AI News

Apple researchers open-source humanoid robot control system HALO, with a 91% single-task success rate

X.PINUpdated Nov 10 00:02

AI summary

Apple researchers have open-sourced a humanoid robot control system called HALO, which achieves a 91% success rate on a single real-world task. But when actions are chained together, the success rate drops noticeably—for example, when sequentially crawling under an obstacle, walking, and pushing a box, the success rate falls to about 50%. The original text also mentions that Ming-Chi Kuo, based on this, believes that large-scale mass production will not come until 2028 at the earliest.

Why read this

AI score 60

The original text presents the gap between the single-task success rate and the success rate after chaining multiple tasks, so readers can judge how far humanoid robot control still is from practical deployment.

Topics

Tags

Body

Apple researchers just open-sourced "HALO," a humanoid control system hitting 91% success on single real-world tasks.

The catch shows why Ming-Chi Kuo pegged mass production for 2028 at the earliest: chaining "duck under obstacle → walk → push box" drops success to a 50% coin flip.

Source

X.PIN