a history of cybernetic animals and early robots
Early learning machines designed to solve a maze
In 1952, Richard A. Wallace built a Maze Solving Computer as a model of "machine learning". His definition of learning is "The ability to modify a response to a stimulus because of past experience with the stimulus." see full pdf here.
The Thomas Ross Maze Learning Machine showing its feeler tracking the slots of this comb-shaped maze. See complete Scientific American 1933 article titled "Machines That Think" – pdf here.
Maisie the Robot (c1977) with David Strange. From a comment below, David Strange informs me that the robot he called Maizie was a maze solving robot whilst he was working for the BBC Open University. It was used in several programmes on cognitive psychology. Thanks David. From further correspondence with David (Dec 2015): The whole of …
Read More “1977 – “Maizie the Robot” – David Strange (British)”
A Machine Capable of Being Conditioned Joseph R. Cautela; Harutune Mikaelian The American Journal of Psychology, Vol. 76, No. 1. (Mar., 1963), pp. 128-134. RH2009-Its interesting to note that in the introduction is says "type of conditioned reflex machine developed by Slukin, who tells of a machine that was conditioned to respond to a whistle …
Read More “1963 – Conditioned Cybernetic Machine – Cautela and Mikaelian (American)”
The diagrammatic view of the 1950-1 Maze-solving Mouse built by Claude A. Shannon. Claude Shannon knew Edmund C. Berkeley quite well. Berkeley had two young associates working part-time with him on his early robots, by the names of Ivan and Bert Sutherland. Ivan was soon to have Claude Shannon as his Thesis supervisor. Berkeley was keen …
Read More “1950 – Maze-Solving Mouse – Claude Shannon (American)”