How do you drive-by-wire a car using Python ?

[igorcarron]

Hello everybody,

Our entry in the DARPA Grand Challenge race uses Python as a
programming language. For those of you who are interested, we are
beginning to put some of our code on our blog.

Before being autonomous, our vehicle (a four wheel drive Jeep) has to
first be driven by wire, i.e. use controls through a computer in order
to command the different steering, acceleration/braking actions.

This entry shows you the lighter version of the code we use to do this
drive-by-wire

http://pegasusbridge.blogspot.com/2005/05/how-do-you-drive-by-wire-car-using.html

(please note the disclaimer)

Cheers,

Igor.

 

[Tim Churches]

Hello everybody,

Our entry in the DARPA Grand Challenge race uses Python as a
programming language. For those of you who are interested, we are
beginning to put some of our code on our blog.

Here is a shot of a Pythonic DARPA Grand Challenge autonomous vehicle
pausing to do garbage collection:
http://www.shoalhaven.nsw.gov.au/council/sections/waste/images/garbage_truck_lifting_bin_1.jpg

Tim C

 

[igorcarron]

Please note we had to avoid trash cans when the DARPA folks came to
visit us. Our vehicle aims at being a garbage avoidance system instead


Igor.

 

[Cameron Laird]

Please note we had to avoid trash cans when the DARPA folks came to
visit us. Our vehicle aims at being a garbage avoidance system instead


Igor.

Python clearly is unsuitable for Grand Challenges, as I believe I once
heard someone in a hallway say that it doesn't properly release garbage
back to The System, and, anyway, it doesn't recognize every spelling for
garbage used in any other language. Python must be for weak girlie men.

 

[igorcarron]

Cameron,

Good point, I know you are a newbie . Let me help you out, just tell
the guy in the hallway that for the recognition of the spelling for
garbage in any other languages we use the zipfile module as pointed out
in
http://pegasusbridge.blogspot.com/2005/05/on-being-innovative-part-i.html
"...Using the Right Classification Approach

One of our approach to make classification of images for the purpose of
road following as well as obstacle avoidance is based on defining some
type of distance between drivable and non-drivable scenes. There are
many different projection techniques available in the literature. Let
us take the example of the "zipping-classifier" mechanism and how we
are using it for obstacle avoidance. This technique uses a compressor
like Winzip or 7-zip to produce some type of distance between files
(here images.) A very nice description of it can be read here...."

Hope this helps

Cheers,

Igor.