Subject:
|
Re: Design
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Sat, 3 Dec 2005 23:08:07 GMT
|
Viewed:
|
1670 times
|
| |
|
|
In lugnet.robotics, Mr S <szinn_the1@yahoo.com> wrote:
> 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 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
(perhaps better than their biological equivalent), but they don't mimic a
"creature"s senses.
The stuck behind the sofa problem might simplify if touch via hundreds or
thousands of individual sensors over the whole outer skin combined with hundreds
of sensors buried in every joint detecting stress could contribute toward an
external sensation of stuckness. I think that creatures that blunder into things
gain a huge advantage by having a "sensation" of how they're stuck.
Certainly, an RCX with 3 sensor inputs can never hope to model this. I have yet
to see a commercial robot design which comes close to providing the kind of
sensory input I think it will take to compete with nature's creepy crawlies,
although the military are working hard on "smart skins" for military vehicles to
help monitor damage.
JB
|
|
Message is in Reply To:
 | | Re: Design
|
| 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 (...) (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
|
|
|
|
