RoboBoom
NEXT with John Koetsier· October 6, 2026· 28:12

1000 robots, 1 factory: Hexagon preps for robot fleets at Schaeffler

Arno Rober, president of Hexagon Robotics, talks with John Koetsier on NEXT about preparing Aeon robot fleets for factory work, including the Schaeffler plan to train, deploy, and scale toward 1,000 robots.

In this talk

  1. 1:02

    A multipurpose fleet for changing factory demand

    Rober says a fleet of 1,000 robots needs planning beyond repeating one robot's single task. Hexagon designed Aeon to take on different jobs, from moving boxes and pick-and-place work to inspecting parts and capturing factory conditions, so robots can be assigned where demand shifts.

  2. 3:56

    Training with factory data and feedback

    Rober describes using simulation, synthetic, and recorded data to train robots. Factory-specific data must be protected, and Hexagon's approach includes feeding sensor records from real tasks back into training to account for changes in the surrounding environment. He says training needs useful data, not just large volumes.

  3. 10:21

    From pilot feasibility to production

    Rober distinguishes a pilot that proves a task can be done from production, which requires repeatable performance and scale. He says a production robot should complete the work reliably across a six-hour shift, and that what one robot learns must transfer to many others. Hexagon focuses on cycle time and human intervention as key measures.

  4. 15:40

    Designing for mobility and human collaboration

    Rober says early sensor-fusion methods were too simple because manipulation depends on the robot's position and the wider environment, not just its arms and target object. Hexagon chose a wheeled base for mobile factory tasks and says it can also handle stairs. He describes a future factory where autonomous robots help address labor shortages and bottlenecks while workers shift toward problem-solving.

  5. 25:47

    A stepwise path to 1,000 robots at Schaeffler

    Rober says Hexagon is taking a staged approach with Schaeffler: train Aeon in the Schaeffler Gym, a replica of the production environment, then deploy and scale. The team is evaluating multiple tasks there, scaling the ones Aeon performs well and using harder tasks to guide future development.

Briefs summarise talks and interviews; timestamps open the video at that moment. Claims in a talk are the speaker's own.

More talks