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.
More from Embodied
- Full teardown: inside Zmotor's 32mm linear actuator for humanoids — MarwaEldiwiny · 2026-10-27
- Full Teardown of a Zmotor Linear Actuator Used in China's Humanoid Robots — MarwaEldiwiny · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- First unboxing shots of Apple's foldable "iPhone Duo" surface — chrisfirst · 2026-10-27
- Bedrock Robotics Raises $600M Series C as Autonomous Excavators Do Paid Work on US Job Sites — davidpattersonx · 2026-10-27
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27