OpenAI’s Robots Learn From Humans In VR

Teaching robots complex tasks is going to be much easier in the future. There are already various methods to do it. OpenAi has developed a robotic system that allows robots to learn from humans by just watching tasks done in a VR environment. The  one-shot imitation learning allows humans to show new tasks to robots.

The system is powered by two neural networks: a vision and an imitation network. Here is how it works:

The vision network ingests an image from the robot’s camera and outputs state representing the positions of the objects. The imitation network observes a demonstration, processes it to infer the intent of the task, and then accomplishes the intent starting from another starting configuration. The network learns this from the distribution of training examples. It is trained on dozens of different tasks with thousands of demonstrations for each task. Each training example is a pair of demonstrations that perform the same task.

More info is available here.

*some of our articles have aff links. Please read our disclaimer on how we fund Exxponent.
Read more:
Neurocam: Brainwave-Reading Camera

Cameras are getting better and smarter all the time. But the Neurocam is at another level. This is a wearable...

Apple To Charge $400 for the iWatch

Apple is expected to unveil its first smartwatch on September 9. The device won't be shipping until early 2015, but...

Beddit 3 Smart Flexible Sleep Tracker

Here is another sleep tracker that helps you better understand your sleeping patterns and what affects your sleep quality. The...

Close