hrcak mascot   Srce   HID

Izvorni znanstveni članak

AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES

Marko Švaco   ORCID icon orcid.org/0000-0002-6761-4336 ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia
Bojan Jerbić   ORCID icon orcid.org/0000-0003-1811-5669 ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia
Filip Šuligoj ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia

Puni tekst: engleski, pdf (3 MB) str. 13-28 preuzimanja: 231* citiraj
APA 6th Edition
Švaco, M., Jerbić, B. i Šuligoj, F. (2014). AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES. Transactions of FAMENA, 38 (4), 13-28. Preuzeto s https://hrcak.srce.hr/135873
MLA 8th Edition
Švaco, Marko, et al. "AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES." Transactions of FAMENA, vol. 38, br. 4, 2014, str. 13-28. https://hrcak.srce.hr/135873. Citirano 14.10.2019.
Chicago 17th Edition
Švaco, Marko, Bojan Jerbić i Filip Šuligoj. "AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES." Transactions of FAMENA 38, br. 4 (2014): 13-28. https://hrcak.srce.hr/135873
Harvard
Švaco, M., Jerbić, B., i Šuligoj, F. (2014). 'AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES', Transactions of FAMENA, 38(4), str. 13-28. Preuzeto s: https://hrcak.srce.hr/135873 (Datum pristupa: 14.10.2019.)
Vancouver
Švaco M, Jerbić B, Šuligoj F. AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES. Transactions of FAMENA [Internet]. 2014 [pristupljeno 14.10.2019.];38(4):13-28. Dostupno na: https://hrcak.srce.hr/135873
IEEE
M. Švaco, B. Jerbić i F. Šuligoj, "AUTONOMOUS ROBOT LEARNING MODEL BASED ON VISUAL INTERPRETATION OF SPATIAL STRUCTURES", Transactions of FAMENA, vol.38, br. 4, str. 13-28, 2014. [Online]. Dostupno na: https://hrcak.srce.hr/135873. [Citirano: 14.10.2019.]

Sažetak
The main concept of the presented research is an autonomous robot learning model for which a novel ARTgrid neural network architecture for the classification of spatial structures is used. The motivation scenario includes incremental unsupervised learning which is mainly based on discrete spatial structure changes recognized by the robot vision system. The learning policy problem is presented as a classification problem for which the adaptive resonance theory (ART) concept is implemented. The methodology and architecture of the autonomous robot learning model with preliminary results are presented. A computer simulation was performed with four input sets containing 22, 45, 73, and 111 random spatial structures. The ARTgrid shows a fairly high (>85%) match score when applied with already learned patterns after the first learning cycle, and a score of >95% after the second cycle. Regarding the category proliferation, the results are compared with a more predictive modified cluster centre seeking algorithm.

Ključne riječi
autonomous systems; machine learning; adaptive resonance theory

Hrčak ID: 135873

URI
https://hrcak.srce.hr/135873

Posjeta: 443 *