SIA OpenIR  > 机器人学研究室
The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control
Smith, Simón C.1; Dharmadi, Richard1; Imrie, Calum1; Si BL(斯白露)2,3; Herrmann, J. Michael1,2
Department机器人学研究室
Source PublicationFrontiers in Neurorobotics
ISSN1662-5218
2020
Volume14Pages:1-7
Indexed BySCI ; EI
EI Accession number20204109309139
WOS IDWOS:000576158900001
Contribution Rank2
Funding OrganizationORCA Hub EPSRC project (EP/R026173/1, 2017-2021) ; EP/L016834/1 for the University of Edinburgh, School of Informatics, Centre for Doctoral Training in Robotics and Autonomous Systems from the UK Engineering and Physical Sciences Research Council (EPSRC) ; National Key R&D Program of China (2019YFA0709503)
Keyworddeep neural networks autonomous learning homeokinesis self-organizing control robot control
Abstract

The proposed architecture applies the principle of predictive coding and deep learning in a brain-inspired approach to robotic sensorimotor control. It is composed of many layers each of which is a recurrent network. The component networks can be spontaneously active due to the homeokinetic learning rule, a principle that has been studied previously for the purpose of self-organized generation of behavior. We present robotic simulations that illustrate the function of the network and show evidence that deeper networks enable more complex exploratory behavior.

Language英语
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/27718
Collection机器人学研究室
Corresponding AuthorHerrmann, J. Michael
Affiliation1.Institute of Perception, Action and Behaviour (IPAB), School of Informatics, University of Edinburgh, Edinburgh, United Kingdom
2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China
3.School of Systems Science, Beijing Normal University, Beijing, China
Recommended Citation
GB/T 7714
Smith, Simón C.,Dharmadi, Richard,Imrie, Calum,et al. The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control[J]. Frontiers in Neurorobotics,2020,14:1-7.
APA Smith, Simón C.,Dharmadi, Richard,Imrie, Calum,Si BL,&Herrmann, J. Michael.(2020).The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control.Frontiers in Neurorobotics,14,1-7.
MLA Smith, Simón C.,et al."The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control".Frontiers in Neurorobotics 14(2020):1-7.
Files in This Item: Download All
File Name/Size DocType Version Access License
The DIAMOND Model_ D(1291KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Smith, Simón C.]'s Articles
[Dharmadi, Richard]'s Articles
[Imrie, Calum]'s Articles
Baidu academic
Similar articles in Baidu academic
[Smith, Simón C.]'s Articles
[Dharmadi, Richard]'s Articles
[Imrie, Calum]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Smith, Simón C.]'s Articles
[Dharmadi, Richard]'s Articles
[Imrie, Calum]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: The DIAMOND Model_ Deep Recurrent Neural Networks for Self-Organizing Robot Control.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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