Developmental robotics: Difference between revisions

Revision as of 20:17, 20 September 2021

Revision as of 13:22, 9 January 2022

Line 9:

Can a robot learn like a child? Can it learn a variety of new skills and new knowledge unspecified at design time and in a partially unknown and changing environment? How can it discover its body and its relationships with the physical and social environment? How can its cognitive capacities continuously develop without the intervention of an engineer once it is "out of the factory"? What can it learn through natural social interactions with humans? These are the questions at the center of developmental robotics. Alan Turing, as well as a number of other pioneers of cybernetics, already formulated those questions and the general approach in 1950,<ref name="Turing50">{{cite journal

| last = Turing | first = A.M. | date = 1950 | url = http://www.csee.umbc.edu/courses/471/papers/turing.pdf | title = Computing machinery and intelligence | journal = Mind | publisher = LIX | issue = 236 | pages = 433–460 | volume=LIX| doi = 10.1093/mind/LIX.236.433 }}</ref>

but it is only since the end of the 20th century that they began to be investigated systematically.<ref name="Lungarella03">{{cite journal

| last1 = Lungarella | first1 = M. | last2 = Metta | first2 = G. | last3 = Pfeifer | first3 = R. | first4 = G. | last4 = Sandini | date = 2003 | title = Developmental robotics: a survey | citeseerx = 10.1.1.83.7615 | journal = Connection Science | volume = 15 | issue = 4 | pages = 151–190 | doi=10.1080/09540090310001655110| s2cid = 1452734 }}</ref><ref name="Asada09">{{cite journal