NEURA Robotics, E.ON and enviaM are partnering to develop Physical AI for grid inspections, asset monitoring and hazardous tasks.
Robotic skills will first be trained and tested at TUM RoboGym powered by NEURA in Munich, using NEURA’s open Physical AI platform, Neuraverse. MITNETZ STROM, enviaM’s grid subsidiary, will then test initial applications in real-world grid operations.
MITNETZ STROM is one of the largest regional distribution system operators in eastern Germany. enviaM Group chief executive Stephan Lowis said the company expects to gain initial practical experience during 2027.
The initial focus will be on tasks such as inspections, monitoring critical assets including substations, and supporting site security. Work in potentially hazardous environments will also be assessed.
TUM RoboGym was opened by NEURA and the Technical University of Munich at LabCampus at Munich Airport in October. It covers more than 2,300 sq. metres, and companies from more than 10 industries are already training robots there. E.ON is joining the centre to bring the energy sector into the mix.
Teams from E.ON, MITNETZ STROM and NEURA will identify specific use cases in grid operations at the outset. Skilled workers will contribute their experience and requirements, while NEURA will provide the training and software infrastructure through its NEURA Gym and Neuraverse. Findings from the tests will inform further development of both the skills and the platform.
Robots will be trained using three methods: human demonstrations by grid specialists, captured through sensor-equipped suits, motion capture and teleoperation; real-world robot data recorded during tasks; and simulation, with skills then validated on real robots. They will learn using Neuron AI, NEURA’s multimodal foundation model, which combines 3D vision, touch, audio, robot state, language and memory.
NEURA said humanoid robots such as its 4NE1 could navigate grid facilities, which are built with stairs, doors, control cabinets and tools, without requiring modifications. Neuraverse is intended to allow skills trained in the NEURA Gym to be reused on compatible robots and at additional sites. E.ON and enviaM will retain control of their own data and trained skills, and will decide whether, and with whom, to share them.
David Reger, founder and chief executive of NEURA Robotics, said: “Physical AI and cognitive robotics will fundamentally reshape the energy sector. The key is to combine technological progress with the practical expertise of the people who operate our energy infrastructure every day. That is precisely where we come in: with Physical AI that supports these people and opens up new possibilities for them.
“Together with E.ON and enviaM, we want to make this expertise available to intelligent machines through Neuraverse. Robots will learn in our NEURA Gyms and then apply their skills where they can ease people’s workloads and improve safety. Our shared ambition goes beyond deploying individual robots: we want to create a scalable foundation for Physical AI in critical infrastructure, developed and trained in Europe.”
Translating innovation into practice
Stefan Padberg, senior vice president for innovation at E.ON, said: “The energy transition needs strong grids, and strong grids need innovation. Together with enviaM and NEURA Robotics, we are demonstrating how innovation translates into practical grid operations – and how digital technologies can improve safety, make processes more efficient and create smarter, more resilient energy infrastructure.”
Lowis said: “Electricity grids are the backbone of our society. They face greater demands than ever: electrification and the transformation of the energy supply require power lines and assets to be expanded, modernised and continuously monitored. This partnership brings next-generation technology to where it can deliver tangible value – day-to-day grid operations.
“Our employees carry out demanding work with a high level of responsibility every day. Humanoid robots can provide targeted support, particularly for physically demanding tasks or those with specific safety requirements. They can take on routine tasks and work in potentially hazardous areas, allowing skilled workers to focus on the tasks that require their expertise. We expect to gain initial practical experience during 2027.”
Image credit: NEURA Robotics
Read next: Bellrock names Matt Forbes chief executive
Are you a building professional? Sign up for a FREE MEMBERSHIP to upload news stories, post job vacancies, and connect with colleagues on our secure social feed.


