Learning Situation-Dependent Rules:
Improving Task Planning for an Incompletely Modelled Domain

Karen Zita Haigh
Honeywell Technology Center
3660 Technology Drive
Minneapolis, MN 55418
Manuela M. Veloso
School of Computer Science
Carnegie Mellon University
5000 Forbes Ave
Pittsburgh, PA 15213
To appear in the 1999 AAAI Spring Symposium on Search Techniques for Problem Solving under Uncertainty and Incomplete Information

Most real world environments are hard to model completely and correctly, especially to model the dynamics of the environment. In this paper we present our work to improve a domain model through learning from execution, thereby improving a task planner's performance. Our system collects execution traces from the robot, and automatically extracts relevant information to improve the domain model. We introduce the concept of {\em situation-dependent rules}, where situational features are used to identify the conditions that affect action achievability. The system then converts this execution knowledge into a symbolic representation that the planner can use to generate plans appropriate for given situations.

  • Compressed Postscript (6 pages, 53K)