Controlling a humanoid robot in home environment with a cognitive architecture

Abstract

Latest humanoid robots mimic the human body in realistic ways, but their control mechanisms fall short of the human mind. More often than not, the robots simply have a fixed set of routine codes that govern their behavior, and even the ones with some learning capabilities are not human-like. Since cognitive architectures aim for general intelligence and provide infrastructure for modeling human cognition, we can benefit from this line of research by adapting such architectures as control mechanisms in our robots. Recent studies revealed that this strategy is, in fact, very useful. Previously, we used one such architecture, ICARUS, to control a humanoid robot for Blocks World tasks. In this paper, we extend the system to perform more complex tasks autonomously on a similar platform. Despite the challenges we encountered in system integration, sensory updates, and navigation, the overall success of this application indicates that the system is capable of more complex tasks to provide services in home environments.