AI Trends

Hao AI Lab Speeds Up GPT-6 Astra + Codex Robotic Agent by About 3×

UCSD Hao AI LabUpdated Nov 20 09:59

AI summary

By consolidating tool-call round trips, shortening the context, and running model reasoning in parallel with robot motion, Hao AI Lab made the GPT-6 Astra + Codex agent about 3× faster on test tasks. The cup task was shortened from 11.1 min to 3.4 min, while towel folding was reduced from about 18 min to about 6 min, and the share of time spent on robot motion increased from 24% to 84%. Each action is still based on observations from about 5 s earlier, so reacting to environmental changes takes about 5 s.

Why read this

SelectedAI score 69

By consolidating tool-call round trips and running model reasoning in parallel with robot motion, the team offers a transferable engineering approach to reducing the time required for real-world robotic tasks.

Topics

Tags

Body

First, we gave Astra a cup game: three cups hide a pear, a ball and nothing, and it has to put the pear under the empty cup (video at 3.5x). https://t.co/tdYyjJV5Qj

Source

UCSD Hao AI Lab