Commonsense Situational Awareness, and Activity Interpretation

Situation awareness (SA) has been a subject of long-time investigation from human cognition, complex systems, human factors and computer-human interaction viewpoints. Given the background of these research areas, commonsense situational awareness in the context of space, actions, and change for the domain of Assistive Technologies and Systems concerned with models of Spatio-Temporal, Contextual, and Behavioural intelligence within Ambient Intelligence and Smart Environments may be abstractly defined as:

"the perception of elements within the volume of time and space, the comprehension of their meaning, the explanation of their present (observed) status and the ability to project the same in the near future."

The emerging fields of ambient intelligence and smart environments, and pervasive and ubiquitous computing will benefit immensely from the vast body of representation and reasoning methods and tools that have been developed in artificial intelligence in general, and commonsense reasoning, qualitative reasoning, spatial representation and reasoning, and spatial cognition and computation in particular.

Space, Action and Change

A wide-range of application domains within the fields of ambient intelligence, smart environments, and pervasive and ubiquitous computing environments require the ability to represent and reason about dynamic spatial phenomena. Real world ambient intelligence systems that monitor and interact with an environment populated by humans and other artefacts require a formal means for representing and reasoning with spatio-temporal, event and action based phenomena that are grounded to real aspects of the environment being modelled. A fundamental requirement within such application domains is the representation of dynamic knowledge pertaining to the spatial aspects of the environment within which an agent, system or robot is functional. At a very basic level, this translates to the need to explicitly represent and reason about dynamic spatial configurations or scenes and desirably, integrated reasoning about space, actions and change. With these modelling primitives, primarily the ability to perform predictive and explanatory analyzes on the basis of available sensory data is crucial toward serving a useful intelligent function within such environments.

Ambient Intelligence

The emerging fields of ambient intelligence, and pervasive and ubiquitous computing will benefit immensely from the vast body of representation and reasoning tools that have been developed in Artificial Intelligence in general, and Qualitative Reasoning, Spatial and Temporal Reasoning, Spatial Cognition in specific. There have already been proposals to explicitly utilise qualitative spatial calculi pertaining to different spatial domains for modelling the spatial aspect of an ambient environment (e.g., smart homes and offices) and also to utilize a formal basis for representing and reasoning about space, change and occurrences within such environments. High-level reasoning patterns involving projection, explanation may assume a more applied character for applications in behaviour monitoring and interpretation, activity analysis, and so forth.

Spatial and Temporal Reasoning

The field of qualitative spatial representation and reasoning has evolved as a sub-division in its own right within the broader field of Artificial Intelligence -- recent years have witnessed remarkable advances in some of the long-standing problems of the field. For instance, new results about tractability for spatial calculi, explicit construction of models, characterisation of important subclasses of relations, as well as in the development of new areas such as the emergence of integrated spatio-temporal calculi and the importing of non-monotonic techniques for dealing with various aspects intrinsic to dynamic spatial systems. Inextricably linked to space is time, i.e., spatial configurations change over time. Spatial change may also be perceived as being spatio-temporal and recent work has been devoted to providing useful and well-grounded models to be used as high level qualitative description of spatio-temporal change. Reasoning about space and spatial dynamics also involves reasoning about changing spatial configurations, and in more realistic scenarios, integrated reasoning about space, actions and change. Recent work supporting this paradigm has also explicitly addressed the formal modelling of dynamic spatial systems and ensuing interactions between the spatial reasoning domain and the field of reasoning about actions and change, and commonsense reasoning.

Driven by cognitive approaches that characterise the processing of spatial information within qualitative spatial reasoning, there has been considerable influx of people from other areas within AI such as computer vision, robotics etc, working on qualitative representation and reasoning about spatial change, spatio-temporal interactions, and the formal modelling of dynamic spatial systems in general. Qualitative conceptualisations of space and tools/techniques for efficiently reasoning with them being well-established, there is now a clear felt need within the community to utilise the tools and formalisms that have been constructed in the recent years in novel application scenarios.
Mehul Bhatt, Hans Guesgen. 2012. Commonsense Situational Awareness for Assistive Technologies: Agenda of the STAMI Initiative. In: Situational Awareness for Assistive Technologies. . Ambient Intelligence and Smart Environments. Vol 14. Pages 1-8, ISBN 978-1-61499-122-9 (print), ISBN 978-1-61499-123-6 (online) IOS Press. Amsterdam. www, pdf