Open AccessAcquisition of a space representation by a naive agent from sensorimotor invariance and proprioceptive compensation
Author(s) -
Gurvan Le Clec’H,
Bruno Gas,
J. Kevin Ο’Regan
Publication year - 2016
Publication title -
international journal of advanced robotic systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.394
H-Index - 46
eISSN - 1729-8814
pISSN - 1729-8806
DOI - 10.1177/1729881416675134
Subject(s) - representation (politics) , a priori and a posteriori , space (punctuation) , contingency theory , computer science , contingency , internal model , compensation (psychology) , simple (philosophy) , mathematics , artificial intelligence , psychology , control (management) , social psychology , epistemology , politics , knowledge management , philosophy , law , operating system , political science
International audienceIn this article, we present a simple agent which learns an internal representation of space without a priori knowledge of its environment, body, or sensors. The learned environment is seen as an internal space representation. This representation is isomorphic to the group of transformations applied to the environment. The model solves certain theoretical and practical issues encountered in previous work in sensorimotor contingency theory. Considering the mathematical description of the internal representation, analysis of its properties and simulations, we prove that this internal representation is equivalent to knowledge of space
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom