POSTMODULAR SYSTEMS: ARCHITECTURAL PRINCIPLES FOR COGNITIVE ROBOTICS
Author:
Lynn Andrea Stein
DOI:
10.1080/019697297126001
Publication Frequency:
8 issues per year
Subjects:
Cybernetics;
Human Computer Intelligence;
Information & Communication Technology (ICT);
Machine Learning - Design;
Robotics;
Formats available:
PDF
(English)
View Article:
View Article (PDF)
Abstract
Modular-functional decomposition is a fundamental tenet of computer science. Cognitive robotics, with strong roots in cognitive science and biology,replaces modular-functional decomposition with a more opportunistic approach. Nonetheless, we can extract heuristics with both analytic and synthetic power: architectural principles for postmodular systems. This paper describes three postmodular principles: imagination, shared grounding, and incremental adaptation. It briefly discusses examples of each drawn from existing systems. The paper concludes with an illustration of these three principles used in concert to build a system that progresses first to hand-eye coordination, then to planned complex reaching, and finally to shared attention.
|

Download Citation
CiteULike
Del.icio.us
BibSonomy
Connotea