Researchers Comment on Robot In-Context Learning Video
Posts examine a robot demonstration of in-context learning for new tasks.
TLDR
Andrew Carr responded to Lerrel Pinto's post by suggesting 3D simulation of robot demonstrations to replace physical ones. Yoav Goldberg replied that the robot in the video squeezed too hard and dropped early, striking the side of the bowl. He added that semantic understanding appears incomplete and guessed the system had learned to pick the yellow item and drop it over the blue one.
Combined views
14.3K
2 Sources, first seen ago
Sources
AC 
Andrew Carr ๐คธ@andrew_n_carrnow imagine if you could simulate this in 3D so you didn't need to do the demonstrations yourself!! https://twitter.com/LerrelPinto/status/2093400831941116254
- likes: 36
- replies: 3
- bookmarks: 9
- reposts: 0
(' (((ู()(ู() 'yoav))))๐พ@yoavgoam I the only one seeing the robot squeeze too hard and also dropping too early hitting the side of the bowl? (not saying this is easy, but semantic understanding is not quite there yet --- i assume it learned "pick yellow drop over blue")โฆ
- likes: 4
- replies: 1
- bookmarks: 1
- reposts: 0