors":[{"name":"Daniel Habering","slug":"daniel-habering","given":"Daniel","family":"Habering","affiliation":""},{"name":"Till Hofmann","slug":"till-hofmann","given":"Till","family":"Hofmann","affiliation":""},{"name":"Gerhard Lakemeyer","slug":"gerhard-lakemeyer","given":"Gerhard","family":"Lakemeyer","affiliation":""}],"abstract":"Plan execution on a mobile robot is inherently error-prone, as the robot\r\nneeds to act in a physical world which can never be completely\r\ncontrolled by the robot. If an error occurs during execution, the true\r\nworld state is unknown, as a failure may have unobservable consequences.\r\nOne approach to deal with such failures is diagnosis, where the true\r\nworld state is determined by identifying a set of faults based on sensed\r\nobservations. In this paper, we present a novel approach to explanatory\r\ndiagnosis, based on the assumption that most failures occur due to some\r\nrobot hardware failure. We model the robot platform components with\r\nstate machines and formulate action variants for the robots' actions,\r\nmodelling different fault modes. We apply diagnosis as\r\nplanning with a top-k planning approach to determine possible diagnosis\r\ncandidates and then use active diagnosis to find out which of those\r\ncandidates is the true diagnosis.  Finally, based on the platform model,\r\nwe recover from the occurred failure such that the robot can continue to\r\noperate. We evaluate our approach in a logistics robots scenario by\r\ncomparing it to having no diagnosis and diagnosis without platform\r\nmodels, showing a significant improvement to both alternatives.","doi":"10.24963/ijcai.2021/263","url":"https://ijcai.org/proceedings/2021/263","pdf":"https://ijcai.org/proceedings/2021/0263.pdf","markdown":"https://ijcai.org/proceedings/2021/263.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/263","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":263,"pages":{"first":1908,"last":1914},"keywords":["Robotics: Cognitive Robotics","Robotics: Dependable Robots","Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}