Salzburg University of Applied Sciences and ABB’s B&R division develop reinforcement learning techniques to reduce energy losses in robots, machine tools, and production lines, marking a significant step towards greener manufacturing.
Austrian researchers are trying to make industrial motion systems more energy-efficient by teaching software to learn from the behaviour of real machines rather than relying only on mathematical models.
The work brings together Salzburg University of Applied Sciences and ABB’s Machine Automation Division, known as B&R, and has already led to a joint patent application for energy-optimised motion control in industrial drive systems. The intended applications include robots, machine tools and automated production lines, where movements such as positioning, acceleration, deceleration and repeated cycles must be controlled with high precision.
The project is being carried out at the university’s Josef Ressel Centre for Intelligent and Secure Industrial Automation, where the team is tackling a long-standing problem in automation: conventional control methods can be highly accurate on paper, but they do not always capture the energy losses that occur in real-world operation. Those losses can be measured in practice, yet they are often too complex to model fully.
To address that gap, the researchers are using reinforcement learning, a form of artificial intelligence that improves through interaction with a physical system. Rather than depending on a complete model of the machine, a learning agent observes how different motion patterns affect energy consumption and then adjusts the control approach accordingly.
A key feature of the work is a new mathematical formulation designed to speed up learning while reducing the amount of data needed. That matters because reinforcement learning has often been seen as too slow and data-hungry for industrial deployment. By making training more efficient, the researchers aim to bring the technique closer to practical use in cyber-physical systems and improve energy performance without compromising operating conditions.
B&R’s innovation manager Martin Haidacher said the collaboration allows industrial research to be translated into usable applications at an early stage, while Stefan Huber, head of research at Salzburg University of Applied Sciences, said the goal is to ensure that academic work leads to tangible technological innovation for industry.
The effort builds on earlier Austrian and German cooperation in AI for manufacturing, including the KI-Net project launched in 2020. That initiative focused on helping small and medium-sized manufacturers adopt artificial intelligence by linking academic expertise with industrial practice, and produced open-access guides and demonstrator prototypes.
The latest patent work also fits into a wider Austrian push to support industrial digitalisation. AI5Production, one of Austria’s European Digital Innovation Hubs, offers manufacturing companies access to research infrastructure, expertise and training to help them develop and test new digital and production technologies. For energy-intensive industries under pressure to cut emissions and improve efficiency, projects like these show how AI is moving from theory towards operational decarbonisation.
- https://drivesncontrols.com/austrian-project-uses-ai-to-boost-energy-efficiency-in-industrial-drives/?utm_source=rss&utm_medium=rss&utm_campaign=austrian-project-uses-ai-to-boost-energy-efficiency-in-industrial-drives – Please view link – unable to able to access data
- https://roboticsandautomationnews.com/2026/06/03/abb-and-salzburg-researchers-patent-ai-system-to-cut-energy-use-in-industrial-robots/102231/ – Salzburg University of Applied Sciences and ABB’s Machine Automation Division (B&R) have collaborated to develop an AI system aimed at enhancing energy efficiency in industrial robots. This partnership has resulted in a joint patent application for energy-optimised motion control in industrial drive systems, including robots, machine tools, and automated production lines. The focus is on translating advanced research into practical solutions for industrial drive systems, addressing challenges in industrial automation by using AI, particularly reinforcement learning methods, to learn directly from real system behaviours. This approach aims to make motion sequences more energy-efficient while reflecting real operating conditions. ([roboticsandautomationnews.com](https://roboticsandautomationnews.com/2026/06/03/abb-and-salzburg-researchers-patent-ai-system-to-cut-energy-use-in-industrial-robots/102231/?utm_source=openai))
- https://ki-net.eu/projekt/ – The KI-Net project, funded under the Interreg Austria-Bavaria 2014-2020 programme, aims to develop a cross-border competence network investigating fundamental components for AI-based optimisations in industrial manufacturing. The project addresses the challenges faced by small and medium-sized enterprises (SMEs) in adopting AI technologies by providing them with the necessary expertise and resources to implement AI in production and maintenance processes. The initiative focuses on bridging the gap between academic AI theory and real-world industrial practice, producing open-access application guides and demonstrator prototypes for SMEs. ([ki-net.eu](https://ki-net.eu/projekt/?utm_source=openai))
- https://pure.fh-salzburg.ac.at/en/publications/ki-net-ai-based-optimization-inindustrial-manufacturinga-project-/ – The KI-Net project, led by the Software Competence Center Hagenberg (SCCH) with partners from the University of Innsbruck, Rosenheim University of Applied Sciences, Kempten University of Applied Sciences, and Salzburg University of Applied Sciences, focuses on AI-based optimisation in industrial manufacturing. The project aims to develop a cross-border competence network that investigates fundamental components for AI-based optimisations in industrial manufacturing, addressing the challenges SMEs face in adopting AI technologies. The initiative seeks to bridge the gap between academic AI theory and real-world industrial practice, producing open-access application guides and demonstrator prototypes for SMEs. ([pure.fh-salzburg.ac.at](https://pure.fh-salzburg.ac.at/en/publications/ki-net-ai-based-optimization-inindustrial-manufacturinga-project-/?utm_source=openai))
- https://www.ait.ac.at/en/about-the-ait/center/center-for-vision-automation-control/complex-dynamical-systems/projects/ai5production?no_cache=1 – AI5Production is a project that supports Austrian manufacturing companies with up to 2,999 employees in their digitalisation efforts. As part of the European Digital Innovation Hubs (EDIH) initiative, AI5Production acts as a central point of contact to make companies fit for the challenges of digital transformation. Services include access to research infrastructure and expertise to support digital transformation efforts, as well as assistance in securing funding for investments. In close cooperation with the hub’s partners, companies develop individual research and development approaches, providing access to infrastructure for tests, measurements, and test series, as well as the development of new products and processes. This offering is complemented by a diverse training programme that includes courses, webinars, and workshops on relevant topics relating to digitalisation and Industry 5.0. ([ait.ac.at](https://www.ait.ac.at/en/about-the-ait/center/center-for-vision-automation-control/complex-dynamical-systems/projects/ai5production?no_cache=1&utm_source=openai))
- https://european-digital-innovation-hubs.ec.europa.eu/edih-catalogue/ai5production-website/about – AI5Production is one of Austria’s four European Digital Innovation Hubs (EDIHs) within the pan-European EDIH network. It provides comprehensive digitalisation services to Austrian manufacturing companies with up to 3,000 employees, free of charge. Led by the Vienna University of Technology’s pilot factory, AI5Production comprises 16 partner institutions based in Vienna and Upper Austria, covering a wide range of expertise. The hub involves prominent universities such as TU Vienna, the University of Vienna, and JKU, along with AIT, Profactoras, several competence centers, and industrial partners. It grants Austrian companies free access to research infrastructure and expertise, facilitating their digital transformation. Additionally, the hub provides assistance in securing financing for digitisation investments. AI5Production focuses on four main areas: Digital Design, Digital Manufacturing, Cybersecurity, and Digital Transformation. ([european-digital-innovation-hubs.ec.europa.eu](https://european-digital-innovation-hubs.ec.europa.eu/edih-catalogue/ai5production-website/about?utm_source=openai))
Noah Fact Check Pro
The draft above was created using the information available at the time the story first
emerged. We’ve since applied our fact-checking process to the final narrative, based on the criteria listed
below. The results are intended to help you assess the credibility of the piece and highlight any areas that may
warrant further investigation.
Freshness check
Score:
8
Notes:
The article was published on 8 June 2026. A similar announcement was made on 28 May 2026 by Salzburg University of Applied Sciences and ABB’s Machine Automation Division (B&R), detailing a joint patent application for energy-optimised motion control in industrial drive systems. ([fh-salzburg.ac.at](https://www.fh-salzburg.ac.at/fhs/aktuelles/news/gemeinsame-patentanmeldung-von-fh-salzburg-und-abb-br-ki-fuer-energieeffiziente-industrieautomatisierung?utm_source=openai)) The earlier publication date suggests that the content may be recycled, potentially affecting the freshness score.
Quotes check
Score:
7
Notes:
The article includes direct quotes from Martin Haidacher, Innovation Manager at B&R, and Stefan Huber, Head of Research at Salzburg University of Applied Sciences. However, these quotes are also present in the 28 May 2026 announcement. ([fh-salzburg.ac.at](https://www.fh-salzburg.ac.at/fhs/aktuelles/news/gemeinsame-patentanmeldung-von-fh-salzburg-und-abb-br-ki-fuer-energieeffiziente-industrieautomatisierung?utm_source=openai)) The repetition of these quotes raises concerns about the originality of the content.
Source reliability
Score:
6
Notes:
The article originates from Drives & Controls, a publication focusing on automation and manufacturing. While it is a niche publication, it is not a major news organisation. The reliance on a press release from Salzburg University of Applied Sciences and ABB (B&R) indicates that the content may be based on promotional material, which can affect the independence and reliability of the information presented.
Plausibility check
Score:
8
Notes:
The claims about the collaboration between Salzburg University of Applied Sciences and ABB (B&R) to develop AI-based energy optimisation for industrial drives are plausible and align with known industry trends. However, the lack of independent verification and the reliance on a press release raise questions about the accuracy and completeness of the information.
Overall assessment
Verdict (FAIL, OPEN, PASS): FAIL
Confidence (LOW, MEDIUM, HIGH): MEDIUM
Summary:
The article presents information about a collaboration between Salzburg University of Applied Sciences and ABB (B&R) to develop AI-based energy optimisation for industrial drives. However, the content appears to be recycled from a press release dated 28 May 2026, with identical quotes and similar wording. The reliance on a single source without independent verification raises concerns about the freshness, originality, and reliability of the information. Given these issues, the article does not meet the necessary standards for publication.
