Towards anticipatory service composition in Ambient Intelligence

Abstract

Anticipatory cognitive mechanisms have been investigated so far in gaze control or in simple robot navigation. This is in order to build cognitive systems endowed with the ability to predict the outcome of their actions. However, research on the actual benefit of anticipatory behavior in Ambient Intelligence (AmI) for user assistance is still in its infancy. This paper proposes some use cases to illustrate the benefits of anticipatory service composition in AmI, highlights issues resulting from the incorporation of anticipation into ubiquitous environments, comes up with guideline principles and existing approaches that have shown promising results to address the identified challenges, and emphasizes the questions and issues that still need a suitable research program before they can be addressed.