Abstract
This article details flight results from the Principal Investigator (PI)-in-a-Box project. The project is an attempt to understand the issues involved in building automated real-time advisory systems to improve the conduct of science in remote laboratory settings. This is an important problem, as examples of these situations can be found throughout aerospace. A knowledge-based approach is used to facilitate real-time reactions to experiment data as they are collected by a competent, hut not expert, operator. The system was flown on the Space Shuttle in October 1993. The PI-in-a-Box system was able to outperform humans in a variety of science-related tasks, including data integrity assurance, data analysis, and scientific model validation.
Notes
The authors would like to thank other members of the PI-in-a-Box team, past and present, for their efforts, especially Mike Compton, Irv Statler, Peter Szolovits, Larry Young, Jeff Shapiro, Guido Haymann-Haber, and Chih Chao Lam. Thanks as well to our reviewers for their helpful comments. Many thanks to the five SLS-2 PI-in-a-Box operators for their patience and skill: Marty Fettman, Shannon Lucid, Bill McArthur, Rhea Seddon, and Dave Wolf. Last but not least, thanks to NASA and especially Peter Friedland for management support. This work was funded by the NASA Office of Advanced Concepts and Technology AI program, to whom we are very grateful.