Maker's videoGalbot · 23 June 2026
World’s First General-Purpose Cerebellum GPT Foundation Model for Humanoid Robots: AstraBrain-WBC0.5
Against the record
Galbot G1, from Galbot (Galaxy General Robot), is at stage 3 of 5 on our ladder: pilot. Working with a named customer in a real setting. The latest milestone on its record is from Dec 2025: Galbot said G1 helps in patient rooms, pharmacies and with directions at Xuanwu Hospital.
This video comes from the maker's own channel, and makers show their robots at their best. The stage above comes from dated public records, not from the video.
From the video's description
Trained on 20,000 hours of human motion data — the largest-scale dataset to date — AstraBrain-WBC 0.5 marks the first validation of Scaling Law in the field of humanoid robot motion control, demonstrating that a robot’s motion control capabilities can continue to improve with data scale, just like large AI models. More importantly, the model enables real humanoid robots to execute a wide range of unseen motions through zero-shot generalization for the first time. Humanoid motion control is beginning to move beyond the traditional paradigm of “learning one motion, performing one motion,” and toward a foundation model approach capable of continuous generalization and evolution.
Written by Galbot on YouTube.
More videos of Galbot G1
Robot Tennis Stuns the Crowd in Seoul 🎾🤖 | GALBOT’s Korean Debut
Tennis Pro vs. a Humanoid Robot 🎾🤖 | China Open
From AlphaGo to AstraTennis: The World’s First Autonomous Humanoid Robot Tennis Match | GALBOT
Meet GALBOT ET1.
WAM-TTT: Teaching Robots to Adapt to New Environments by Watching Humans | GALBOT AstraBrain
All Data. Any Quality. Fully Utilized by one Latent World Action Model