Cognitive robotics: Difference between revisions

Revision as of 05:45, 2 August 2025

Latest revision as of 05:48, 2 August 2025

(3 intermediate revisions by the same user not shown)

Line 1:

{{more footnotes|date=February 2012}}

'''Cognitive Roboticsrobotics ''' or '''Cognitivecognitive Technologytechnology''' is a subfield of [[robotics]] concerned with endowing a robot with intelligent behavior by providing it with a processing architecture that will allow it to [[Robot learning|learn]] and reason about how to behave in response to complex goals in a complex world. Cognitive robotics may be considered the engineering branch of [[embodied cognitive science]] and [[embodied embedded cognition]], consisting of [[Roboticrobotic Processprocess Automationautomation]], [[Artificialartificial Intelligenceintelligence]], [[Machinemachine Learninglearning]], [[Deepdeep Learninglearning]], [[Opticaloptical Charactercharacter Recognitionrecognition]], [[Imageimage Processingprocessing]], [[Processprocess Miningmining]], [[Analyticsanalytics]], [[Softwaresoftware Developmentdevelopment]] and [[Systemsystem Integrationintegration]].

==Core issues==

While traditional [[cognitive model]]ing approaches have assumed symbolic coding schemes as a means for depicting the world, translating the world into these kinds of symbolic representations has proven to be problematic if not untenable. [[philosophy of perception|Perception]] and [[motor cognition|action]] and the notion of [[Mental representation|symbolic representation]] are therefore core issues to be addressed in cognitive robotics.

==Starting point==

Cognitive robotics views human or animal cognition as a starting point for the development of robotic information processing, as opposed to more traditional [[artificial intelligence]] techniques. Target robotic cognitive capabilities include perception processing, attention allocation, [[anticipation (artificial intelligence)|anticipation]], planning, complex motor coordination, reasoning about other agents and perhaps even about their own mental states. Robotic cognition embodies the behavior of [[intelligent agent]]s in the physical world (or a virtual world, in the case of simulated cognitive robotics). Ultimately, the robot must be able to act in the real world.

==Learning techniques==

Line 16:

{{main|Motor babbling}}

A preliminary robot learning technique called [[motor babbling]] involves correlating pseudo-random complex motor movements by the robot with resulting visual and/or auditory feedback such that the robot may begin to ''expect'' a pattern of sensory feedback given a pattern of motor output. Desired sensory feedback may then be used to inform a motor control signal. This is thought to be analogous to how a baby learns to reach for objects or learns to produce speech sounds. For simpler robot systems, where, for instance, [[inverse kinematics]] may feasibly be used to transform anticipated feedback (desired motor result) into motor output, this step may be skipped.

===Imitation===

Line 26:

A more complex learning approach is "autonomous [[knowledge acquisition]]": the robot is left to explore the environment on its own. A system of goals and beliefs is typically assumed.

A somewhat more directed mode of exploration can be achieved by "curiosity" algorithms, such as Intelligent Adaptive Curiosity<ref>http://www.pyoudeyer.com/ims.pdf {{Bare URL PDF|date=March 2022}}</ref><ref>http://www.pyoudeyer.com/oudeyer-kaplan-neurorobotics.pdf {{Bare URL PDF|date=March 2022}}</ref> or Category-Based Intrinsic Motivation.<ref>http://science.slc.edu/~jmarshall/papers/cbim-epirob09.pdf {{Bare URL PDF|date=March 2022}}</ref> These algorithms generally involve breaking sensory input into a finite number of categories and assigning some sort of prediction system (such as an [[Artificialartificial Neuralneural Networknetwork]]) to each. The prediction system keeps track of the error in its predictions over time. Reduction in prediction error is considered learning. The robot then preferentially explores categories in which it is learning (or reducing prediction error) the fastest.

==Other architectures==

Line 33:

==Questions==

Some of the fundamental questions to still be answered in cognitive robotics are:

Some of the fundamental questions to still be answered in cognitive robotics are:

* How much human programming should or can be involved to support the learning processes?

* How can one quantify progress? Some of the adopted ways is theare reward and punishment. But what kind of reward and what kind of punishment? In humans, when teaching a child, for example, the reward would be candy or some encouragement, and the punishment can take many forms. But what is an effective way with robots?{{Citation needed|date=August 2019|reason=It seems that this passage contains confusion about reinforcement learning, a citation to a source that shows how to use 'reward and punishment' for 'progress quantification' is needed.}}

== Books ==

Cognitive Robotics book <ref>{{Cite web|title = Cognitive Robotics|url = https://www.crcpress.com/Cognitive-Robotics/Samani/9781482244564|website = CRC Press|accessdate = 2015-10-07}}</ref> by Hooman Samani,<ref>{{Cite web|title = Hooman Samani|url = http://www.hoomansamani.com/|website = www.hoomansamani.com|accessdate = 2015-10-07}}</ref> takes a multidisciplinary approach to cover various aspects of cognitive robotics such as artificial intelligence, physical, chemical, philosophical, psychological, social, cultural, and ethical aspects.

==See also==

Line 57 ⟶ 53:

== References ==

{{Reflist}}

== BooksSources ==

*[https://web.archive.org/web/20090314232056/http://www.ss-rics.org/ The Symbolic and Subsymbolic Robotic Intelligence Control System (SS-RICS)]

*[https://web.archive.org/web/20060617202124/http://www.cs.uu.nl/groups/IS/robotics/robotics.html Intelligent Systems Group - University of Utrecht]