Design considerations for COSA2

In this article, we present the architectural and algorithmic details for a COgnitive System Architecture that uses a Centralized Ontology with Specific Algorithms (COSA2). COSA2 is a layered intelligent agent framework on the basis of the modified Rasmussen model of human performance. It encompasses integrated algorithmic support for goal-driven situation interpretation, dynamic planning and plan execution, as well as provisions for reactive behavior. A unique feature is the claim for an expressive, centralized ontology representation, used by all functions to ensure consistency. The framework is being applied to different problems in the domain of uninhabited aerial vehicles. The modeling and processing details described in this article are illustrated by a simplified example from the intelligent onboard systems management domain.

[1]  Jens Rasmussen,et al.  Skills, rules, and knowledge; signals, signs, and symbols, and other distinctions in human performance models , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  Tom Bylander,et al.  The Computational Complexity of Propositional STRIPS Planning , 1994, Artif. Intell..

[3]  Avrim Blum,et al.  Fast Planning Through Planning Graph Analysis , 1995, IJCAI.

[4]  Axel Schulte,et al.  A Generic Cognitive System Architecture Applied to the UAV Flight Guidance Domain , 2010, ICAART.

[5]  Axel Schulte,et al.  System-Ergonomic Design of Cognitive Automation: Dual-Mode Cognitive Design of Vehicle Guidance and Control Work Systems , 2010, Studies in Computational Intelligence.

[6]  Axel Schulte,et al.  Human factors in the guidance of uninhabited vehicles: oxymoron or tautology? , 2009, Cognition, Technology & Work.

[7]  Reiner Onken,et al.  COSA – A generic cognitive system architecture based on a cognitive model of human behavior , 2003, Cognition, Technology & Work.

[8]  E. Gat.  On Three-Layer Architectures , 1997 .

[9]  Tara Estlin,et al.  Plan Execution Interchange Language (PLEXIL) , 2006 .

[10]  Barbara Messing,et al.  An Introduction to MultiAgent Systems , 2002, Künstliche Intell..

[11]  Winfried Lamersdorf,et al.  Augmenting BDI Agents with Deliberative Planning Techniques , 2006, PROMAS.

[12]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[13]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[14]  Maria Fox,et al.  PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains , 2003, J. Artif. Intell. Res..

[15]  Todd R. Johnson.  Control in Act-R and Soar , 1997 .

[16]  Avelino Francisco Zorzo,et al.  Propositional planning in BDI agents , 2004, SAC '04.

[17]  Axel Schulte,et al.  Using cognitive automation for aircraft general systems management , 2010, 2010 5th International Conference on System of Systems Engineering.

[18]  Michael E. Bratman,et al.  Intention, Plans, and Practical Reason , 1991 .

[19]  J. Finger,et al.  Exploiting constraints in design synthesis , 1987 .

[20]  Innes A. Ferguson.  TouringMachines: an architecture for dynamic, rational, mobile agents , 1992 .

[21]  David E. Smith,et al.  Reasoning About Action I: A Possible Worlds Approach , 1987, Artif. Intell..

[22]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[23]  Félix Ingrand,et al.  Propice-Plan: Toward a Unified Framework for Planning and Execution , 1999, ECP.

[24]  Daniel J. Garland,et al.  Situation Awareness Analysis and Measurement , 2009 .

[25]  Axel Schulte,et al.  Efficient Graph Matching with Application to Cognitive Automation , 2008, AGTIVE.

[26]  P. Pandurang Nayak,et al.  A Reactive Planner for a Model-based Executive , 1997, IJCAI.