Caricare documenti e articoli online è un sito progettato per cercare i documenti in vari tipi di file e il caricamento di articoli online.

Non ricordi la password?  ››  Iscriviti gratis




Cog is the newest and most ambitious robot developed by Rodney Brooks, scientist of MIT(Massachusetts Institute of Technology) Cog is a robot design to develop an artificial intelligence, it's the only machine of its kind in the United States. It has already "learned" some basic skills. For example 343f59d , it can reach its hand to a visual target and it can shake its head back and forth or nod up and down in imitation of a researcher.


The goal of researchers is to build a system that can operate in the same world we live in; so they base its design on "embodiment": the theory that people -- and robots -- need the form of the human body to shape human thoughts. "Our experience of the world is very constrained by our bodies."

A robot that looks like a human is also easier for people to interact with, and the researchers believe that such interactions are critical to Cog's development. "A child doesn't learn by sitting in a black box -- he learns by interacting with parents, caregivers and other people."

In keeping with embodiments, Cog was built with a human form; it consists of a torso with two arms, two hands, three degrees of freedom in the neck and the hips, and a computer brain modelled on human neuroanatonomy.

The scientist want Cog to have the ability to interact with humans in real sense, they don't want their robot to be aliens; Professor Brooks said that they'll know they have succeeded when the graduate students feel bad about switching off the robot.


Cog is not, however, pre-programmed for a given task. "That's fine for robots used in things like factory automation, where a car door appears in exactly the same location and there is exactly the same welding sequence. But it's not as useful if you're in an environment that changes, because once it changes, all the mathematics you went through for a specific task won't work."

The researchers use a variety of standard "learning" programs that allow Cog to learn by trial and error; so the robot can apply what it's learned to completing the same task under different conditions; for example with another pair of hand or with a new head.


Key to all these efforts is Cog's brain, which is composed of many sets of computers; each set of computers represents a different part of Cog's "nervous system." For example, the computers in one refrigerator-sized rack handle motor control. A part of the brain under construction -- Cog's "associative cortex" -- will allow the robot to do more complex, interactive behaviours.

Recently the researcher put a third generation of arms on the robot; conventional robot arms are so dangerous for humans to work around. They're programmed to move a certain way with a certain force, and if they hit an object that's in the way, they'll keep pushing. That can break the arm. In addition, if the abject in the way is you, a human, it could get messy.

Consequently, the arms developed by the Cog team are reactive to their environment. Among other things, if something gets on the way of an arm, it will stop moving. Depending on the task at hand, the arms can also be rigid or floppy.

Central to this work are a physical spring system and virtual spring software developed by Mr. Williamson. With the physical spring the arms can be compliant, stable, and withstand collision and shock loads without damage; the software allows the arms to work more like those of a human than those of a conventional robot.

Other parts of the robot are currently under development; include the ability for the face to be expressive.

Cog, however, will never have legs, because just solving the engineering of legs would take all of the time of the researcher; besides, they have enough things to study even without legs.


Articolo informazione

Hits: 1733
Apprezzato: scheda appunto

Commentare questo articolo:

Non sei registrato
Devi essere registrato per commentare


Copiare il codice

nella pagina web del tuo sito.

Copyright 2024