Action Learning Experiments Using Spiking Neural Networks and Humanoid Robots
dc.contributor.supervisor | Cangelosi, Angelo | |
dc.contributor.author | de Azambuja, Ricardo | |
dc.contributor.other | School of Engineering, Computing and Mathematics | en_US |
dc.date.accessioned | 2018-02-12T16:25:11Z | |
dc.date.issued | 2018 | |
dc.identifier | 10428733 | en_US |
dc.identifier.uri | http://hdl.handle.net/10026.1/10767 | |
dc.description | Edited 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.sponsorship | CAPES Foundation, Ministry of Education of Brazil (scholarship BEX 1084/13-5) | en_US |
dc.description.sponsorship | UK EPSRC project BABEL (EP/J004561/1 and EP/J00457X/1) | en_US |
dc.language.iso | en | |
dc.publisher | University of Plymouth | |
dc.rights | Attribution-NonCommercial-ShareAlike 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/3.0/us/ | * |
dc.subject | Neural Networks | en_US |
dc.subject | Liquid State Machines | en_US |
dc.subject | Robotics | en_US |
dc.subject | Action Learning | en_US |
dc.subject | Spiking Neural Networks | en_US |
dc.subject | LSM | en_US |
dc.subject | Humanoid Robots | en_US |
dc.subject.classification | PhD | en_US |
dc.title | Action Learning Experiments Using Spiking Neural Networks and Humanoid Robots | en_US |
dc.type | Thesis | |
plymouth.version | non-publishable | en_US |
dc.identifier.doi | http://dx.doi.org/10.24382/1114 | |
dc.type.qualification | Doctorate | en_US |
rioxxterms.version | NA | |
plymouth.orcid.id | https://orcid.org/0000-0003-0185-545X | en_US |
Files in this item
This item appears in the following Collection(s)
-
01 Research Theses Main Collection
Research Theses Main