Subject:
|
Re: Design
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Sat, 3 Dec 2005 17:01:42 GMT
|
Original-From:
|
Mr S <szinn_the1@yahoo*saynotospam*.com>
|
Viewed:
|
1422 times
|
| |
|
|
Peter,
Carrying on from my last post, you are right, AI
research has done little despite its claims and
researchers. The mighty cockroach still defeats the AI
world. I don't think that is reason to despair, but
personally, I look at it as a reason to absorb what AI
research has done, then keep looking at it from
different angles until I see something different. I
hope its not seen as evil but for all the research
that has been done with subsumption architecture,
vision, etc. there just isn't any breakthroughs yet.
You, I believe, are right... at least how I see
things. We need to build a cockroach or ant type robot
that functions on its own, that can work in your
living room and not get stuck. It doesn't have to do
anything but explore and eat (recharge) and explore
some more. It just has to not get stuck. No matter how
you present this, it won't be a very popular contest
for clubs...
AI, itself, is not defined in terms that are easily
applied to a microcontroller. The more we learn about
human brains, the more we can understand that humans
preprocess data and stimulii before our brain actually
acts on it. There is a soft limit of about 7
concurrent tasks for humans. We have a good
understanding of how our vision works, yet none of the
AI research is leading to any kind of similar
implementation of those systems yet.
In fact, at the very basic level, the premise of
software/hardware design is (in my opinion)
incorrect. I tried to explain this next part on
another board very unsuccessfully, so I'll be brief
here.
That cockroach has a program running even when it is
sitting absolutely still. That program reacts to
environment even if the roach is not moving at all.
This is true of all living things. When we build
robots, that is the program that we leave out... we
simply program a linear set of events to react to a
single set of stimulus... that is what a contest is.
The programming has to have a basic loop that is
introspective, yet able to activate the programming
that interacts with the environment. Think of a cat or
dog resting... when our robots have that ability,
things will be different. Some have tried, but were
limited in what they could do because of hardware or
software.... FPGA and processor hardware is getting
smaller and cheaper by the week. Soon you will be able
to build hardware that previous robot builders could
only dream about. We'll see the ability to create
sophisticated hardware with much longer run times than
30 minutes. That's when you will be able to do more,
be more autonomous.
I agree that if you have a Lego Mindstorms, you are
free to experiment on the cutting edge... the trouble
is that the cutting edge is not pushing in the right
direction with the software and the basic premises of
that software.
Well, that is my opinion anyway.
--- PeterBalch <PeterBalch@compuserve.com> wrote:
It's apalling that AI robotics research has achieved
so little in the
last
40 years. New sciences usually achieve their most
spectacular
breakthoughs
when they're young but that simply hasn't happened in
AI robotics. It
isn't
as though AI needs lots of money. Physics or biology
or astronomy have
made
huge breakthoughs in that time even though they need a
billion-dollars-worth of telescope,
particle-accelerator or
DNA-sequencer.
With a bucket-full of lego and a desktop PC you can do
cutting-edge
research. Which is great news for people with Lego but
the AI
researchers
should hang their heads in shame.
__________________________________________
Yahoo! DSL – Something to write home about.
Just $16.99/mo. or less.
dsl.yahoo.com
|
|
Message has 1 Reply:
 | | Re: Design
|
| (...) I think there may be a fundamental reason why the commonplace research robot is unable to come close to the behaviour of the average housefly - sensor density. Most research robots have highly individual sensors, many of which are very good (...) (19 years ago, 3-Dec-05, to lugnet.robotics)
|
Message is in Reply To:
| | Re: Design
|
| Bruce (...) getting (...) Tee hee! I seem to have stirred things up a little :-) (...) These are extremely artificial environments. The problems are far easier to solve than the "getting stuck behind the sofa" problem. (Ask any AI researcher "how (...) (19 years ago, 3-Dec-05, to lugnet.robotics)
|
3 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
|
|
|
|
