Subject:
|
Re: Design
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Wed, 7 Dec 2005 02:05:57 GMT
|
Original-From:
|
steve <{sjbaker1@}AntiSpam{airmail.net}>
|
Viewed:
|
1170 times
|
| |
|
|
Brian Davis wrote:
> 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.
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 satellite photographs. The result was better than my best hand-coded
solution - and *much* better than the best trained neural network I
could come up with.
The other answer is that you don't usually get what you want - only
something that is what you told it to be...that's not always the same
thing!
A good example here (in an admittedly 'toy' world) was of a guy who
wrote a careful simulation of a simple 'world' and had creatures made
of blocks that were formed from 'genes' and brains that were made from
simple subroutines - also formed from genes.
He set up his world - setting up his 'evolutionary' system to allow
the creatures that moved the fastest to survive and to breed the next
generation - whilst the slowest creatures were killed off. His
criteria was to race the creatures. The first to cover a certain
distance (or the one that get closest to the line if neither makes
it within a certain time) was the winner.
His first effort ran for a bazillion generations.
He'd hoped for some kind of interesting locomotion to 'just evolve'.
What actually happened was that his creatures evolved into enormously
tall blocks with no brains whatever. All they did was to fall over.
However, being so enormously tall, when they fell over, they crossed
the finish line - and thereby out-evolved any possible elegant walking
machine!
He patched up his algorithm in a variety of ways - but each time,
his creatures would evolve into some totally un-interesting form
that would win by exploiting loopholes in his testing scheme.
He even ended up with creatures that collected energy by exploiting
bugs and roundoff errors in his physics simulation! For those
virtual creatures, roundoff error was as natural a resource as
grass is to cows...so they learned to exploit it.
This isn't a good way to do engineering. You can't just specify
simple goals and expect to get a super-sophisticated machine that
does what you actually *wanted* - typcially, all you get is something
that meets your goals in some annoying and totally useless way!
> 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 ;-).
There have been some cases where evolutionary design has worked in the
real world...but you're right - it's not an automatic win.
|
|
Message has 1 Reply:
 | | Re: Design
|
| --- steve <sjbaker1@airmail.net> wrote: ... (...) This is fascinating stuff -- did the fellow publish? Any pointers to his work would be greatly appreciated. It ties in directly with some research I've been doing on reversible physics and (...) (19 years ago, 7-Dec-05, to lugnet.robotics)
|
Message is in Reply To:
| | Re: Design
|
| (...) 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 (...) (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
|
|
|
|
