The Munich Institute of Robotics and Machine Intelligence (TUM MIRMI) at the Technical University of Munich (TUM) and NEURA Robotics have opened the TUM RoboGym, one of Europe's most advanced training and research centers for embodied artificial intelligence. Initially, around 100 humanoid and service robots will learn specific skills and processes in 48 training cells. The large volumes of training data will help make robots safer and more reliable.
Andreas Heddergott / TUM In brief
- New TUM RoboGym robot training center opens at the LabCampus innovation hub.
- Collaboration between TUM and NEURA aims to translate research findings into industrial applications.
- Robotics company NEURA provides humanoids robots and infrastructure.
In addition to its robot training cells, the center at the LabCampus innovation hub at Munich Airport provides substantial computing power for AI model training and computer simulations. These resources generate large amounts of data to support the development of more intelligent robots. The current focus is on industrial applications and intralogistics.
Generating large volumes of data in training and simulation environments
Unlike generative AI systems such as ChatGPT, which can draw on vast amounts of data from the internet, embodied AI requires training data from real-world physical interactions. Such data is currently scarce. The new training center features robot training cells where robots learn tasks including folding boxes, assembling components and using tools. At the TUM RoboGym, robotic skills can be developed and tested in realistic environments. At the opening, NEURA Robotics also unveils the next generation of its 4NE1 humanoid robot, which will subsequently be available at the TUM RoboGym.
Data generated at the TUM RoboGym flows into a curated cloud data lake, where it is available for training physical AI models. As a central scientific resource, the data lake enables scalable research into generalizable robotic skills, safe human-robot interaction and AI models for robotics.
Turning prototypes into products
The project's core objective is to transfer scientific results into practical applications. "Close, continuous and flexible collaboration with the robotics industry is essential for research in physical AI. It is the only way to systematically and rapidly develop research prototypes into market-ready products," says Prof. Achim Lilienthal of TUM MIRMI, Scientific Coordinator of the TUM RoboGym. He describes the initiative as a pioneering pilot project for TUM.
Hubert Aiwanger, Deputy Minister-President of Bavaria and Bavarian Minister of Economic Affairs: "Whether in a factory, a trades business or the care sector, intelligent robots can make a real difference. They can transport materials, assemble components, and take over physically demanding routine tasks. This eases the burden on employees and frees them up for tasks that require human skills. With skilled workers in short supply, this presents a major opportunity for our businesses."
TUM President Prof. Thomas F. Hofmann emphasizes: "The TUM RoboGym is unique in Germany and Europe. Through our collaboration with NEURA Robotics, we are also sending a clear signal in support of Germany as an industrial base at a time of geopolitical uncertainty."
Prof. Lorenzo Masia, Executive Director of TUM MIRMI and Director of the TUM RoboGym: "TUM MIRMI and NEURA Robotics are two partners with the potential to achieve great things together. Building on our world-leading scientific expertise, we can now work with a strong industrial partner to prepare concrete applications for the market. Our long-term goal is to create a dynamic robotics industry that can help drive growth in the German economy."
David Reger, CEO of NEURA Robotics: "Our companies hold knowledge that has been built up over generations. People know how to work materials, assemble components and master difficult processes. This knowledge is one of our greatest strengths in the age of Physical AI. With TUM, we are building a powerhouse for physical capabilities, where this knowledge becomes the foundation for new possibilities. The Mittelstand, in particular, should be able to help shape this future. With the launch of the humanoid 4NE1 Gen 4, we are showing today which robots are ready for it: designed for series production, built for productive work and powered by Neuron AI, our own foundation model that learns from experience in the NEURA Gyms. Developed, built and trained in Germany, for the world."
- As an interdisciplinary innovation hub, LabCampus brings together academia, international technology companies, scale-ups and emerging talent. Its curated community promotes collaboration between research and industry, creating further opportunities for joint innovation. Further information
- The infrastructure includes the following components:
- Service and maintenance areas for humanoid and collaborative robot platforms
- Motion-capture systems for recording movements and tracking objects. These systems generate datasets for training foundation models in physical AI.
- Cloud computing infrastructure for computer simulations, reinforcement learning based on trial and error, and training large-scale AI models. GPU-based computing nodes, networks and storage systems are integrated into NEURA's software ecosystem, Neuraverse.
- Q&A on the TUM RoboGym
- The Munich Institute of Robotics and Machine Intelligence (TUM MIRMI) is an Integrative Research Institute at TUM focusing on robotics and AI. It has leading expertise in key areas of robotics, including perception and data science. Nearly 80 TUM professorships are connected through TUM MIRMI to develop innovative robotics and AI-supported solutions for the environment, health, mobility, work, and security and defense. Prof. Lorenzo Masia is Executive Director of TUM MIRMI, with Prof. Achim Lilienthal serving as Deputy Director. Further information is available at www.mirmi.tum.de.
