A password will be e-mailed to you.

Robots struggle with tasks that involve dexterity

This problem could soon be solved.

6 August, 2018 

In a blog released their website this week OpenAI revealed the latest version of their OpenAI Five learning algorithm that they’ve now wrapped into a system called “Dactyl” which lets them train robots in new ways and without the need to use “physical based modelling.” The result, when combined with the Shadow Dexterous Hand, which you can see in the video below, is a robot hand that can manipulate objects with near human-like dexterity.

“We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity,” reads the non-profit’s blog.

OpenAI explained that Dactyl is trained entirely within a virtual simulated environment and successfully adapts that acquired knowledge into the real world.

During their experiments the researchers place a block in the palm of the robotic hand and order Dactyl to reposition it. Dactyl then processes the hand’s fingertip coordinates and images from three cameras positioned around it and elegantly twirls the block around. The resulting motion is eerily human-like.

Robotic humanoid hands were first introduced decades ago but traditional robotics techniques have so far proved ineffective in coming up with solutions to help them manipulate objects efficiently so OpenAI decided to use domain randomization, a process created by the lab to solve the difficulties related to transferring simulated experiences into the real world referred to as the reality gap to come up with a new approach.

Instead of training a model on a single simulated environment, domain randomization exposes it to a wide range of environments in a simulation designed with many experiences, and bingo, they had a winner.




No more articles
Send this to a friend