A task domain for combining and evaluating robotics and cognitive modeling techniques
Nicholas Cassimatis, J. Gregory Trafton, Alan Schultz, William Adams
- Year
- 2002
- Citations
- 2
Abstract
Building systems that integrate different artificial intelligence techniques to achieve a higher level of total intelligence is very difficult. In order to build integrated systems, simplifying assumptions or abstractions are usually made when working in a specific domain. As a result of these assumptions and abstractions, the proper evaluation of integrated artificial intelligence techniques can be quite challenging. We suggest that the domain of hide and seek is a particularly well-suited task for integrating robotics and higher-level reasoning mechanisms such as computational cognitive modeling. Three different instantiations of integrated systems in the “hide and seek ” domain, which combine cognitive-level algorithms with lower level algorithms for perception and navigation are discussed.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002