Tuesday, September 28, 2010

Detection of Objects in Messes

This looks like an interesting approach for practical object detection. However I think the generation of part models is going to be the biggest real world constraint. I not sure how effective this approach will be in the long term unless the PR2 is capable of generating the internal models from objects found in the environment as opposed to generating the part models in an automatic photo booth.

Considering the insanity of perpetual copyrights and the modern legal system, I'm not sure that it is possible to develop a system for sharing part models. Without a method for generating models in the field or a system for sharing part models I am not sure how this approach is going to scale up to the consumer level.

If I look at a copyrighted image, my memory isn't legally controlled by the copyright owner, I can use that memory to recognize objects without paying them, but a robot's memory of a copyrighted image may well be. Is the FFT of a trademark controlled by the trademark holder? Is it copyrightable? Robot lawyers may be needed in the near future to resolve this, though the route to personhood may be worked out for AIs, they apparently just need to incorporate.

More information on the ROS object recognition infrastructure can be found here. Though it is appears to be work in progress with limited documentation for generating your own part models and templates.


Robotbling said...

You bring up an interesting point about copyrights that I hadn't considered before. Having a database of company logos would certainly help in identifying the objects, but I'm guessing they could sue. Notice how TV shows these days tend to blur any corporate logos and even artwork that they don't own the rights to?

I Heart Robotics said...

Well part of that is probably that they want to get paid for the advertising.

INAL, but my biggest concern is that even data that is only machine readable may be effected by legal issues or the threat of legal issues.

Some bottle designs are trademarked or copyrighted so obviously 3D point cloud, of sufficient resolution to 3D print a copy, may not be covered by fair use. However, is there a one-way transform of the data that could be distributed without infringing?

If the robot generates and uses the data internally I believe it is covered under fair use, but who knows how it's going to play out.

Any lawyers want to chime in?

Can we distribute high resolution color 3D scans of C*ke cans or M*ckey M*use toys so our robots can recognize them, without getting sued several times?