# Transferring AI To The Real World (OpenAI) | Two Minute Papers #202

## Метаданные

- **Канал:** Two Minute Papers
- **YouTube:** https://www.youtube.com/watch?v=mmeoUZ_wRm4
- **Дата:** 02.11.2017
- **Длительность:** 2:37
- **Просмотры:** 22,321

## Описание

The paper "Domain Randomization for Transferring Deep Neural  Networks from Simulation to the Real World" is available here:
https://arxiv.org/pdf/1703.06907.pdf

We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Andrew Melnychuk, Brian Gilman, Christoph Jadanowski, Dave Rushton-Smith, Dennis Abts, Eric Haddad, Esa Turkulainen, Evan Breznyik, Kaben Gabriel Nanlohy, Malek Cellier, Michael Albrecht, Michael Jensen, Michael Orenstein, Steef, Steve Messina, Sunil Kim, Torsten Reil.
https://www.patreon.com/TwoMinutePapers

Two Minute Papers Merch:
US: http://twominutepapers.com/
EU/Worldwide: https://shop.spreadshirt.net/TwoMinutePapers/

Music: Antarctica by Audionautix is licensed under a Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/)
Artist: http://audionautix.com/ 

Thumbnail background image credit: https://pixabay.com/photo-2874016/
Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu

Károly Zsolnai-Fehér's links:
Facebook: https://www.facebook.com/TwoMinutePapers/
Twitter: https://twitter.com/karoly_zsolnai
Web: https://cg.tuwien.ac.at/~zsolnai/

## Содержание

### [0:00](https://www.youtube.com/watch?v=mmeoUZ_wRm4) Segment 1 (00:00 - 02:00)

dear fellow scholars this is two minute papers with károly on IFA here in this series we talk a lot about different AI algorithms and solve a variety of super difficult tasks these are typically tested within a software environment in the form of a simulation program however this often leaves the question open whether these algorithms would really work in real-world environments so what about that this work from open AI goes by the name domain randomization and is about training in AI and relatively crude computer simulations in a way that can be transferred to the real world the problem used to demonstrate this was localizing and grasping objects note that this algorithm has never seen any real images and was trained using simulated data it only played a computer game if you will now the question we immediately think about is what the term domain randomization has to do with transferring simulation knowledge into reality the key observation is that using simulated training data is okay but we have to make sure that the AI is exposed to a diverse enough set of circumstances to obtain knowledge that generalizes properly has the term domain randomization in these experiments the following parameters were heavily randomized number of shapes and distractor objects on the table positions and textures on the objects table and the environment number of lights material properties and the algorithm was even exposed to some random noise as well in the images and it turns out that if we do this properly leaning on a knowledge of only a few thousand images when the algorithm is uploaded to a real robot arm it becomes capable of grasping the correct proscribed objects in this case the objective was spam detection very amusing I think the very interesting part is that it is not even using photorealistic rendering and light simulations these programs are able to create high quality images that resemble the real world around us and it is mostly clear that those would be useful to train such an algorithm however this only uses extremely crude data and the knowledge of the AI still generalizes to the real world how about thanks for watching and for your generous support and I'll see you next time

---
*Источник: https://ekstraktznaniy.ru/video/14564*