AAAI Publications, Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence

Font Size: 
A Taxonomic Framework for Task Modeling and Knowledge Transfer in Manufacturing Robotics
Jacob O'Donnal Huckaby, Henrik I. Christensen

Last modified: 2012-07-15

Abstract


Robust methods for representing, generalizing, and sharing knowledge across various robotics systems and configurations are important in many domains of robotics research and application. In this paper we present a method for modeling tasks and robot skills to simplify the programming and reuse of knowledge between robots in manufacturing environments. Specifically, we propose an assembly taxonomy designed to represent the decomposition of high-level, complex assembly tasks into simple skills and skill primitives that the robot must use in a specified sequence. By using programming by demonstration to populate the taxonomy, we propose a method to easily interact with and reuse knowledge in various manufacturing robotics systems, making it possible to reduce programming time and overhead. We present both a detailed discussion of this taxonomy, as well as an example of how the taxonomy can be applied to an assembly task.

Full Text: PDF