News for hackers. Stuff that matters.
Re:Covariant.ai and applying deep learning to robotics by amelius on Wednesday May 06, 2020 @07:19PM (#23097604)
I was under the impression that reinforcement learning already tackled the "picking" problem sufficiently well.
Re:Covariant.ai and applying deep learning to robotics by sgillen on Wednesday May 06, 2020 @08:21PM (#23098165)
I believe your impression is wrong. I believe that amazon shut down its picking challenge in 2018 because it was clear to them the technology wasn’t ready to replace humans in there distributions centers yet.

I’d be happy to be proven wrong though if you have examples.

Re:Covariant.ai and applying deep learning to robotics by dbcurtis on Wednesday May 06, 2020 @08:48PM (#23098357)
We are pretty far away. Perception-based manipulation is a very active area of research. It will help a lot of underfed grad students get their PhD's over the next decade.
Re:Covariant.ai and applying deep learning to robotics by ragebol on Thursday May 07, 2020 @02:50AM (#23100396)
Maybe on a research level in still relatively controlled settings.

It's only recently that that you could use this with a high success rate in 'the wild'