Toward A Knowledge Transfer Framework for Process Abstraction in Manufacturing Robotics

Abstract

Robust methods for representing, generalizing, and sharing knowledge across dierent robotic systems and congurations are important in many domains of robotics research and application. In this paper we present a framework for capturing robot capability and process specication to simplify the sharing and reuse of knowledge between robots in manufacturing environments. A SysML model is developed that represents knowledge about system capabilities in the form of simple skills and skill primitives that can be used in dierent situations or contexts. We present a discussion of the form this model takes and advantages of this type of representation, as well as a demonstration of how the model can be applied to dierent assembly tasks.