BMW Plant Landshut develops AI software for humanoid robots in component production
BMW's Landshut plant will develop the software stack for humanoid robots to handle flexible, fine-motor tasks in component production.
- 2026
What Happened
BMW Group Plant Landshut is taking on central software development for AI-supported robotics in component production. The work complements pilot projects already underway exploring humanoid robotics at Plants Leipzig and Spartanburg. Landshut's role as a center of expertise for in-house component production provides ideal conditions for testing new approaches under real-world conditions.
- Open software platforms
- Generation, provision and processing of training data
- Simulation and motion planning
- Training of robotic systems
“At BMW Group Plant Landshut, we are combining software expertise with industrial practice in our component production. This allows us to test new technologies at an early stage and carefully evaluate their benefits for production.”
The technological foundation relies on open platforms that combine traditional deterministic programming with modern Vision-Language-Action (VLA) models. The goal is a modular robotics ecosystem where diverse systems work together. Data from real production environments and test setups is captured and integrated into simulations to accelerate learning.
Humanoid robotic systems acquire new skills through demonstration-based learning. Movement patterns are first demonstrated by the project team, captured by camera systems, motion capture suits and data gloves, then converted into generalizable behavioral models called policies.
“For us, it is crucial to develop the technology in very close alignment with real-world requirements. We are not just testing what is technically possible, but also where humanoid robotics can truly deliver reliable benefits in component production.”
BMW is collaborating with partners including Athenyx Robotics, a startup from RWTH Aachen University, to develop an 'intelligence stack' that integrates perception, learning, simulation and decision-making. The University of Applied Sciences Landshut is also involved in data generation, simulation and testing specific use cases.
Why this matters
This development could lead to humanoid robots taking over complex manual tasks in BMW's component production, increasing flexibility and efficiency. It positions BMW as a leader in applying AI to manufacturing, potentially affecting how production lines are staffed and designed.
Terms in This Story
- humanoid robotics
- Robots designed to resemble the human body, capable of performing tasks in environments built for humans.
- Vision-Language-Action (VLA) models
- AI models that combine visual perception, language understanding, and robotic actions to enable autonomous behavior.
- policy
- In robotics, a behavioral model that maps sensor inputs to actions, allowing a robot to perform tasks autonomously.
Summarised from the linked release; details can be imperfect — always verify against the original source.