Subject:
|
Re: 2D positioning ???
|
Newsgroups:
|
lugnet.robotics
|
Date:
|
Thu, 9 Dec 1999 14:20:30 GMT
|
Original-From:
|
Tim Gion <TCG3J@CS.VIRGINIAsaynotospam.EDU>
|
Viewed:
|
619 times
|
| |
|
|
On Wed, 8 Dec 1999, michael yates wrote:
> Has anyone out there used an overhead mounted camera to do this sort of thing?
> Was it sucessful? We were reading about the roboCup soccer and the overhead
> camera thing was the method they used. However we are not sure what sort of
> resources (time and hardware) would be required to pull this level of image
> manipulation and calculations off.
I plan to try this myself once I test the robot controllers in simulation.
In "Reactive Visual Control of Multiple Non-Holonomic Robotics Agents,"
the CMU team says that they use a frame grabber with frame rate transfer
from a 3CCD camera. A 166mhz Pentium is used for the image processing.
I found this paper at
http://www.cs.cmu.edu/afs/cs/user/kwunh/www/pubs/visual-control.ps
I'm wondering how well one IR tower will communicate with multiple RCX's.
I haven't played with this yet as I haven't purchased the additional
equipment. Actually, I haven't played with the single RCX I have, at this
point. I plan on running all the controllers on a PC and beaming a
command stream each time step into the "play area." The command for each
individual robot will be preceded by its ID number.
Tim
Tim Gion
tcg3j@cs.virginia.edu (fastest) or gion@cs.virginia.edu
http://www.cs.virginia.edu/~tcg3j
|
|
Message is in Reply To:
 | | 2D positioning ???
|
| I realise this is an open ended question but I will ask anyhow. We (as I have mentioned a number of times, probably maing in RCX newsgroup) have 6 RCX's that we wish to make into a demo for school kids. Ideally that demo would involve some sort of (...) (25 years ago, 8-Dec-99, to lugnet.robotics)
|
8 Messages in This Thread:
 
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
