Subject:
|
Obstacles avoiding -Reply
|
Newsgroups:
|
lugnet.robotics.handyboard
|
Date:
|
Mon, 5 Apr 1999 15:59:40 GMT
|
Original-From:
|
wengd@+nospam+optionshealthcare.com
|
Viewed:
|
1044 times
|
| |
|
|
The idea behind a reactive (behavior based) architecture of a Rug
Warrior robot is essentially stateless. You may want to add some kind of
schedule or activation layer (process ) that enables the low level
behaviors based on some type of state or map information. A book from
MIT Press call BEHAVIOR BASED ROBOTICS is an excellent source book
on behavior and hybrid robot architectures.
-Drew
> > > "emiel.agema@multiweb.nl" 04/04/99 04:12pm >>>
Hello,
I would like to know if there is anyone who has a good idea to avoid
obstacles in a intelligent way.
I've build a Rugwarrior robot.
My robot has two IR proximity detectors (in front) and four bump
switches (one on each side). If you simple build in a reflex which will act
every time the same, e.g. bump front will cause the robot to move
backward and go left, it will be not enough. At one moment the robot
needs to know was happend some time before. You need some history
of all the sensors, to avoid getting in a loop when the robot is in a corner
of a room/field.
Any ideas I like to know to solve this problem.
Greetings Emiel
|
|
1 Message in This Thread:
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
