On Fri, Jan 2, 2009 at 11:28 PM, <scope_creep [..] ...> wrote:
> Hello,
> I'm new to this, so bear with me.
> I'm looking for software which can drive a sensor on a robot to detect many
> different types of plastics, from bottles, sheet, fragments, lying on the
> ground, in tree's, banks, hills. Anywhere on the ground.
> --------------------------------------
>
> I know that currenly their is no single detector which can detect the type
> of plastic from differentiating its physical properties.
> What I want to know, can the BFL be used, in combination with, say a vision
> system, to enable the defintion of what type of plastic, or indeed a step
> lower, to class a material, as being plastic, by using a combination of the
> BFL to classify it.

Let's say that, if you can write down the definitions mathematically
(probabilistically), BFL can be used for creating a Bayesian detection
algorithm.

> If that is the case, how would I get started?

That depends on your background. Are you familiar with Bayesian
probability theory?

> ---------------------------------------------
>
> The second part is what capabilities does the CDL have. Can it drive an
> autonomous robot
> across any landscape, or even a class lower, alongs beeches, flat land etc?

I guess you mean KDL here, and I leave the answer to the KDL people on
this list.

Klaas

> --
> Orocos-Users mailing list
> Orocos-Users [..] ...
> http://lists.mech.kuleuven.be/mailman/listinfo/orocos-users
>
> Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm
>
>