Autonomous task execution of a humanoid robot using a cognitive model

Abstract

Cognitive architectures provide infrastructure for modeling human cognition. Recent studies reveal that these architectures are useful control mechanisms for a variety of robots. Previously, we showed one such architecture, ICARUS, can successfully control a humanoid robot for Blocks World tasks in a simulated environment. In the current work, we extend the application to the real world and use the architecture to perform similar tasks with Mahru-Z platform. As commonly expected, we encountered many challenges in system integration, vision-based information updates, and manipulation tasks. This paper reports the result of our initial work to address some of these issues. The successful completion of a color sorting task indicates the system is capable to adapt to such challenges and we expect similar results in more complicated tasks in this domain.