A vision model walked a humanoid robot to a table and described what was on it
An LLM with vision controlled his Unitree humanoid, walked slowly to a table, steered to it and described objects on it, avoiding crashes better than other models tried.
This only partly worked. Read what happened before you try it.
How it works
- An LLM with vision controls the humanoid robot
- Walks slowly to a table, steers to it and describes the objects on it
- Avoiding crashes better than other models tried
Why it’s worth knowing
A language model with legs is a sentence nobody wrote before this decade.
Where it’s from
Summarized from a public post on news.ycombinator.com. See the original ↗