Behavior Retrieval for Robot Control in a Unified CBR Hybrid Planner

Susan Eileen Fox

Mathematics/Computer Science Department
Macalester College
1600 Grand Avenue
Saint Paul, MN 55105 USA
fox@macalester.edu
Phone: (651) 696-6553
FAX: (651) 696-6518

Abstract

This research examines a hybrid planner for a real-world mobile robot delivering messages in an office environment. The overall project, RUPART, uses "unified CBR" to combine behavior-based control with high-level case-based planning, using a single similarity metric to retrieve both behavior cases and plan cases. This paper focuses on case-based reasoning for behavior cases. Each behavior case describes a set of behaviors targeted for a particular environment. We explore features used to index behavior cases, as well as adaptation and learning methods. We describe initial results for behavior case retrieval, and its place in the overall project.

Keywords: case-based reasoning, unified CBR, hybrid planning, learning, behavior-based, robot control, route planning, goal management, introspective reasoning