Qualitative Spatial Scene Modeling for Ambient Intelligence Environments Frank Dylla and Mehul Bhatt SFB/TR 8 Spatial Cognition, Universit¨at Bremen, Germany {dylla,bhatt}@sfbtr8.uni-bremen.de Abstract. In ambient intelligence systems, it is necessary to represent and reason about dynamic spatial scenes and configurations. Primarily, the ability to perform predictive and explanatory analyses on the basis of available sensory data is crucial toward serving a useful intelligent func- tion within such environments. In this paper, we present a qualitative model for representing the relevant aspects of these environments in an adequate manner. The model is suited for reasoning about spatial config- urations and dynamics in spatial environments. We clarify and elaborate on our ideas with examples grounded in a smart home environment. 1 Introduction A wide-range of application domains in Artificial Intelligence, from cognitive robotics to intelligent systems encompassing diverse paradigms such as ambi- ent intelligence and ubiquitous computing environments, require the ability to represent and reason about spatial scenes or configurations and how they might evolve over time. For instance, real world ambient intelligence systems that mon- itor and interact with an environment populated by humans and other artefacts require a formal means for representing and reasoning with spatio-temporal and event-based phenomena that are grounded in the environment being modeled. Here, the location of a mobile-object, e.g., a person or animal, may require to be projected within the spatial environment at hand, e.g., smart homes, airports, or traffic junctions, for the purpose of dynamic scene analyses and interpretation, event-recognition, alert generation, and so forth. Similarly, the unfolding of se- quences of spatial configurations that correspond to certain activities within the application domain of interest may be required to be modeled too, e.g., in the form of causal explanation of observations on the basis of the actions and events that may have caused the observed state-of-affairs. A fundamental requirement within such application domains is the representation of dynamic knowledge per- taining to the spatial aspects of the environment within which an agent (e.g., a robot) or a system is functional, e.g., a monitoring or alert generation system in a smart-home [1,2]. Furthermore, it is also desired that the perceivable variations in space be explicitly linked with the functional aspects of the environment being modeled and reasoned about – in other words, it is necessary to explicitly take into consideration the fact that perceivable changes in the surrounding space C. Xiong et al. (Eds.): ICIRA 2008, Part I, LNAI 5314, pp. 716–725, 2008. c  Springer-Verlag Berlin Heidelberg 2008