The ERAT Program 2026

08:00 – 08:30 a.m. | Welcome Area

08:10 – 08:25 a.m. | Tech Arena

08:30 – 08:50 a.m. | Europasaal

A. Pogany (BMIMI), J. Herk (President of the Styrian Economic Chamber), U. Haslauer (President of GMAR ), H. Ritter (Chairman of AT STYRIA)

08:50 – 09:30 a.m. | Europasaal

This talk explores how model-based inference and deep representations can be composed to enable robust robot autonomy, with a focus on perception and planning in complex environments. Building on some of the recent research activities and achievements of the Laboratory for Autonomous Systems and Mobile Robotics (LAMOR) in visual odometry, monocular depth estimation, and sensor calibration, we will show how a modular pipeline combining geometry, probabilistic estimation, and transformer-based architecture improves accuracy, robustness, and generalization of visual ego-motion estimation methods. On the planning side, we will discuss an approach to high-dimensional motion planning for efficient navigation of robotic manipulators in cluttered scenes, thus closing the loop between perception, estimation, and planning.

Ivan Marković is a Full Professor at the University of Zagreb Faculty of Electrical Engineering and Computing, Croatia (UNIZG-FER) where he leads the Robotic perception and sensor fusion group within the Laboratory for Autonomous Systems and Mobile Robotics – LAMOR (http://lamor.fer.hr). He received the M.Sc. and Ph.D. degree in Electrical Engineering from the UNIZG-FER in 2008 and 2014, respectively. His research is focused on various aspects of estimation theory, sensor fusion, and  machine learning with applications to robot and vehicle autonomy and human-robot interaction. He received the National Science Award by the Republic of Croatia (2023), the Young Scientist Award “Vera Johanides” from the Croatian Academy of Technical Sciences (2018), and the Silver Plaque “Josip Lončar” UNIZG-FER for outstanding doctoral dissertation (2014). He has actively participated as a researcher in about 20 research and development projects at national and EU level. He was a visiting researcher at INRIA Rennes-Bretagne Atlantique, Rennes, France, under the supervision of Prof. François Chaumette. He serves as the Editor-In-Chief of the T&F journal Automatika indexed in the Science Citation Index Expanded. He is a member of the Institute of Electrical and Electronics Engineers(IEEE), IFAC Technical Committee on Robotics, and the Croatian Society for Communication, Computing, Electronics, Measurement and Control (KoREMA).

09:30 – 10:00 a.m. | Europasaal

The agentic age has arrived inside industrial operations. Autonomous systems are taking decisions on the shop floor, in the warehouse, in plant energy management, and across supplier networks. Europe regulates. The US deploys. China industrializes. The boards and CEOs that read this moment correctly will set the standard for European industry over the next decade. The rest will follow at a price. The Question is still open: Who sets the agenda? Plain spoken, industrially grounded, with a clear list of what to decide and by when.

Christina Wilfinger has built an international career in leading technology companies. At SAP and Microsoft, she held executive leadership roles with responsibility for key business units. As CEO of SAP Austria, with additional responsibility for the CEE region, she drove growth, customer development, and the mid-market business.Today, she brings her experience in digital transformation, strategic corporate leadership, and change management to her work as an independent advisor, investor, and supervisory board member, including roles with Raiffeisen Holding Lower Austria-Vienna, GRAWE Banking Group, Umdasch Store Makers, and as a Foundation Board Member of Austrian broadcasting corporation. She also serves as a University Council Member of the University of Graz and is a F&A investor focused on innovation and the digitalization of European start-ups.

10:00 – 10:45 a.m. | Tech Arena

10:45 – 11:15 a.m. | Europasaal

Applied robotics and AI at CRTA: From science to industrial innovation

The talk will present CRTA as an application-oriented research ecosystem, with examples from actual projects such as PRONOBIS, which develops a robot-assisted prostate biopsy system; ANDROMEDA, focused on autonomous robotic drilling for neurosurgical applications; INSPIRATION, addressing non-invasive patient registration for robotic neurosurgery; INSIGHT, a cooperation with the BMW Group on AI-based models for battery cell manufacturing and recycling; MARINERO, an autonomous robotic system for smart marinas; and ASAP, a robotic system for autonomous inspection and prediction of transport infrastructure integrity. These projects demonstrate how advanced robotics and AI can move beyond laboratory prototypes toward clinically relevant systems, industrial services, autonomous inspection platforms, sustainable tourism technologies, and safer human-centered environments.

About CRTA: The Regional Center of Excellence for Robotic Technology, CRTA, at the University of Zagreb Faculty of Mechanical Engineering and Naval Architecture, is a national reference point for research, development, testing, and implementation of advanced robotic systems in industry and medicine. Its mission is not only to advance scientific excellence, but also to create a practical environment in which robotic technologies, artificial intelligence, and autonomous systems can be validated together with industrial partners, hospitals, and research institutions. CRTA’s activities are focused on replacing rigid automation and demanding manual work with flexible, versatile, and adaptive robotic systems, while strengthening technology transfer and cooperation between academia and the economy.

11:15 a.m. – 12:15 p.m. | Europasaal

Moderation: Yeongmi Kim, MCI

Talk 1: Korea’s economy journey: From recovery to Physical AI, Minister, Embassy & Permanent Mission of the Republic of Korea

In one generation, Korea transformed from a war-torn, aid-dependent nation into a global technology and manufacturing powerhouse. Building on that momentum, it is now pursuing a bold national strategy to become the world’s leader in Physical AI by 2030.

Talk 2: Model-Based System Engineering with AI and Simulink, DI Dr. Andreas Ravazzolo-Mehrle, Mathworks

Agentic AI is currently being adopted by industry and researchers alike to accelerate development workflows. In this talk, we demonstrate such a workflow through the development of an inexpensive real-world robot using AI coding agents in MATLAB and Simulink while applying Model-Based Design principles. We show how engineering rigor can be combined with proper validation and verification practices to build trustworthy systems using MATLAB and Simulink with Agentic AI.

Talk 3: Kohyoung Technology – True In-line 3D Optical Inspection and AI Powered Smart Factory Solution, Dr. Hoseok Song, Koh Young Research Germany GmbH

Koh Young Technology is having No.1 global market share in the SMT inspection market. Based on this success, the company is expanding its business scope into the advanced packaging and medical industries. In this presentation, I will provide an overview of Koh Young Technology and introduce our recent effort to apply AI for improving usability and optimizing whole process in SMT line.

Talk 4: From Mobile Robots to Autonomous Material Flow: Integrating Intelligent Robotics into Smart Manufacturing, Thomas Kreuzberger, CTO, MIMM Engineers

Mobile robots are becoming an important part of smart manufacturing, evolving from isolated transport solutions toward increasingly connected and flexible material flow systems. This talk provides practical insights from industrial applications and looks at how mobile robots can be integrated into existing production environments, including interfaces, fleet management, and production planning. It also gives a brief outlook on current trends and the ongoing development toward more intelligent and autonomous material flow.

12:15 – 01:15 p.m. | Canteen & Tech Arena

01:15 – 02:00 p.m. | Europasaal

Moderation: FH-Prof. DI Dr. techn. Udo Traussnigg, Campus 02 University of Applied Sciences, Head of the Department of Automation Technology

Siemens Energy and the Smart Factory of TU Graz will present their success stories in this session, which you can experience live during the company tour on October 6. Register now for the company tour as well – places are limited!

Talk 1: From Weiz to the World – Power Transformers for a Reliable Grid, Simon Niederhold, Siemens Energy

Large power transformers from Weiz keep the grid running around the world. In this talk, Siemens Energy introduces its site, its people and its role in the energy transition – and shows how we combine traditional craftsmanship with modern manufacturing to stay ahead.

Talk 2: Autonomous Production: Visions and real-world Applications for Mechanical Engineering 2030+, Univ.-Prof. Dipl.-Ing. Dr.techn. Franz Haas, Dean of the Faculty of Mechanical Engineering and Economic Sciences & Head of the Institute of Production Engineering, TU Graz

As part of the Lab Tour, the TU Graz Institute of Production Engineering will present its activities in the Smart Factory area. In the age of AI, the vision of autonomous production is close to come into reality. In the future, we expect not only an upswing in the manufacturing sector but also breakthroughs in technologies such as edge computing, data analysis, humanoid robotics, and data spaces. Practical applications will be introduced in the talk. Live demonstrations during the Lab Tour show that modern production technologies offer high potentials for competitiveness.

02:00 – 02:30 p.m. | Tech Arena

03:00 – 3:50 p.m. | Europasaal

Moderation: Alexander Numrich, GMAR

Talk 1: SONIC – AI-Driven Robotic Tomography for Non-Destructive Testing, Thomas Gallien, Joanneum Research Robotics

SONIC is an FFG-funded research project investigating flexible, AI-supported non-destructive testing for complex industrial components. The project combines robotic Laser Ultrasound and X-ray CT with 3D surface acquisition, automated trajectory planning, and an Inference-as-a-Service concept in which measurement data are transferred via 5G to cloud/HPC resources for reconstruction. A particular focus is the use of physics-based simulation to generate synthetic training data for surrogate models and, subsequently, generative AI reconstruction methods. The talk will present the SONIC concept, its industrial use cases, and the current development status of the simulation and data-generation pipeline.

Talk 2: Simulated First, Live Later: When AI Agents Take Control of the Machine, Michael Eberle, digifai

Digital twins have arrived in mechanical engineering. They enable machines and control software to be developed and tested in a safe virtual environment before the actual system is built and commissioned. However, creating these digital twins takes time. This is where AI agents come in: they support the creation of simulation models and significantly shorten the path to a fully functional digital twin. And then what? Another agent takes over control. First in the simulation, where mistakes come at no cost. Then on the real machine, where they certainly do. Michael Eberle from digifai demonstrates this approach using twin as an example and explains why robust, reliable simulations are essential before AI agents can be allowed anywhere near a real machine.

03:50 – 04:30 p.m. | Europasaal

Moderation: Ivan Marković, University of Zagreb

Talk 1: Beyond the Pilot: What It Actually Takes to Scale Autonomous Forklifts, Tomislav Haus, Gideon

Gideon builds Trey, an AI-powered autonomous forklift that loads and unloads trailers in live warehouse and production operations. Getting a robot to work in a pilot is a different problem from getting a fleet to work every shift, and this talk is about the second one. After a brief pass over the core stack — 3D perception, autonomy and fleet orchestration — we turn to what daily production actually demanded: throughput and space efficiency against real operational targets, manipulation cases a pilot never exercises, goods and infrastructure that don’t behave as specified, and enough flexibility to fit processes that differ at every site. Each looked like an edge case at first and proved to be a precondition for volume.

Tak 2: Perception that grew up in a car: transferring automotive-grade computer vision into robotics, Hrvoje Šamija, Visage Technologies

Visage Technologies has spent over a decade building computer vision that ships in production vehicles — face and gaze tracking, driver and occupant monitoring, and ADAS perception developed inside the constraints of automotive: fixed silicon budgets, intense validation requirements, and functional safety process discipline. Those constraints turn out to be valuable knowledge for wider application. This talk examines what happens when that stack and expertise is applied to new domains: human-aware machines and operator monitoring, off-highway autonomy, visual inspection in pharma and medical fields, and defence. Using driver monitoring as the worked example, we cover what genuinely transfers—real-time inference on constrained hardware, corner-case discovery, and validation rigor—and what does not: the missing datasets, the absent sensor standards, and the regulatory landscapes that still lag behind automotive.

Talk 3: GrapOS in the wild: A safety-critical RTOS finding its place in robotics and beyond, Sandro Margeta, Končar Electrical Engineering Institute

KONČAR – Electrical Engineering Institute is primarily known for safety-critical systems in railway and power electronics, certified up to SIL 4. At the heart of those systems is GrapOS, our in-house real-time operating system designed from the ground up for functional safety applications. This talk explores how GrapOS has been stepping into the robotics and mechatronic space through three projects: a functional-safety-certified proximity protection system for human-robot coexistence in automated warehouses, embedded electronics and firmware for remotely operated vehicles requiring precise real-time control and our latest research effort bridging GrapOS with ROS 2. Along the way, we share what functional safety experience brings to robotic systems development, and what it doesn’t.

04:00 – 06:00 p.m. | Exhibitor Area

05:30–05:45 p.m. | Innovation Stage

DITEDI, the ICT Cluster of Friuli Venezia Giulia, connects digital innovation, industry and talent to accelerate the transition towards Industry 5.0. Following its 2026 alliance with the Styrian innovation ecosystem, DITEDI is developing Digital Frontiers  a cross-border gateway designed to connect SMEs and innovation ecosystems, foster technology exchange and build new pathways for European collaboration and growth.

05:45–07:00 p.m. | Innovation Stage

A TASTE OF STYRIA: WINE & CULINARY CLOSING

A convivial closing moment celebrating Styrian wine, culinary culture and international connections, followed by acknowledgements and an outlook on ERAT 2027 – Italy as Partner Country.