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.
More from Embodied
- Musk predicts Tesla Optimus will wash, dry and put away dishes in 12-18 months — Polymarket · 2026-11-19
- Nimo Robotics launches N1 glove and D1 hand: highest-DoF commercial UMI system for industrial robot skills — Scobleizer · 2026-11-19
- Robot Model Dream-1 Learns to Drive a Real Tesla From 1.5h of Demos — scott_e_reed · 2026-11-19
- Stack-chan desktop robot gets a screwless multi-leg armor mod, files open-sourced — alexcovo_eth · 2026-11-19
- Inceptio tops 1.2B km of driverless-truck operations, makes the case for freight-native physical AI — 量子位 · 2026-11-19
- Antigravity Robotics plugin lets anyone build MuJoCo sim tasks with prompts — DynamicWebPaige · 2026-11-19