Skild AI trains Unitree G1 with 140 years of self-play to play soccer against humans
ZGojcic · x · 2026-09-24
Skild AI unveiled its #Messinator project: a Unitree G1 humanoid trained via self-play equivalent to 140 years in a simulated World Cup, then deployed in the real world to autonomously play soccer against humans — intercepting, defending, and dribbling on the attack.
The sim-to-real approach sidesteps the decade-long linear training a human player needs, compressing over a century of match experience into a few weeks of simulation. The author frames soccer as just a proving ground: the same self-play-plus-simulation recipe could scale to construction sites, factories, supermarkets, and homes.
More from Embodied
- Guava distills GPT-5.4 into a 4B robot agent with just 2,000 simulated trajectories — jbhuang0604 · 2026-11-09
- Dex-One2Many learns dexterous manipulation from one human video, 95%+ success across 4 hands — jbhuang0604 · 2026-11-09
- Fly-by-Code: coding agents pilot drones via active visual and physical feedback loops — jbhuang0604 · 2026-11-09
- μ0 world model learns robot physics from video only, beats π0 by 5 points on RoboCasa365 — jbhuang0604 · 2026-11-09
- NVIDIA unveils GR00T 2 open-world robot action model, hitting 95% success with 5 demos — CyberRobooo · 2026-11-09
- CoRL keynote to explore open-source data and hardware for robotics — micoolcho · 2026-11-09