Evolution of computer vision subsystems in robot navigation and image classification tasks

Autor(en): Lange, S
Riedmiller, M
Herausgeber: Nardi, D
Riedmiller, M
Sammut, C
SantosVictor, J
Stichwörter: Computer Science; Computer Science, Artificial Intelligence; Robotics
Erscheinungsdatum: 2005
Herausgeber: SPRINGER-VERLAG BERLIN
Journal: ROBOCUP 2004: ROBOT SOCCER WORLD CUP VIII
LECTURE NOTES IN COMPUTER SCIENCE
Volumen: 3276
Startseite: 184
Seitenende: 195
Zusammenfassung: 
Real-time decision making based on visual sensory information is a demanding task for mobile robots. Learning on high-dimensional, highly redundant image data imposes a real problem for most learning algorithms, especially those being based on neural networks. In this paper we investigate the utilization of evolutionary techniques in combination with supervised learning of feedforward nets to automatically construct and improve suitable, task-dependent preprocessing layers helping to reduce the complexity of the original learning problem. Given a number of basic, parameterized low-level computer vision algorithms, the proposed evolutionary algorithm automatically selects and appropriately sets up the parameters of exactly those operators best suited for the imposed supervised learning problem.
Beschreibung: 
8th International RoboCup Symposium, Inst Superior Tecnico, Lisbon, PORTUGAL, JUN 27-JUL 05, 2004
ISBN: 9783540250463
ISSN: 03029743

Show full item record

Page view(s)

1
Last Week
0
Last month
0
checked on Feb 21, 2024

Google ScholarTM

Check

Altmetric