Author Interview - SayCan - Do As I Can, Not As I Say - Grounding Language in Robotic Affordances

Author Interview - SayCan - Do As I Can, Not As I Say - Grounding Language in Robotic Affordances

Yannic Kilcher via YouTube Direct link

- Introduction & Setup

1 of 17

1 of 17

- Introduction & Setup

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Author Interview - SayCan - Do As I Can, Not As I Say - Grounding Language in Robotic Affordances

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Introduction & Setup
  2. 2 - Acquiring atomic low-level skills
  3. 3 - How does the language model come in?
  4. 4 - Why are you scoring instead of generating?
  5. 5 - How do you deal with ambiguity in language?
  6. 6 - The whole system is modular
  7. 7 - Going over the full algorithm
  8. 8 - What if an action fails?
  9. 9 - Debunking a marketing video :
  10. 10 - Experimental Results
  11. 11 - The insane scale of data collection
  12. 12 - How do you go about large-scale projects?
  13. 13 - Where did things go wrong?
  14. 14 - Where do we go from here?
  15. 15 - What is the largest unsolved problem in this?
  16. 16 - Thoughts on the Tesla Bot
  17. 17 - Final thoughts

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.