Talk:Cognitive robotics

From Wikipedia, the free encyclopedia

	Cognitive robotics is within the scope of WikiProject Robotics, an attempt to standardise coverage of Robotics. If you would like to participate, you can edit the article attached to this notice, or visit the project page, where you can join the project or contribute to the discussion.
???	This article has not yet received a rating on the Project's quality scale. Please rate the article and then leave a short summary here to explain the ratings and/or to identify the strengths and weaknesses of the article.
???	This article has not yet received an importance rating on the importance scale.

[edit] No sources?

Any ideas on finding further inforamtion on cognitive robotics? -- kanzure 04:30, 11 January 2006 (UTC)

The distinction between all the terms under "see also" are so vage than I am not even so sure that the deffinition given is correct. (It is worth looking at all of them.) If it is, the references at intelligent agent would be a good start. Only a view universities label their AI robotics work as such. I'll add the one where I got the def from. I don't really think the work at these instututes differs anything from that at places working on evolutionary/developmental/epigenetic robotics. Please add if you find anything. I am now starting research in this field so I might have so to come soon :) --moxon 06:18, 11 January 2006 (UTC)

Indeed. These fields seem to be defined poorly, especially in the boundaries / directions of progress. Is this a coincidence, or is this really how these fields actually work? -- kanzure 03:24, 12 January 2006 (UTC)

To me it seems that these terms are made up by these instututions to try and distinguish themselfs and their work (but with no formal deffinition by which to limit themselfs). Many of these terms are borrowed from psychology (cognitive psychology, developmental psychology, evolutionary psychology etc.), Their definition are a bit better defined, but in terms of robotic as far as i could gather: cognitive >> lifetime learning; evolutionary >> populations and generations of robots; developmental >> emergence of complexity; epigenetic >> out of nothing. --moxon 08:22, 13 January 2006 (UTC)

Although that might be classified as original research, that type of distinction between the fields on a page would be helpful to passer-bys. I suggest Robotics, or Artificial Intelligence; either of those articles. -- kanzure 13:37, 24 January 2006 (UTC)

That progression does indeed sound like far-fetched speculative research. The real-world field of "robot cognition" is far more broad than the anthropocentric concept of "android cognition" and "android self-socialization", for example, the various robots which we've sent into space over the past few decades, and their ever-increasingly sophisticated kin operate completely devoid of human contact (outside of receiving programming). Unfortunately, there's even less apparent research around the (IMO more apt) term "robot cognition" (only ~600 Google hits compared with over ~50,000 for "cognitive robotics") . --sydhart 05:00, 6 March 2006 (UTC)

This entire article looks like far-fetched speculative research. What's the line between "speculative research", pseudoscience, protoscience, and NPOV? -- 24.153.226.112 20:44, 6 March 2006 (UTC)

My understanding of cognitive robotics, and I added this to the main page, was that it draws upon human psychological principles as a starting point for algorithm development and makes a point of NOT using some of the more traditional AI approaches to memory storage and knowledge representation. So, for example, memory decay might seem to some robotics researchers as a problem, or a poor system design, but it would be embraced by cognitive roboticits as an essential component of the robotics system since it is an essential component of the human cognitive system.Doghouseman 21:16, 2 November 2007 (UTC)

[edit] NPOV ?

I have reverted the redirect. If anything, it should not redirect to Strong AI, which takes you to a wanm debate on the definition of intelligence. While the title might be deceiving, the definition indicates something far from speculative: the creation of continuously and autonomously learning, interactively exploring and adapting, physical real-world robots. This is an engineering science, a progressive modern outflow of the long time established field of cybernetics, focusing on adaptability. --moxon 17:40, 16 March 2006 (UTC)

[edit] Relations

Which are the relations with developmental robotics and evolutionary robotics?. Concepts are better drawn when one can see the differences with related ones--Altermike 07:45, 7 April 2007 (UTC)