Automated Instructor Assistant for Ship Damage Control

The decision making task of ship damage control includes addressing problems such as fire spread, flooding, smoke, equipment failures, and personnel casualties. It is a challenging and highly stressful domain with a limited provision for real-life training. In response to this need, a multimedia interactive damage control simulator system, called DC-Train 2.0 was recently deployed at a Navy officer training school; it provides officers with an immersive environment for damage control training. This paper describes a component of the DC-Train 2.0 system that provides feedback to the user, called the automated instructor assistant. This assistant is based on a blackboard-based expert system called Minerva-DCA, which is capable of solving damage control scenarios at the "expert" level. Its innovative blackboard architecture facilitates various forms of user assistance, including interactive explanation, advising, and critiquing. In a large exercise involving approximately 500 ship crises scenarios, Minerva-DCA showed a 76% improvement over Navy officers by saving 89 more ships.

[1]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[2]  Robert J. Crutcher,et al.  The role of deliberate practice in the acquisition of expert performance. , 1993 .

[3]  B. Chandrasekaran.  Generic TasksinKnowledge- BasedReasoning: High-Level Building Blocks forExpert SystemDesign , 1986 .

[4]  Avron Barr,et al.  The Handbook of Artificial Intelligence , 1982 .

[5]  William J. Clancey,et al.  Heuristic Classification , 1986, Artif. Intell..

[6]  David C. Wilkins,et al.  Bayesian Network Models for Generation of Crisis Management Training Scenarios , 1998, AAAI/IAAI.

[7]  David C. Wilkins,et al.  Recursive heuristic classification , 1994 .

[8]  William J. Clancey,et al.  Acquiring, representing, and evaluating a competence model of diagnostic strategy , 1993 .

[9]  H. Nii.  Blackboard Systems , 1998 .

[10]  Barbara Hayes-Roth,et al.  A Blackboard Architecture for Control , 1985, Artif. Intell..

[11]  D. C. Wilkins.  Knowledge base refinement as improving an incorrect and incomplete domain theory , 1993 .

[12]  John V. Fuller.  Measuring Damage Control Assistant's (DCA) Decision-Making Proficiency in Integrated Damage Control Training Technology (IDCTT) Training Scenarios , 1993 .

[13]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[14]  Victor Lesser,et al.  The Evolution of Blackboard Control Architectures , 1992 .

[15]  Edward A. Felgenbaum.  The art of artificial intelligence: themes and case studies of knowledge engineering , 1977, IJCAI 1977.

[16]  Mark S. Johnson.  Validation of an active multimedia courseware package for the Integrated Damage Control Training Technology (IDCTT) trainer , 1994 .

[17]  Glenis Moore,et al.  The art of artificial intelligence , 1987 .

[18]  Randolph M. Jones,et al.  Automated Intelligent Pilots for Combat Flight Simulation , 1998, AI Mag..

[19]  Matthew M. Huntbach,et al.  The Art in Artificial Intelligence , 1999 .

[20]  Jan Eric Larsson,et al.  Knowledge Systems Laboratory August 1996 Report No . KSL – 96 – 25 Guardian : Final Evaluation , 1996 .

[21]  Edward A. Feigenbaum,et al.  The Art of Artificial Intelligence: Themes and Case Studies of Knowledge Engineering , 1977, IJCAI.

[22]  Ziad H. Najem.  A hierarchical representation of control knowledge for a heuristic classification shell , 1993 .