Home > News > Daily News > Through trial and error robot can learn new skills
News
Daily News
Industry News
Company news
Certifications
Latest News

Gifts of love in ancient China

Jade pendants The ancient Chinese usually gave their lovers something small so that they could easily take it everywhere. A jade pendant is a good cho...

what is mild steel

Mild steel is a type of carbon steel with a low amount of carbon – it is actually also known as “low carbon steel.” Although ranges vary depending ...

10 Differences between a Businessman and Entrepreneur

10 Differences between a Businessman and Entrepreneur Business people and entrepreneurs have many similarities.However, they are not the same kind of ...

What is ALOCROM 1200 surface treatment

What is ALOCROM 1200surface treatment Alocrom 1200 is a rapidnon-electrolytic dip process which gives excellent protection against corrosionto both pa...

What is Kydex material

What is Kydexmaterial Kydex is a line of thermoplasticacrylic-polyvinyl chloride materials manufactured by Sekisui SPI. It has a widevariety of applic...

What is Over mold?

Overmolding is also called 2 times injection molding in China. Compared with the third-party material bonding, overmolding process makes the process f...

What is Alodine 5200 surface treatment

What is Alodine 5200surface treatment Alodine 5200 treatment is a chromiumfree product and specifically formulated for treating aluminium and its allo...

What is Black Oxide?

Black Oxide, blackening, oxidizing, oxiding, black passivating, gun bluing . . . these terms all refer to the process of forming a black iron oxide on...

How and When to Add Bend Reliefs to Sheet Metal Parts

What is a Bend Relief? A bend relief is nothing more than two small incisions cut into a piece of sheet metal to free the metal between the two. It se...

Privacy Policy

We will not collect and store your information in any form.
Contact Us
Vice General Manager: Ivy
Tel:86-13312953695
Tel:86-755-82737317/82737469
Fax:86-755-82737710
E-mail: sales910@xy-global.com, sales.china@xy-global.com
Postal Code: 518129
Off Add: Room1702,17F,Building#4,Tianan Cloud Park,No.2018 Xuegang Rd.,Longgang District,Shenzhen.
Factory Add:Daling Industrial Area,Shaling,Fenggang Town,Dongguan City Contact Now

Through trial and error robot can learn new skills

Through trial and error robot can learn new skills

naky www.diecastingpartsupplier.com 2015-05-26 18:27:23
Researchers at the University of California, Berkeley, have developed algorithms that enable robots to learn motor tasks through trial and error using a process that more closely approximates the way humans learn, marking a major milestone in the field of artificial intelligence. They demonstrated their technique, a type of reinforcement learning, by having a robot complete various tasks -- putting a clothes hanger on a rack, assembling a toy plane, screwing a cap on a water bottle, and more -- without pre-programmed details about its surroundings. 
 
"What we're reporting on here is a new approach to empowering a robot to learn," said Professor Pieter Abbeel in UC Berkeley's Department of Electrical Engineering and Computer Sciences. "The key is that when a robot is faced with something new, we won't have to reprogram it. The exact same software, which encodes how the robot can learn, was used to allow the robot to learn all the different tasks we gave it." 
 
The latest developments will be presented on Thursday, May 28, in Seattle at the International Conference on Robotics and Automation (ICRA). Abbeel is leading the project with fellow UC Berkeley faculty member Trevor Darrell, the director of the Berkeley Vision and Learning Center. Other members of the team are postdoctoral researcher Sergey Levine and Ph.D. student Chelsea Finn.
 
The work is part of a new People and Robots Initiative at UC's Center for Information Technology Research in the Interest of Society (CITRIS). The new multi-campus, multidisciplinary research initiative seeks to keep the dizzying advances in artificial intelligence, robotics and automationaligned to human needs. 
 
"Most robotic applications are in controlled environments where objects are in predictable positions," said Darrell. "The challenge of putting robots into real-life settings, like homes or offices, is that those environments are constantly changing. The robot must be able to perceive and adapt to its surroundings."

Following is our company detail:Our factory has specilized in the die is cast meaning buy die cast modelsdie cast army
die cast promotionsdie cast metal for many year since 2002. And our products are always well received and approved by our customers from Asian, European, North American and Australian etc.