Handling temporality in human activity reasoning

Human-aware Artificial Intelligent systems are goal directed autonomous that capable of interacting, collaborating, and teaming with humans. Activity reasoning is a formal approach aims to provide common sense capabilities these interactive intelligent systems. This can be done by considering evidences –which may conflicting–related activities human performs. In this context, it important consider the temporality such evidence in order distinguish analyse relations between activities. Our based on argumentation reasoning, specifically, Timed Argumentation Frameworks (TAF), which an appropriate technique for dealing inconsistencies knowledge bases. involves two steps: local selection global selection. selection, model world human’s mind constructed form hypothetical fragments (pieces evidences) set observations. These have kinds relations: conflict relation temporal relation. Based relations, attack notion defined. We define forms attacks namely strong weak attack. The former has same characteristics TAF whereas latter extended. For determining consistent sets fragments, part activity or non-conflicting activities, extension-based semantics applied. degrees fulfillment determined. study some properties our apply scenario where performs different relations.