Title :
Characterization of a neural network-based trajectory recognition optical sensor for an automated guided vehicle
Author :
Borges, G.A. ; Lima, A.M.N. ; Deep, G.S.
Author_Institution :
Dept. de Engenharia Eletrica, Univ. Fed. do Parana, Curitiba, Brazil
Abstract :
Characterization of a relatively simple optical sensor system used for recognition of the desired fixed trajectory for an automated guided vehicle, painted on an industrial shop floor, is described. The optical sensor consists of 14 IR emitter-detector pairs arranged in two columns and is fixed underneath the vehicle chassis. A microcomputer-based test platform for evaluation of the proposed sensor is also described. The sensor performance is evaluated using geometrical algorithms and one based on neural networks, the latter giving much better results
Keywords :
automatic guided vehicles; backpropagation; computerised navigation; image sensors; multilayer perceptrons; optical sensors; optical tracking; path planning; position control; robot vision; IR emitter-detector pairs; automated guided vehicle; backpropagation; desired fixed trajectory; geometrical algorithms; industrial shop floor; microcomputer-based test platform; multilayer perceptrons; navigation control; neural network-based; nonlinear neurons; normalised position index; painted trajectory; sensor performance; tracking system; trajectory recognition optical sensor; Automatic control; Character recognition; Control systems; Global Positioning System; Infrared detectors; Mobile robots; Navigation; Neural networks; Optical sensors; Remotely operated vehicles;
Conference_Titel :
Instrumentation and Measurement Technology Conference, 1998. IMTC/98. Conference Proceedings. IEEE
Conference_Location :
St. Paul, MN
Print_ISBN :
0-7803-4797-8
DOI :
10.1109/IMTC.1998.676910
