ETH uses RL to teach a 5-tonne skid-steer loader acrobatic stunts

Kyrannio · x · 2026-11-19

ETH's legged robotics team used reinforcement learning, trained in simulation and transferred to a real 5-tonne John Deere skid-steer loader, to autonomously perform complex manoeuvres: balancing on two wheels, navigating rough terrain, spinning, and controlling the bucket before landing safely. Paper published — a striking demo of AI-driven automation for heavy machinery. The quip: only a few humans could match this after a beer or twelve.

Related event: ETH Zurich Uses Reinforcement Learning to Make a 5-Ton Skid Steer Perform Two-Wheel Stunts(5 posts)→

Original post →

More from Embodied

Embodied channel →