Subject:
|
Re: Bump switches and "aggression"
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Wed, 3 Dec 2003 15:57:53 GMT
|
Viewed:
|
1845 times
|
| |
|
|
In lugnet.robotics, Jim Choate <ravage@einstein.ssz.com> wrote:
>
> The current approach I'm looking for is to model the 'fight or flight'
> behavior and this seems like a prime candidate. I also see it as being
> very compatible with subsumption architecture and nervous network
> approaches, which I think is critical.
>
> To my thinking there are two approaches to this, really too levels of
> difficulty,
>
> - Make it deterministic, in that if a switch is bumped invert your
> current trajectory axis, if going forward then reverse, if going R
> then go L.
>
> - Make it more stochastic. The first choice when a bump switch goes off
> is whether to stop, reverse your current trajectory, or select a random
> trajectory.
>
> I believe the second level provides a pretty good simulation to the 'fight
> or flight' approach by extending it to cover 'camouflage' strategies which
> are quite prevelant in biological systems. Take rabbits for example, they
> are sensitive to ground vibration. They generaly have two strategies
> (assuming they aren't in heat) freeze (ie stop) or run in a (semi-)random
> direction (ie zig-zag).
How exactly, do you want to trigger this 'fight or flight'?
It seems to me that a rabbit (for example) would use both of the methods above.
If it's running along, and it's nose smacks into a tree (I mean bumps into a
tree) the behavior is very deterministic. Invert (or change) trajectory.
That's using it's nose sensor.
But, if it detects ground vibration, or possibly a noise from an unknown
direction, that is when the 'fight or flight' kicks in. At that point, the
'danger' is coming from an unknown direction, so the response CAN NOT be
deterministic.
In fact, it seems to me (no scientific basis for this assumption) that a rabbit
would respond different to noise than to vibrations. Noise=freeze,
vibration=run.
So, I think modeling that behavior may require several methods of triggering it.
For example: 1) touch sensors (as you've suggested) for normal navigation and 2)
tilt/acceleration/angle sensor(s) to detect movement which is not consistant
with programmed navigation.
One simple method for option 2 is to have a free hanging pendulum, which in it's
neutral state, presses a touch sensor.
Just some ideas
Steve
|
|
Message has 1 Reply:
 | | Re: Bump switches and "aggression"
|
| (...) Easy the bump switch jumps into a RNG, and it's important to understand that the output of a RNG does -not- need to be equi-probable, and it decides. Watch animals when they're startled, they don't stop and think, they jump around for a second (...) (21 years ago, 3-Dec-03, to lugnet.robotics)
|
Message is in Reply To:
| | Bump switches and "aggression"
|
| I mentioned a 'reference platform' for the H18 group I've been working on in a previous post, and I'm curious if anyone will share their views on how they view bump switches and 'behavior'. I'm not interested in a debate but rather a 'collection'. (...) (21 years ago, 3-Dec-03, to lugnet.robotics)
|
60 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
|
|
|
|
