Show simple item record

dc.contributor.supervisorCangelosi, Angelo
dc.contributor.authorde Azambuja, Ricardo
dc.contributor.otherSchool of Engineering, Computing and Mathematicsen_US
dc.date.accessioned2018-02-12T16:25:11Z
dc.date.issued2018
dc.identifier10428733en_US
dc.identifier.urihttp://hdl.handle.net/10026.1/10767
dc.descriptionEdited version embargoed until 12.02.2019 Full version: Access restricted permanently due to 3rd party copyright restrictions. Restriction set on 12.02.2018 by SE, Doctoral College
dc.description.abstract

The way our brain works is still an open question, but one thing seems to be clear: biological neural systems are computationally powerful, robust and noisy. Natural nervous system are able to control limbs in different scenarios with high precision. As neural networks in living beings communicate through spikes, modern neuromorphic systems try to mimic them by using spike-based neuron models. This thesis is focused on the advancement of neurorobotics or brain inspired robotic arm controllers based on artificial neural network architectures. The architecture chosen to implement those controllers was the spike neuron version of Reservoir Computing framework, called Liquid State Machines. The main goal is to explore the possibility of using brain inspired neural networks to control a robot by demonstration. Moreover, it aims to achieve systems robust to environmental noise and internal structure destruction presenting a graceful degradation. As the validation, a series of action learning experiments are presented where simulated robotic arms are controlled. The investigation starts with a 2 degrees of freedom arm and moves to the research version of the Rethink Robotics Inc. collaborative humanoid robot Baxter. Moreover, a proof-of- concept experiment is also done using the real Baxter robot. The results show Liquid State Machines, when endowed with an extra external feedback loop, can be also employed to control more complex humanoid robotic arms than a simple planar 2 degrees of freedom one. Additionally, the new parallel architecture presented here was capable to withstand noise and internal destruction better than a simple use of multiple columns also presenting a graceful degradation behaviour.

en_US
dc.description.sponsorshipCAPES Foundation, Ministry of Education of Brazil (scholarship BEX 1084/13-5)en_US
dc.description.sponsorshipUK EPSRC project BABEL (EP/J004561/1 and EP/J00457X/1)en_US
dc.language.isoen
dc.publisherUniversity of Plymouth
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectNeural Networksen_US
dc.subjectLiquid State Machinesen_US
dc.subjectRoboticsen_US
dc.subjectAction Learningen_US
dc.subjectSpiking Neural Networksen_US
dc.subjectLSMen_US
dc.subjectHumanoid Robotsen_US
dc.subject.classificationPhDen_US
dc.titleAction Learning Experiments Using Spiking Neural Networks and Humanoid Robotsen_US
dc.typeThesis
plymouth.versionnon-publishableen_US
dc.identifier.doihttp://dx.doi.org/10.24382/1114
dc.type.qualificationDoctorateen_US
rioxxterms.versionNA
plymouth.orcid.idhttps://orcid.org/0000-0003-0185-545Xen_US


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 3.0 United States
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 3.0 United States

All items in PEARL are protected by copyright law.
Author manuscripts deposited to comply with open access mandates are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author.
Theme by 
Atmire NV