Gemini 4 Argon taught a humanoid robot to play cornhole from a video
Google DeepMind says Gemini 4 Argon watched a video of cornhole, worked out the physics, wrote its own simulation and used it to teach Apptronik's Apollo humanoid robot, which then landed seven throws in a row.
Why it matters
It shows a model going from watching to simulating to controlling a real robot, a step towards robots that learn new tasks quickly.
Who it's for
Robotics engineers, researchers and anyone tracking where AI agents are heading.
How to try it
- Watch the clip in DeepMind's post.
- Note the chain: video → physics model → simulation → robot policy.
- For your own work, try asking Argon to write a small physics simulation from a description or video.
Plan & availability: Research demo from Google DeepMind; not a consumer feature.
Source: @GoogleDeepMind on X ↗
Written by AgentStackList from the original post. Checked Oct 17, 2026. Features, plans and availability can change, so confirm on the source before you rely on it.
roboticsargondeepmind
More Gemini tricks
- Nano Banana prompt pack: SQL-style "planet in a hand" city dioramas · Oct 17
- A developer reports high cache-miss rates on the Gemini API · Oct 17
- Turn a dense PDF into an interactive web app with Canvas · Oct 16
- Google AI Pro subscribers can now build with Argon in AI Studio · Oct 16
Agent Stack Weekly · free
Get the week's best AI tricks
Limit and pricing changes, new MCP servers, and setup fixes for Claude Code, Codex, Cursor, Copilot and Antigravity.
No spam. Unsubscribe anytime. Read past issues