EMPOWER - Empowered Workers Collaborating with Cognified Machines
Sprache der Bezeichnung:
Englisch
Original Kurzfassung:
The speed of the state-of-the-art advance in artificial intelligence (AI) in general, and machine learning (ML) in particular, has taken human-machine collaboration to continually recalibrate our expectations on what machines can do with the help of AI, but at the same time also on what humans can do with physical and mechanical empowerment coming from AI operated machines.
EMPOWER is driven by the rational that human-machine collaboration performance is rooted at the confluence of (i) the core intellectual abilities of humans, and (ii) the mechanical proficiencies of machines. EMPOWER attempts for a performance efficient entanglement of human and machine abilities, by (i) integrating advanced AI technology into industrial machinery (Cognification), while (ii) at the same time amplifying human physical strength by body worn reinforcement systems like exoskeletons (Empowerment).
EMPOWER (i) builds upon a multi-modal, multi-sensor based perception of working situations in human machine collaborations, (ii) attempts to identify current work tasks from manipulative activities and worker skill levels, (iii) quests for comprehension of the workflow to predict upcoming work steps, and (iv) adjusts control settings to meet the mechanical requirements of the upcoming worksteps. The proposed innovation of proactive exoskeletons is a step towards energy efficiency due to low power consumption, integrated task and intention prediction enables energy savings for exoskeletons and collaborative machines through use-dependent activation.