This paper analyses the requirements of automation and adaptation in the so called perceptive environments. These environments are places with the ability of perceiving the context through sensors and other mechanisms. Focusing on personal/home environments, we present a first approach and prototype to semi-automatic adaptation of Perceptive Environments through a system of rule-based, configurable and modular agents, which are able to explain their behaviors and to adapt to the changing habits of the users. This prototype has been implemented over a real environment: a living room equipped with ambient intelligence capabilities. The core of the system relies on a set of modular agents equipped with rules. Those rules are composed of triggers, conditions and actions that enable them to express desired behaviors of the environment as well as to infer high-level context from low level context. One of the main objectives of the system is to leverage the control of the user over his/her own environment, making it easy to create powerful and personal behaviors without expert assistance. In this sense this work follows Greenberg’s thought of making "simple ideas simple to be done" [Greenberg 07].

ubiquitous computing, ambient intelligence, smart home, automatic adaptation, natural programming