Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/26532

Title: Robot competence development by constructive learning
Authors: Meng, Qinggang
Lee, Mark H.
Hinde, Chris J.
Issue Date: 2010
Publisher: © Springer
Citation: MENG, Q., LEE, M. and HINDE, C., 2010. Robot competence development by constructive learning. IN: Ao, S. ... et al. (eds.). Advances in Machine Learning and Data Analysis. (Lecture Notes in Electrical Engineering ; 48.) London: Springer, pp.15-26.
Series/Report no.: Lecture Notes in Electrical Engineering;48
Abstract: This paper presents a constructive learning approach for developing sensor-motor mapping in autonomous systems. The system's adaptation to environment changes is discussed and three methods are proposed to deal with long term and short term changes. The proposed constructive learning allows autonomous systems to develop network topology and adjust network parameters. The approach is supported by findings from psychology and neuroscience especially during infants cognitive development at early stages. A growing radial basis function network is introduced as a computational substrate for sensory-motor mapping learning. Experiments are conducted on a robot eye/hand coordination testbed and results show the incremental development of sensory-motor mapping and its adaptation to changes such as in tool-use.
Description: The final publication is available at Springer via: https://doi.org/10.1007/978-90-481-3177-8_2.
Version: Accepted for publication
DOI: 10.1007/978-90-481-3177-8_2
URI: https://dspace.lboro.ac.uk/2134/26532
Publisher Link: http://dx.doi.org/10.1007/978-90-481-3177-8_2
ISBN: 9789048131778
ISSN: 1876-1100
Appears in Collections:Book Chapters (Computer Science)

Files associated with this item:

File Description SizeFormat
Chapter-meng.pdfAccepted version625.85 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.