Subject:
|
Re: Analysis of robot behaviours?
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Sun, 1 May 2005 11:38:14 GMT
|
Viewed:
|
1007 times
|
| |
|
|
In lugnet.robotics, Johan Hjertman wrote:
> How do I analysea the robot behaviors and
> how can compare the results?
Generally, with a neural network, just write an evaluation function that
generates a number and use that as your "standard"
> Is there "standardize" way of doing it?
What is considered important here for a "successful" result? Speed ("the
faster a find a bright light the better")? Accuracy ("the more precisely I can
point towards the bright light the better")? Flexibility ("don't get stuck in a
corner")?
> One important factor for "following the light"
> behavior is for example the positions of the light
> sensors.
Use one that you think is likely to be good, and go from there. Or, more
interestingly, have the light sensors positioned on a structure that the robot
can adjust, and have the neural network optimize this too.
How are you coding the neural network? Standard firmware, custom firmware, or
is it all done on a remote system and the LEGO robot is just a dumb front-end?
--
Brian Davis
|
|
Message has 1 Reply:
 | | Re: Analysis of robot behaviours?
|
| Hi Brian, Thx alot for the reply!! I´m sorry. I was so........ unclear. So I will try to explain the problem again. But first little info about the robots. There are two robots, one is the prey (3 bump sensors, 1 rotation sensor) that just drive (...) (19 years ago, 1-May-05, to lugnet.robotics)
|
Message is in Reply To:
| | Analysis of robot behaviours?
|
| Hi all!! This is maybe a little off topic, but maybe some one can help me here. I´m building a lego robot that learns how to avoid things and to follows a lamp. For the brain I use ANN (=Artificial Neural Network). So it learns how to solve the (...) (19 years ago, 30-Apr-05, to lugnet.robotics)
|
6 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
|
|
|
|
