Adaptive Reasoning for Real-World Problems: A Schema-Based Approach

Adaptive Reasoning for Real-World Problems: A Schema-Based Approach

Adaptive Reasoning for Real-World Problems: A Schema-Based Approach

Adaptive Reasoning for Real-World Problems: A Schema-Based Approach


This book describes a method for building real-world problem solving systems such as medical diagnostic procedures and intelligent controllers for autonomous underwater vehicles (AUVs) and other robots. The approach taken is different from other work reported in the artificial intelligence literature in several respects:

• It defines schema-based reasoning, in which schemas -- explicitly declared packets of related knowledge -- are used to control not only the reasoner's planning, but also all other facets of its behavior.

• It is a kind of reactive reasoning that the author calls adaptive problem solving -- the reasoner maintains commitments to future goals but is able to change its focus of attention as the problem-solving situation requires.

• It is a context-sensitive reasoning method. Every decision it makes relies on the use of contextual knowledge to be appropriate for the current problem-solving situation. Furthermore, context is represented explicitly; by always keeping a current representation of the context in mind, the reasoner's behavior is automatically sensitive to the context with very little work needed per decision.

• Schema-based reasoning -- a generalization of case-based reasoning -- extends the usual idea of case-based reasoning to encompass all aspects of the reasoner's behavior, and it extends it to make use of generalized "cases" (i.e., schemas) rather than particular cases, thus saving effort needed to transfer knowledge from an old case to a new situation.

Though the work originated in the domain of medical diagnostic problem solving, treating diagnosis as a planning task, it is even more appropriate for controlling autonomous systems. The author is currently extending the approach by creating a robust controller for long-range autonomous underwater vehicles that will be used to carry out ocean science missions.


This book is an outgrowth of my dissertation work on adaptive problem solving for medical diagnostic reasoning, which was done at the Georgia Institute of Technology. As that work progressed, it became clear that schema- based reasoning is applicable to any problem-solving task in which an agent must cope with incomplete information, uncertainty, and unanticipated events. a particularly fruitful opportunity to expand the work presented itself at the University of New Hampshire, which until recently had one of the premier autonomous underwater vehicle (AUV) laboratories in the world. (The Marine Systems Engineering Laboratory, msel, has since moved to Northeastern University.) It seemed natural to move from the fairly unreactive medical diagnostic domain toward the challenges to be faced in the real-world task of controlling AUVs as they perform useful scientific missions, such as global change monitoring. Based on my experience so far, I believe that schema- based reasoning will prove useful for solving problems in this and most other complex real-world domains.

The book discusses schema-based reasoning and two implementations of it. medic is a medical diagnostic consultant for pulmonology that was developed several years ago. Orca, a robust intelligent controller for ocean science AUVs, is currently being implemented by me and other members of the unh Cooperative Distributed Problem Solving (CDPS) research group. It is hoped that Orca will see application on MSEL's AUVs within two or three years.

I am indebted to colleagues at unh and Northeastern, particularly Elise Turner and the other members of the cdps research group, as well as Dick Blidberg and the staff of msel, for their insights and discussions throughout this work. I am also indebted to colleagues at Georgia Tech, including my advisor, Janet Kolodner, for their helpful discussions during my dissertation work. I would also like to thank my editors at Lawrence Erlbaum Associates, Amy Pierce and Teresa Faella, for their help and patience.

The work reported here was generously funded by several agencies, to whom I am grateful. For funding work on medic, I thank the Army Research Office (contract number DAAG29-83-G-0016), the National Science Foundation (grants IST-831771 and IST-8608362), and the Lockheed ai Center (grant dtd 09-25-87). For funding work on Orca, I thank the National Science Foundation (grant number BCS-9211914).

The writing process would have been painful without excellent software tools such as the Free Software Foundation's gnu Emacs editor, tgif, dvips . . .

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.