Model-based ambient analysis of human task execution

One of the challenges for ambient intelligent agents to support a human in demanding tasks, is to find out and be aware of what the human is exactly doing, and how much progress is made. Of course, in principle it would be possible to interact with the human to discover what this human is doing, but this communication can potentially slow down or even endanger task performance. In this paper an ambient agent model is presented that is able to obtain such an awareness of the human's progress in task execution by performing model-based analysis using available workflow models and available observation information. The design of the model is based on a component-based generic ambient agent model. Simulation experiments for a case study are discussed, and evaluated by automated formal verification.

[1]  Clarence A. Ellis,et al.  Modeling and Enactment of Workflow Systems , 1993, Application and Theory of Petri Nets.

[2]  Amit P. Sheth,et al.  An overview of workflow management: From process modeling to workflow automation infrastructure , 1995, Distributed and Parallel Databases.

[3]  Michel C. A. Klein,et al.  A Component-Based Ambient Agent Model for Assessment of Driving Behaviour , 2008, UIC.

[4]  Wenke Lee,et al.  Attack plan recognition and prediction using causal networks , 2004, 20th Annual Computer Security Applications Conference.

[5]  James M. Rehg,et al.  A Scalable Approach to Activity Recognition based on Object Use , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Wil M. P. van der Aalst,et al.  Workflow Patterns , 2004, Distributed and Parallel Databases.

[7]  Henry A. Kautz,et al.  Location-Based Activity Recognition using Relational Markov Networks , 2005, IJCAI.

[8]  Tibor Bosse,et al.  Specification and Verification of Dynamics in Cognitive Agent Models , 2006, 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology.

[9]  Jan Treur.  On Human Aspects in Ambient Intelligence , 2007, AmI Workshops.

[10]  Daniel Thalmann,et al.  The Role of Virtual Humans in Virtual Environment Technology and Interfaces, In: Frontiers of Human-Centred Computing , 1999 .

[11]  Tibor Bosse,et al.  A Language and Environment for Analysis of Dynamics by Simulation , 2005, Int. J. Artif. Intell. Tools.

[12]  Henry A. Kautz,et al.  Fine-grained activity recognition by aggregating abstract object usage , 2005, Ninth IEEE International Symposium on Wearable Computers (ISWC'05).

[13]  Tibor Bosse,et al.  Model-Based Reasoning Methods within an Ambient Intelligent Agent Model , 2007, AmI Workshops.

[14]  Diane J. Cook,et al.  Proceedings of the Eighth International Workshop on Human Aspects in Ambient Intelligence , 2007 .

[15]  Michel C. A. Klein,et al.  An Agent-Based Generic Model for Human-Like Ambience , 2007, AmI Workshops.