For energy-optimized drive systems

Salzburg University of Applied Sciences and ABB’s Machine Automation Division (B&R) have filed a joint patent application for energy-optimized drive systems. This innovation is a key outcome of their collaboration within the Josef Ressel Center for Intelligent and Secure Industrial Automation (JRZ ISIA); it underscores the effectiveness of industry-oriented applied research and highlights the importance of industry-research partnerships for driving innovation.

The patent application focuses on a novel approach to the energy-optimized motion control of drive systems in industrial automation—such as in robots, machine tools, or automated production lines—where highly dynamic motion sequences (including positioning, acceleration, braking, and cycling) require precise control. While conventional control methods rely on highly accurate mathematical models of the system, this new approach addresses the very area where such models reach their limits: real-world energy losses that are often difficult to capture—measurable, yet not fully modelable or known in minute detail.

By employing artificial intelligence methods—specifically reinforcement learning (RL)—a learning agent is deployed directly on the actual system. It adaptively optimizes motion strategies by independently learning, through interaction, how various motion sequences contribute to energy losses and adjusting its control logic accordingly—all without requiring a complete system model.

A key innovative aspect of the patent lies in the novel mathematical design of the learning strategy: it enables a significant acceleration of RL methods—which have historically been too slow and data-intensive for industrial applications—while simultaneously delivering superior results. This makes practical implementation in cyber-physical systems both economically and technically viable for the first time, with the ultimate goal of making motion sequences significantly more energy-efficient while comprehensively accounting for real-world operating conditions.

AI Research with Industrial Relevance

"This patent application impressively demonstrates how scientific excellence and industrial practice go hand in hand at the Josef Ressel Center. Our goal is not to let research end in the laboratory, but to develop concrete technological innovations for the industry," emphasizes Stefan Huber, Head of Research at Salzburg University of Applied Sciences.

"Especially in the field of artificial intelligence, we need world-class research in Austria and Europe at the technological cutting edge—research that has a direct impact on our industry's business sectors."

ABB’s Machine Automation Division (B&R) also views the collaboration as strategically important: "Close cooperation with Salzburg University of Applied Sciences enables us to rapidly translate innovative research methods into industrial applications. The submitted patent application is a strong signal of the innovative power generated by this partnership," says Martin Haidacher, Innovation Manager at B&R.

Joint research – growing since 2020

The underlying research has a long history of development: initial work dates back to 2020 and was launched as part of the EU Interreg project KI-Net. Since 2022, the topic has been further developed at the Josef Ressel Center—in collaboration with industry partners from the Machine Automation Division (B&R), Copa-Data, and others.

Cooperation as a driver for new solutions

This joint filing underscores the importance of long-term research collaborations between academia and industry—particularly in a technology field that is crucial for energy efficiency, sustainability, and the international competitiveness of Europe as an industrial hub.