CABINS: Case-Based Interactive Scheduler

Kazuo Miyashita and Katia Sycara

In this paper we discuss the need for interactive factoR' schedule repair and improvement, and identify case-based reasoning (CBR) as an appropriate methodology. Case based reasoning is the problem solving paradigm that relies on a memory for past problem solving experiences (cases) to guide current problem solving. Cases similar to the current case are retrieved from the case memory, and similarities and differences of the current case with past cases are identified. Then a best case is selected and its repair plan is adapted to fit the current problem description. If a repair solution fails, an explanation for the failure is stored along with the-ease in memory, so that the user can avoid repeating similar failures in the future.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.