Creating discourse plans and the supporting software architecture for tutoring using Freedman's Atlas Planning Environment.

摘要

CIRCSIM-Tutor is an Intelligent Tutoring System that conducts a conversation with a student to help the student learn to solve a class of problems in cardiovascular physiology dealing with the regulation of blood pressure. CIRCSIM-Tutor uses natural language for both input and output, and can handle a variety of syntactic constructions and lexical items, including sentence fragments and misspelled words.; This research focuses on the planning aspects of CIRCSIM-Tutor Version 3 and includes a hierarchical reactive planner, APE---the Atlas Planning Engine. By using this planner, we are well suited to effectively respond to dynamic changes in the environment of tutoring students to solve problems in cardiovascular physiology dealing with the regulation of blood pressure. Use of the hierarchical reactive planner allows us to adapt to student initiatives or unpredictable answers by replacing the planner's reactions with newly computed better reactions and allows us to specify new goals to the ITS and have it alter its reactions so as to achieve new goals. The result is a more cohesive dialog with the student.; This effort required a planning mechanism that can generate mixed-initiative dialogs, handle multiturn discourse plans, and also support curriculum planning and turn planning. With this in mind, I used Freedman's Atlas Planning Environment. I have devised a completely new set of discourse plans, which involves many issues in tutoring and discourse planning. My goal is a system that can carry out tutorial dialogues that seem natural to the student, that can handle hierarchical plans, react to unexpected student responses, and replan as needed. I also have made the system modular so that it can function in other domains in physiology.