Time geography inverted: recognizing intentions in space and time

Mobile intention recognition is the problem of inferring a mobile user's intentions from her behavior in geographic space. Such behavior is constrained in space and time. Current approaches, however, have difficulties to handle temporal constraints. We therefore propose using the framework of time geography to formalize and visualize both spatial and temporal constraints for the mobile intention recognition problem. A new rule language is introduced which allows for modeling intentions with spatial and temporal constraints. A location-based game application demonstrates that interpreting a user's spatio-temporal behavior sequence in terms of intentions reduces ambiguity compared to mobile intention recognition without temporal constraints. Categories and Subject Descriptors H.2.8 [Database Applications]: Spatial databases and GIS; I.2.4 [Artificial Intelligence]: Knowledge Representation Formalisms and Methods Keywords Spatio-temporal Behavior, Intention Recognition, Time Ge...

• Type: Journal
• Year: 2010
• Where: GIS
• Authors: Peter Kiefer, Martin Raubal, Christoph Schlieder
• Keywords: Automated Reasoning, GIS 2010, Intention Recognition, Mobile Intention Recognition, Temporal Constraints