This thesis investigates an intelligent system that can in real time infer the course of action of a human opponent in a competitive environment. Such an achievement would indicate the possibility that machines can not only interpret human behavior as it happens, but also predict the future course of action that a human might take. This thesis first examines several different application of intention recognition, describes the approach of Template Based Interpretation (TBI), and details the process of creating an efficient and accurate intention recognition system. The domain chosen is chess. The system's objective was to discern the opponent's strategy. It is able to use the board positions and other relevant data of the current state to gain an understanding of the movement patterns of the opposition.
| Identifer | oai:union.ndltd.org:ucf.edu/oai:stars.library.ucf.edu:honorstheses1990-2015-1440 |
| Date | 01 January 2005 |
| Creators | Akridge, Cameron |
| Publisher | STARS |
| Source Sets | University of Central Florida |
| Language | English |
| Detected Language | English |
| Type | text |
| Source | HIM 1990-2015 |
Page generated in 0.0055 seconds