Vision-based behavioural modules for robotic assembly systems

Abstract

This work describes how to program robots to work reliably in the presence of uncertainty. Some architectural principles are proposed which address the problem of decomposing robotic assembly tasks into modular units. These modular units are called behavioural modules. The problem of uncertainty is dealt with by encapsulating sensing and variation-reducing strategies inside these modules. This architecture also provide a framework to integrate sensors into a robotic assembly system. Experiments are performed with a working robotic assembly system using vision-based behavioural modules to demonstrate the validity of this approach.<>