To Know or Not to Know: On the Utility of Models in Mobile Robotics

Sebastian Thrun

Abstract


This article describes JEEVES, one of the winning entries in the 1996 Annual AAAI Mobile Robot Competition and Exhibition, held as part of the Thirteenth National Conference on Artificial Intelligence. JEEVES tied for first place in the finals of the competition after it won both preliminary trials. A key aspect in JEEVES's software design was the ability to acquire a model of the environment. The model, a geometric map constructed from sensory data gathered while the robot performed its task, enabled JEEVES to sweep the arena efficiently. It facilitated the retrieval of balls and their delivery at the gate, and it helped to avoid unintended collisions with obstacles. This article argues that JEEVES's success depended crucially on the existence of the model. It also argues that models are generally useful in mobile robotics -- even in tasks as simple as the one faced in this competition.

Full Text:

PDF


DOI: http://dx.doi.org/10.1609/aimag.v18i1.1273

Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.