The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control

Smith, Simón C.; Dharmadi, Richard; Imrie, Calum; Si, Bailu; Herrmann, J. Michael

doi:10.3389/fnbot.2020.00062

The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control

Smith, Simón C.; Dharmadi, Richard; Imrie, Calum; Si, Bailu; Herrmann, J. Michael

Authors

Simón C. Smith

Richard Dharmadi

Calum Imrie

Bailu Si

J. Michael Herrmann

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.

Citation

Smith, S. C., Dharmadi, R., Imrie, C., Si, B., & Herrmann, J. M. (2020). The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control. Frontiers in Neurorobotics, 14, Article 62. https://doi.org/10.3389/fnbot.2020.00062

Journal Article Type	Article
Acceptance Date	Aug 3, 2020
Online Publication Date	Sep 15, 2020
Publication Date	2020-09
Deposit Date	Jul 11, 2023
Publicly Available Date	Jul 13, 2023
Journal	Frontiers in Neurorobotics
Electronic ISSN	1662-5218
Publisher	Frontiers Media
Peer Reviewed	Peer Reviewed
Volume	14
Article Number	62
DOI	https://doi.org/10.3389/fnbot.2020.00062
Keywords	deep neural networks, autonomous learning, homeokinesis, self-organizing control, robot control