# Robots that Learn

## Метаданные

- **Канал:** OpenAI
- **YouTube:** https://www.youtube.com/watch?v=0iYxqo1_nJA
- **Дата:** 17.05.2017
- **Длительность:** 2:52
- **Просмотры:** 91,799

## Описание

Learn more: https://blog.openai.com/robots-that-learn/ // Originally on Vimeo: https://vimeo.com/217578517

Directed by: Jonas Schneider
Starring: Josh Tobin
Motion Graphics: Pomp & Clout LLC

## Содержание

### [0:00](https://www.youtube.com/watch?v=0iYxqo1_nJA) Intro

infants are born with the ability to imitate what other people do here a 10-minute old newborn sees another person stick their tongue out for the first time in response he sticks his own tongue out imitation allows humans to learn new behaviors rapidly we would like our robots to be able to learn this way too we've built a proof of concept system trained entirely in simulation we teach the robot a new task by demonstrating how to assemble block towers in a particular way which in this case is a single stack of six virtual blocks previously the robot has seen other examples of manipulating blocks but not this particular one our robot has now learn to perform the task even though its movements have to be different from the ones in the with a single demonstration of the task we can replicate it in a number of different initial conditions teaching the robot how to build a different block Arrangement requires only a single additional demonstration here's how our system

### [1:27](https://www.youtube.com/watch?v=0iYxqo1_nJA&t=87s) How it works

works the robot perceives the environment with its camera and manipulates the blocks with its arm at its core there are two neural networks working together the camera image is first processed by the vision Network then based on the recorded demonstration the imitation Network figures out what action to take next our vision network is a deep neural net that takes a camera image and determines the position of the blocks relative to the robot to train

### [1:51](https://www.youtube.com/watch?v=0iYxqo1_nJA&t=111s) Vision Network

the network we use only simulated data using domain randomization to learn a robust Vision model we generate thousands of different object locations light settings and service textures and show these examples to the network after training the network can find the blocks in the physical world even though it's never seen images from a real camera before now that we know the location of the blocks the imitation Network takes over its goal is to mimic the tasks shown by the demonstrator this neuronet is trained to predict what action the demonstrator would have taken in the same situation on its own it has learned to scan through the demonstration and pay attention to the relevant frames that tell it what to do next nothing in our technique is specific to blocks this system is an early prototype that will form the backbone of the general purpose robotic systems we're developing here at open AI

---
*Источник: https://ekstraktznaniy.ru/video/11633*