Case-Based Seeding for an Interactive Crisis Response Assistant

Melinda Gervasio - Wayne Iba - Pat Langley
Institute for the Study of Learning and Expertise
2164 Staunton Court, Palo Alto, California 94306
{gervasio, iba, langley}@isle.org
http://www.isle.org

Abstract

In this paper, we present an interactive, case-based approach to crisis response that provides users with the ability to rapidly develop good responses while allowing them to retain ultimate control over the decision-making process. We have implemented this approach in INCA, an INteractive Crisis Assistant for planning and scheduling in crisis domains. INCA relies on case-based methods to seed the response development process with initial candidate solutions drawn from previous cases. The human user then interacts with INCA to adapt these solutions to the current situation. We will discuss this interactive approach to crisis response using an artificial hazardous materials domain, HAZMAT, that we developed for the purpose of evaluating candidate assistant mechanisms for crisis response.