AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
| Hi-index | 0.00 |
A conceptual framework is a valuable resource for planning by situated agents. In this paper, we discuss the acquisition of such a framework. We take the position that concepts are abstractions of experience that confer a predictive ability for new situations. We also show specific examples which demonstrate the utility of abstract representations of actions, called {\em activity maps}, for reasoning about concepts and their entailments. In fact, we make the case that activity maps are concepts themselves. Where appropriate, we draw analogies with related work in nonlinear dynamics. This research was supported by ARPA/Rome Laboratory under contracts F30602-91-C-0076 and F30602-93-C-0100. In AAAI Workshop on Robots, Softbots, Immobots: Theories of Action, Planning and Control, 1997.