Do As I Can, Not As I Say: Grounding Language in Robotic Affordances · HackerPapers discussions

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances — HN submission

Thu, 18 Aug 2022 12:37:01 GMT

Do as I Can, Not as I Say: Grounding Language in Robotic Affordances

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances — mentioned by gwern

Fri, 15 Jul 2022 18:15:37 GMT

> Natural language processing just isn't far enough along to understand human direction giving. https://arxiv.org/abs/2207.04429 https://arxiv.org/abs/2204.01691#google https://arxiv.org/abs/2207.05608#google https://arxiv.org/abs/2207.05608#google https://arxiv.org/abs/2109.01115 etc

Paper and discussion history. A mention is not an endorsement.

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances — mentioned by gwern

Tue, 14 Jun 2022 17:27:53 GMT

Because Nethack and video games remove most of the reasons that GOFAI failed; for example, everything hard about perception from pixels is removed when you have a little parsed text grid of cells presented to you or are hooked into the game engine and query objects directly. (The real world is not made of a clean little grid of discrete high-level objects like 'dragon' or 'black jelly'.) Moravec's paradox again: humans find perception easy but things like Sokoban hard, while GOFAI approaches find Sokoban so trivial that it's common to use it (or Sudoku) as a toy problem introduction to…

Paper and discussion history. A mention is not an endorsement.