Implement a cast_to_float method for convenience; at a cost of a couple of bytes in the vtable this will save many callers having to play type introspection games.
It might be possible to implement a set of virtual cast operator overrides, but only float lets us return NAN to indicate that a cast can't be made, so for now we'll stick with just this one.
git-svn-id: https://arducopter.googlecode.com/svn/trunk@1614 f9c3cf11-9bcb-44bc-f272-b75c42450872