ETH researchers train a 5-tonne skid-steer loader to balance on two wheels via RL and sim2real
KyleCranmer · x · 2026-11-19
Researchers trained a 5-tonne John Deere skid-steer loader with reinforcement learning, first in simulation and then transferred to the real machine (sim2real).
The system can autonomously:
- balance and drive on two wheels
- navigate rough terrain
- spin while controlling its bucket, then land safely
The demo highlights the potential of AI-driven automation for heavy construction and industrial machinery, and validates sim2real transfer on massive, non-legged platforms.
Related event: ETH Zurich Uses RL to Teach 5-Ton Loader Two-Wheel Stunts(5 posts)→
More from Embodied
- 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
- META-Robot from HKUST completes 44/56 real-robot trials with self-repair — jiqizhixin · 2026-11-19