https://hackerpaper.kaipfister.de/p/1903.06684/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=20941195urn:hackerpapers:mention:1903.06684:20941195Wed, 11 Sep 2019 15:30:32 GMT<p>This seems to play very well with some of MIT CSAIL&#x27;s research in training robots to be able to manipulate objects they haven&#x27;t seen before. [1] https://www.youtube.com/watch?v=l9U8X6I1vow [2] https://arxiv.org/abs/1903.06684 TL;DR the objects are grouped into categories which determine the &quot;Key points&quot; on the objects (similar to this &#x27;skeleton&#x27;) which the robot knows how to interact with in order to bring about the intended manipulation.</p><p><a href="https://hackerpaper.kaipfister.de/p/1903.06684/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.RO