Brain-Like Artificial Intelligence for Automation — Foundations, Concepts and Implementation Examples

Abstract

Over the last decades, automation technology has made serious progress and can today automate a wide range of tasks having before needed human physical and mental abilities. Nevertheless, a number of important problem domains remain that cannot yet be handled by our current machines and computers. A few prominent examples are applications involving “realworld” perception, situation assessment, and decision-making tasks. Recently, researchers have suggested to use concepts of “Brain-Like Artificial Intelligence”, i.e. concepts inspired by the functioning principles of the human or animal brain, to further advance in these problem domains. This article discusses the potential of Brain-Like Artificial Intelligence for innovative automation solutions and reviews a number of approaches developed together with the ICT cognitive automation group of the Vienna University of Technology targeting the topics “real-world” perception, situation assessment, and decision-making for applications in building automation environments and autonomous agents. Additionally, it is demonstrated by a concrete example how
such developments can also contribute to an advancement of the state of the art in the field of brain sciences.