Subject:
|
Re: Design
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Tue, 6 Dec 2005 15:04:25 GMT
|
Viewed:
|
1148 times
|
| |
|
|
In lugnet.robotics, PeterBalch <PeterBalch@compuserve.com> wrote:
> I believe we should emulate animal evolution by attempting to
> always situate them in the real world. We know that approach worked
> in the past.
I had a question from a student the other day (I teach Biophysics at a
university) who asked why engineering doesn't follow the same mechanism as
evolution (if evoution works so well, why not emulate it?). The brief answer is
becuse, for humans & technology, testing is expensive - either in terms of time
or actual resources. Evolution doesn't "care" - since testing is cheap (free),
evolution proceeds by trying absolutely every small variation, and then subjects
them to ruthless testing ("the good designs literally eat the bad designs").
Genetic/evolutionary techniques are great if you are testing in a virtual
world - they are dang labor intensive for actual hardware, as putting together
the hardware takes skilled labor (this is where biology has the advantage -
making offspring is a wonderful task for unskilled labor, and furthermore every
"robot" you test can do it ;-).
> Life evolved in water.
Life evolved in the water for very good biochemical and biological reasons,
that had nothing to do with processing power or "intelligence". Witness the fact
that even plants started in the water (and were also the first to invade land).
> Have we chosen a domain that's too hard?
No, but quite possible we're trying to jump a very very VERY large number of
steps by even trying to mobile AI. Keep in mind for much of the history of life
(& evolution) on Earth, the organisms were essentially non-mobile (unless you
consider floating). In some ways an aquatic enviroment is much easier - for
instance, gravity isn't an issue, *until* you start moving around or (heaven
forbid) making structures denser than water. Then it comes back in with a
vengence (bouancy & stability).
> The standard biological excuse is to do with dessication
> and UV but maybe land is very much harder for
> locomotion. Maybe we're trying to walk before we can swim.
The biological "excuse" is pretty well founded when you look at the large
number of physical modifications that crossing between land & water (either
way!) engender. Moreover, I things like bouancy (a true 3-D world, not a
"flattened" land-based one) or currents (on land I generally stay where I am
when I stop) make for a very different (perhaps harder) problem.
--
Brian Davis
|
|
Message has 1 Reply:
 | | Re: Design
|
| (...) There are many answers to that. One is that evolution *IS* used in some fields of engineering. Genetic algorithms have been used in many situations. I myself have used a genetic algorithm to develop a program that can recognise buildings in (...) (19 years ago, 7-Dec-05, to lugnet.robotics)
|
Message is in Reply To:
| | Re: Design
|
| (...) space (...) I think that the whole AI community was chastened by SHRDLU (or, at least, 99.9% of them were). It seemed like a huge success: "Why did you clear off the blue cube?" "To put the red pyramid on top of it." It looked like a real (...) (19 years ago, 6-Dec-05, to lugnet.robotics)
|
5 Messages in This Thread:
  
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
