Subject:
|
Re: Analysis of robot behaviours?
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Mon, 2 May 2005 21:11:58 GMT
|
Viewed:
|
1353 times
|
| |
|
|
In lugnet.robotics, Steve Hassenplug wrote:
> On Sun, May 1, 2005 12:42 pm, Johan Hjertman said:
> > But first little info about the robots. There are two robots, one is the prey (3
> > bump sensors, 1 rotation sensor) that just drive around and try to avoid things
> > and it has a lamp on it. The other one is the hunter(2 bump sensors and 2 light
> > sensors). It avoid things and try to follow the prey. ...
> >
> > My question is really how do I evaluate the robots behaviour after I´ve run the
> > program, so I can see if it helps for example if I change the learning rate for
> > the neural network or if I change the sensors position.
>
> I would think you'll want to run some controlled tests. For example, dis-connect
> the motors on the prey, and see how long it takes the hunter to "catch" it. Try
> several positions, then make your changes, and try the positions again, to see how
> that helps or hurts the result. (takes more or less time)
>
> Once you can see how changes affect the result, you'll be able to better understand
> how to evaluate it's behavior.
>
> Steve
Actually this is a bit of a minefield - the performance of your predator ANN
depends on your prey ANN and vice versa. You will have to run controlled tests
but I think the evaluation criteria is up to you - length of time to
intercept/avoid the prey/predator, efficiency of movement (a big deal in the
wild), whether the predator is getting the right time between 'feeds', which is
defined by you. Maybe you will have to run a series of tests. To evaulate the
predator, select and stick with the same ANN for the prey then prioritise the
predator criteria, assign each a weight and use this to give each ANN a score.
Thomas
|
|
Message is in Reply To:
 | | Re: Analysis of robot behaviours?
|
| On Sun, May 1, 2005 12:42 pm, Johan Hjertman said: (...) ... (...) I would think you'll want to run some controlled tests. For example, dis-connect the motors on the prey, and see how long it takes the hunter to "catch" it. Try several positions, (...) (19 years ago, 2-May-05, to lugnet.robotics)
|
6 Messages in This Thread:
 
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
