Open AccessONTOGENETIC TEACHING OF MOBILE AUTONOMOUS ROBOTS WITH DYNAMIC NEUROCONTROLLERS
Author(s) -
Helmut A. Mayer
Publication year - 2014
Publication title -
computing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.184
H-Index - 11
eISSN - 2312-5381
pISSN - 1727-6209
DOI - 10.47839/ijc.3.1.251
Subject(s) - robot , computer science , hebbian theory , mobile robot , artificial intelligence , evolutionary robotics , robotics , robot learning , focus (optics) , artificial life , simple (philosophy) , work (physics) , behavior based robotics , artificial neural network , human–computer interaction , engineering , mechanical engineering , philosophy , physics , epistemology , optics
After a brief survey of work dealing with dynamic neurocontrollers changing their internal structure during the “lifetime” of a mobile autonomous robot, we present experiments employing a standard sensor–motor neurocontroller with self–adapting weights. The change of behavior of the robot is linked to inputs from the environment that cause the emission of artificial neuromodulators (ANMs) in the robot’s neurocontroller. In its simplest form an outside teacher (human or machine) constantly evaluates the robot’s actions by transmitting positive or negative feedback signals to the robot initiating the internal changes. The focus of investigations is put on the mechanisms of the interaction of teaching input and structural changes. A well–known concept for this interaction is Hebbian learning, which is regulated by ANMs in the presented approach. In extension to related work in evolutionary robotics (ER), we analyze important details of robotic (ontogenetic) learning by experiments measuring the ability of robots to learn simple tasks in a simulated environment without employing evolution. Specifically, we are interested in the comparison of Hebb learning variants, and the crucial question of the correct interpretation of reward or punishment signals by the robot.