Intelligent Environments are able to support ever-changing environmental needs by automatically and dynamically adjusting their key parameters without explicit human intervention. However, the current development of Intelligent Environments primarily focuses on the technical aspects of the physical components, and does not give sufficient consideration to the dynamic interrelationship between people and the built environment. As a result, environmental conflicts among users, activities, and physical settings are not properly resolved. To overcome this limitation, this article proposes a model for multi-agent based Intelligent Environments and a conflict resolution mechanism by applying the concept of collaborative design. To demonstrate the types of conflicts and their resolution method, a set of hypothetical cases is developed and tested. The result of the case study shows that the proposed model can enable the environment, as an organization of multiple agents, to intelligently perceive the user activity and efficiently handle setting conflicts, thus minimizing the burden to the users of controlling the setting, while maximizing their environmental satisfaction.
Buildings and other inhabited environments are designed to support diverse human activities, yet they often fail to satisfy this primary role due to their static and rigid nature. That is, they have mobility and dynamics that are too limited to cope with the changing needs of their users, activities, and contexts. Unlike such conventionally built environments, Intelligent Environments are able to support ever-changing environmental needs by automatically and dynamically adjusting their key parameters (temperature, light, sound, etc.) without explicit human intervention.
Since Negroponte's introduction of the concept of Intelligent Environments [1], attempts to make buildings ‘intelligent’ have been actively conducted in various domains, thanks in part to the advent of affordable computer technologies. These attempts can be categorized into two approaches: (i) the development of individual devices or agents that react to simple environmental changes, independently from other devices or agents [2], [3] and [4]; and (ii) the development of multiple devices or agents that control various building components, responding to more complex environmental changes in collaboration with other devices or agents [4], [5], [6], [7], [8], [9], [10] and [11]. An example of the first approach is the i-Land project [12], which comprises a set of room-ware components, such as an interactive table and wall for office workers. As an example of the second approach, a multi-agent system developed by Xerox PARC [13], utilizes multiple temperature controllers to improve the energy management of an office building.
However, most of the attempts to make buildings ‘intelligent’ have dealt primarily with the technical aspects of building components, largely ignoring the dynamic interrelationship between people and the built environment. Consequently, various environmental conflicts among users, their activities, and physical settings are not completely resolved, which may lead to user dissatisfaction [14]. Specifically, in multi-agent based Intelligent Environments, in which multiple intelligent agents modify environmental settings by negotiating with other agents [15], [16] and [17], these environmental conflicts should be properly and promptly resolved to ensure the consistency of environment-wide setting modification [18].
To overcome the drawbacks of the current approach, this article proposes a model of multi-agent based Intelligent Environments that is rooted in the concept of collaborative design. The proposed model comprises a hierarchical organization to facilitate the collaborative (design) decision making of agents for the efficient resolution of the environmental conflicts that arise among objects, users, and (users') activities. To validate the proposed model and demonstrate its conflict resolution mechanism, a set of hypothetical test cases is used.
The resolution of environmental conflicts is a complex process, and is a critical one in multi-agent based Intelligent Environments. Furthermore, there is no single method that is applicable to the resolution of all of the different types of conflicts [33] and [49]. Just as human designers solve a design problem by communicating with each other and resolving conflicts amongst themselves, in the proposed model the object agents modify the setting of the environment through communication and collaboration with other agents, as well as with their higher-level agents. The set of test cases demonstrates that user identification, activity sensing, and communication of agents are essential for building Intelligent Environments. Moreover, the proposed model can enable the environment, as an organization of multiple agents, to perceive the user activity intelligently, modify the settings, and handle setting conflict efficiently, to minimize the user burden of controlling the environmental setting. This, in turn, can overcome the drawbacks of conventional approaches to the development of Intelligent Environments, and broaden its application to various building types to improve the quality of the built environment.
