[HN Gopher] Robot Learns to See in 30 Minutes
___________________________________________________________________
Robot Learns to See in 30 Minutes
Author : stoniejohnson
Score : 40 points
Date : 2023-03-26 21:26 UTC (1 hours ago)
(HTM) web link (antonilo.github.io)
(TXT) w3m dump (antonilo.github.io)
| stoniejohnson wrote:
| Via simulation + meta-learning they can make a _blind_ robot walk
| over arbitrary terrains solely via proprioception.
|
| They add a visual component, which with 30 minutes of real world
| data, through a technique called Cross-Modal Supervision (CMS),
| is able to improve walking performance significantly!
|
| They can even distort its vision (turn the camera) and it learns
| to adapt!
|
| Paper: https://arxiv.org/abs/2211.03785
|
| Advisor Presentation: https://www.youtube.com/watch?v=f6fDpKDxpL0
|
| Note: This is not my work; I originally found the presentation
| above.
| EGreg wrote:
| When one robot learns, millions of them learn
|
| When millions of cars learn, they all can send data back to the
| mothership which crunches the numbers and they all improve
|
| Even without AI, this is how technology has always advanced.
| Humans simply improved things and copied it to all the
| implementations.
|
| So basically, when it comes to competing with robots or
| software, it is a losing proposition in the long run. No
| biological animal can evolve faster than this.
| chiefalchemist wrote:
| It's not the learning that's the magic. It can be 30 minutes or
| 30 days. It hardly matters. Where the sparks fly is that learning
| can he transfered in .3 seconds to 300,000 other robots. And then
| updated as needed.
|
| Now compare the to humans.
| stoniejohnson wrote:
| The fact that it is learning online in fractions of a second to
| prevent falling (I would say) is pretty magic!
| margorczynski wrote:
| I can't find it in the paper - is the inference ran on the robot
| directly or remotely on a more powerful computer?
___________________________________________________________________
(page generated 2023-03-26 23:00 UTC)