Photo: BMW
Humanoid robots are expected to do more than follow predefined routines. In future, they should understand their surroundings, assess situations and independently select appropriate actions. At its Landshut plant, the BMW Group is now developing software for AI-powered robotic systems in component production – marking the transition from conventional automation to Physical AI.
The work focuses on open software platforms, production data, simulations and motion planning. Traditional programming is combined with Vision-Language-Action models that connect visual information, language understanding and robotic actions. The goal is a modular system that can support different robots and industrial applications.
“At the BMW Group Plant Landshut, we combine software expertise with the industrial practice of our component production. This enables us to test new technologies at an early stage and thoroughly assess their benefits for production,” says Dr Wolfgang Blümlhuber, Head of Technology Driving Dynamics and In-house Component Production.
Potential applications include tasks where conventional industrial robots reach their limits: recognising changing environments, precisely gripping components or carrying out activities requiring flexibility and fine motor skills. Human operators demonstrate the movements, which are recorded using cameras, motion-capture suits and data gloves. The resulting data is used to create behavioural models that can be transferred to different tasks.
“We are not only examining what is technically possible, but also where humanoid robotics can deliver tangible benefits in component production,” explains Christoph Jagoda, Project Manager Physical AI at the BMW Group Plant Landshut.
BMW is cooperating with Athenyx Robotics, a startup originating from RWTH Aachen University, as well as Landshut University of Applied Sciences. The developments complement existing pilot projects in Leipzig and Spartanburg and strengthen Landshut’s role as a centre for intelligent production.
You are currently viewing a placeholder content from Google Maps. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou need to load content from reCAPTCHA to submit the form. Please note that doing so will share data with third-party providers.
More Information
