FMC³ Robotics introduced Doceo, a data collection and training system designed to teach industrial robots manufacturing tasks by observing human workers. The system uses smart camera headsets, external cameras, and optional touch-sensitive gloves to capture visual, depth, movement, and tactile information during normal factory operations. That data feeds an AI training pipeline built in partnership with Vector Informatik.
The platform consists of four components: RealCap captures worker activity, Hub synchronizes and annotates data streams, Cloud handles ingestion and model training, and Driver deploys trained capabilities to physical robots. FMC³ positions this as an alternative to simulation-heavy approaches, arguing that real-world production data better reflects the variability and physical constraints robots will encounter.
Two proof-of-concept projects are underway. At a consumer electronics plant, FMC³ is testing a wheeled robot that transports bins of different sizes between workstations. At a battery cell facility, the company is developing a robot to handle electrode sheets with high positioning accuracy. Both remain at early evaluation stages.
The company is also pursuing a German joint venture with Vector Informatik and PEM Motion to standardize industrial training data infrastructure. The goal is to make datasets reusable across factories and robot platforms, reducing the engineering overhead when production requirements change.



