Design of a smart support system architecture focusing on the user activity

Abstract

This work presents a system able to support the user on their daily livings using an activity and intention recognition method. The system is designed to be focused on the applicability, working in real time. The recognition method uses the concept of activity frame, which is defined as a set of sequenced environmental observations containing meaningful information (such as objects' locations, sensors' activation, etc) related to the recognition of activities and tasks accomplished in one location. Analysing the specific frame, it is possible to relate, trough a set of conditions, the observed states to a specific activity or intention. By analysing the frequency of those activities and intentions occurrences, it is possible to identify unusual behaviour and guide an smart interactive device, such as robot, to support the user. Those two elements can be used not only to provide a better understanding of the activity in the range of the temporal constrains, but also to deliver more support options and references to the robotic element.