Combining Experience with Quantitive Models

John J. Grefenstette and Connie Loggia Ramsey

This is a progress report on our efforts to design intelligent robots for complex environments. The sort of applications we have in mind include senlry robots, autonomous delivery vehicles, undersea surveillance vehicles, and automated warehouse robots. We are investigating the issues relating to machine learning, using multiple mobile robots to perform tasks such as playing hide-and-seek, tag, or competing to find hidden objects. We propose that the knowledge acquisition task for autonomous robots be viewed as a cooperative effort between the robot designers and the robot itself. The robot should have access to the best model of its world that the designer can reasonably provide. On the other hand, some aspects of the environmcnt will be unknown in advance. For such aspects, the robot itself is in the best position to acquire the knowledge of what to expect in its world. We have implemented these ideas in an arrangement we call case-based anytime learning. This system starts with a parameterized model of its world and then learns a set of specific models that correspond to the environmental cases it actually encounters. The system uses genetic algorithms to learn high-performance reactive strategies for each environmental model.


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.