ETH Demonstrates Maglev Robot that Catches Flying Objects

lukas_m_ziegler · x · 2026-07-14

A team at ETH Zürich demonstrated a system for catching flying objects using magnetic levitation. It can intercept and catch tossed balls in mid-air using an electromagnetic levitation device.

Key highlights:

The levitation device features 6-DOF control, allowing it to position and adjust object orientation in any direction.
The system predicts the ball's trajectory to intercept it mid-flight.
The design utilizes two eccentric magnets to achieve full 6-DOF control, rather than simple levitation.
Traditional methods rely on analytical models with strong symmetry assumptions (Multipole Expansion Model) and require rigorous calibration.
The new approach uses a neural network to learn magnetic field relationships directly from data, using an MLP to capture non-linearities while preserving the linear relationship between current and force.
This method removes the reliance on symmetry assumptions and can adapt to irregular geometries.

The post includes a link to the paper.

Original post →

ETH Demonstrates Maglev Robot that Catches Flying Objects

More from Embodied