News for hackers. Stuff that matters.

A comment on Google DeepMind's Aloha Unleashed is pushing the boundaries of robot dexterity. Parent comment

Re:Google DeepMind's Aloha Unleashed is pushing the boundari... by johntb86 on Tuesday April 16, 2024 @02:07PM (#40055256)
What do you mean by saying that they're replaying signals from teleoperation demonstrations? Like in https://twitter.com/DannyDriess/status/1780270239185588732, was someone demonstrating how to struggle to fold a shirt, then they put a shirt in the same orientation and had the robot repeat the same motor commands?
[ Parent | on HN ]
Re:Google DeepMind's Aloha Unleashed is pushing the boundari... by YeGoblynQueenne on Wednesday April 17, 2024 @07:43AM (#40063192)
Yeah, it's called imitation learning. Check out the Mobile ALOHA paper where they explain their approach in some detail:

https://arxiv.org/abs/2401.02117

[ Parent | on HN ]