Apologies if I over-condensed the summary there, but my point doesn't really depend on exactly how you slice and dice the wording.
You don't need to be Castle, or to be a 'select company with RISC OS knowledge' (whatever that means), to produce potentially usable hardware - even if you allow ARM-based hardware only.
Any sufficiently skilled programmer can enhance the operating system. Yes, access to the existing codebase would help, but it isn't necessary.
Any sufficiently skilled programmer can help to plug some of the software gaps. Maybe not all of them, but some would be a good start.
To port the existing codebase to new hardware you would (quite possibly) need Castle's consent, but that is very different from requiring that they or an existing player take the initiative. (You do not, of course, have to use any or all of the existing codebase.)
In short, whatever you mean by "advancing RISC OS as a platform" there are options open to us. Some of them might even happen if we spent more time doing rather than complaining.