Toward Robotic Cognition by Means of Decision Tree of Deep Neural Networks Applied in a Humanoid Robot

Página do item simplificado
dc.contributor.authorSILVA, I. J.
dc.contributor.authorJUNIOR, C. O. V.
dc.contributor.authorCOSTA, A. H. R.
dc.contributor.authorReinaldo Bianchi
dc.date.accessioned2022-01-12T21:53:50Z
dc.date.available2022-01-12T21:53:50Z
dc.date.issued2021-08-05
dc.description.abstract© 2021, Brazilian Society for Automatics--SBA.One of the challenges of Deep Learning research is to develop algorithms for mobile robotic agents that operate in uncontrolled environments, in which dynamic changes and limited processing power are common restrictions. A common solution is to develop separate vision and decision modules, so that the former is based on deep neural network architectures and the latter is based on rules, and then interconnect them. The drawback of this solution is that the modules need to exchange high-level information about the objects in the scene, which are usually the positions of all objects in the scene, and this is computationally expensive. To address this problem, this paper presents a Decision Tree of Deep Neural Networks (DT-DNN) that aims to perform end to end—from image to decision—processing, and, thus, eliminating the need for quantitative and relational information about the image. This model is composed of smaller and more specialized modular DNNs, thus solving the trade-off between performance and inference time. Experiments were carried out using a real robot in the RoboCup Humanoid League domain in a soccer field, and also in simulation. We compared DT-DNN with several traditional DNN architectures. From the results, it is possible to conclude that the use of the DT-DNN made the system simpler and more robust, with fewer parameters to be adjusted, reducing the time spent with inference and also increasing the performance when compared to the traditional approach.
dc.description.firstpage884
dc.description.issuenumber4
dc.description.lastpage894
dc.description.volume32
dc.identifier.citationhttps://orcid.org/0000-0001-9097-827X
dc.identifier.citationSILVA, I. J.; VILÃO JÚNIOR, C. O.; COSTA, A. H. R.; BIANCHI, R. Toward Robotic Cognition by Means of Decision Tree of Deep Neural Networks Applied in a Humanoid Robot. Journal of Control, Automation and Electrical Systems, v. 32, n, 4, p. 884-894, Aug. 2021.
dc.identifier.doi10.1007/s40313-021-00719-8
dc.identifier.issn2195-3899
dc.identifier.urihttps://repositorio.fei.edu.br/handle/FEI/3567
dc.relation.ispartofJournal of Control, Automation and Electrical Systems
dc.rightsAcesso Restrito
dc.subject.otherlanguageCognitive robotics
dc.subject.otherlanguageDeep neural networks
dc.subject.otherlanguageMobile robots
dc.subject.otherlanguageRobot learning
dc.subject.otherlanguageRobot vision systems
dc.titleToward Robotic Cognition by Means of Decision Tree of Deep Neural Networks Applied in a Humanoid Robot
dc.typeArtigo
fei.scopus.citations1
fei.scopus.eid2-s2.0-85104879917
fei.scopus.subjectDecision modules
fei.scopus.subjectDynamic changes
fei.scopus.subjectHigh-level information
fei.scopus.subjectHumanoid robot
fei.scopus.subjectMobile robotic
fei.scopus.subjectProcessing power
fei.scopus.subjectSoccer fields
fei.scopus.subjectTraditional approaches
fei.scopus.updated2024-07-01
fei.scopus.urlhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85104879917&origin=inward
Arquivos
Coleções
Artigos