Title :
Fast connectionist learning for trailer backing using a real robot
Author :
Hougen, Dean F. ; Fischer, John ; Gini, Maria ; Slagle, James
Author_Institution :
Dept. of Comput. Sci., Minnesota Univ., Minneapolis, MN, USA
Abstract :
This paper presents the application of a connectionist control-learning system to an autonomous mini-robot. The system´s design is severely constrained by the computing power and memory available on board the mini-robot and the on-board training time is greatly limited by the short life of the battery. The system is capable of rapid unsupervised learning of output responses in temporal domains through the use of eligibility traces and data sharing within topologically defined neighborhoods
Keywords :
mobile robots; neurocontrollers; unsupervised learning; autonomous mini-robot; connectionist control-learning system; data sharing; eligibility traces; fast connectionist learning; neural net; output responses; rapid unsupervised learning; temporal domains; topologically defined neighborhoods; trailer backing; Application software; Computer science; Control systems; Learning systems; Network topology; Neural networks; Neurofeedback; Neurons; Robots; Unsupervised learning;
Conference_Titel :
Robotics and Automation, 1996. Proceedings., 1996 IEEE International Conference on
Conference_Location :
Minneapolis, MN
Print_ISBN :
0-7803-2988-0
DOI :
10.1109/ROBOT.1996.506991
