OpenAI specialists are trained AI system dexterity of human hands

Date:

2018-08-01 12:15:10

Views:

131

Rating:

1Like 0Dislike

Share:

OpenAI specialists are trained AI system dexterity of human hands

We are repeatedly surprised by the capabilities of the robotic company Boston Dynamics. However, recent developments of the nonprofit organization OpenAI, which occupies research in the field of artificial intelligence technology, even against Robo-dogs Boston Dynamics looks like a completely different, more advanced level. OpenAI presented Dactyl – s system, trained robotic arm. It would seem that what is there is impressive? Explain. Dactyl – is a system that allows the robotic arm to manipulate physical objects at a level previously unattainable any AI system. In the future the system will be able to give the robot physical parameter adroitness.

About the full level of dexterity of a robotic body, speech does not go yet, but engineers OpenAI finally laid the Foundation.

the

Sleight of hand and no fraud

Perhaps one of the finest instruments given to us by mother nature are hands. Human hands, nor any other, including the limbs of the most advanced apes, are capable of so finely controlled with your fingers. For robotic engineers are struggling to adapt with the dexterity of human hands in their iron protégé, but some obvious and important progress in this direction was not long ago.

Designed OpenAI system Dactyl is designed for, it would seem that the simplest tasks which even a child will cope. Is it difficult for us to pick up, say, a cube marked on each of its sides with drawings and turn it over to the right side? For us humans, this task is not difficult. For robot is a real torture. But thanks to powerful computers, the researchers were able to teach it that trick in just 50 hours.

the

the practice

Training system Dactyl took place in a simulated environment. To do this, engineers created a digital copy hands and put it in the computer environment, working on the principle of randomization. Engineers were asked a specific set of parameters for the environment (for example, the size of the cube, gravity), and then accidentally change these variables. For faster tutoring system researchers have created several of these virtual hands. Teaching Dactyl to adapt to a wide variety of possible scenarios in a virtual environment, the researchers gave the AI system experience required to adapt to the different scenarios of tasks in the real world.

After 50 hours of training inside among the virtual AI system learned to control the real robotic arm and performed 50 tasks set for it: to rotate a cube on one side or the other, not dropping it and completed the task in 80 seconds to solve a single task. In order to enable the system to "understand" which way to rotate the cube, it uses a set of cameras.

On your Dactyl, the developers explain that as the basis for a new system they applied the algorithm OpenAI Five, previously developed to create a team of 5 neural networks, capable of team play in DOTA 2. This digital brethren we will be able to see on the main cybercorner this year — The International 2018 held annually by the company Valve.

Efficiency Dactyl proves the possibility of creating a universal algorithm that can train an AI system on the performance of multiple tasks. The key benefit of this possibility is that in the future it will simplify and speed up the process of learning artificial intelligence systems, since developers do not have to create and train a new AI for solving various new problems.

Recommended

#video | the Company Boston Dynamics have trained your robot

#video | the Company Boston Dynamics have trained your robot "parkour"

Two years ago, the Boston Dynamics company has introduced a new generation of its two-legged humanoid robot Atlas. The updated version was the ability to walk on uneven surfaces, hop on one foot and even own up in the event of a fall. Furthermore, th...

The robot-snake learned how to climb a ladder

The robot-snake learned how to climb a ladder

Humanoid robots like Atlas from Boston Dynamics can jump over obstacles, and a robotic dog SpotMini without problems . Unfortunately, it is beyond the control of a ladder on which to climb using not only legs but also arms. While robots Boston Dynami...

Passengers on the Tokyo metro will help robots

Passengers on the Tokyo metro will help robots

no doubt, sooner or later robots will take any place in our society. Now going through the development of drones that could help people in the warehouses, in the production of various parts and so on. Successfully tested self-driving trucks and cars,...

Comments (0)

This article has no comment, be the first!

Add comment

Related News

Centauro: robot-centaur for the salvation of men

Centauro: robot-centaur for the salvation of men

the creation of robots, scientists and engineers are often inspired by nature. But robots based on mythical creatures meet not so often. And a new creation Centauro, name and appearance takes us back to the creatures Greek mytholo...

In Australia, divers were replaced by robots to protect reef

In Australia, divers were replaced by robots to protect reef

At the moment, researchers from the Australian Institute of Marine Science are testing drones and underwater robots to monitor the Great Barrier reef. Tests showed that in the future robots will be able to replace divers and to he...

The new control system drones was much the usual joystick

The new control system drones was much the usual joystick

nowadays, a variety of drones is no surprise, and if management is not standardized, it is certainly not much different between different models. However, the staff of the Federal Polytechnic school of Lausanne (Switzerland) have ...