Serendipitous Offline Learning in a Neuromorphic Robot

We demonstrate a hybrid neuromorphic learning paradigm that learns complex sensorimotor mappings based on a small set of hard-coded reflex behaviors. A mobile robot is first controlled by a basic set of reflexive hand-designed behaviors. All sensor data is provided via a spike-based silicon retina c...

Full description

Bibliographic Details
Main Authors:	Stewart, Terrence C., Kleinhans, Ashley, Mundy, Andrew, Conradt, Jörg
Format:	Online
Language:	English
Published:	Frontiers Media S.A. 2016
Online Access:	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4753383/

id	pubmed-4753383
recordtype	oai_dc
spelling	pubmed-47533832016-02-24 Serendipitous Offline Learning in a Neuromorphic Robot Stewart, Terrence C. Kleinhans, Ashley Mundy, Andrew Conradt, Jörg Neuroscience We demonstrate a hybrid neuromorphic learning paradigm that learns complex sensorimotor mappings based on a small set of hard-coded reflex behaviors. A mobile robot is first controlled by a basic set of reflexive hand-designed behaviors. All sensor data is provided via a spike-based silicon retina camera (eDVS), and all control is implemented via spiking neurons simulated on neuromorphic hardware (SpiNNaker). Given this control system, the robot is capable of simple obstacle avoidance and random exploration. To train the robot to perform more complex tasks, we observe the robot and find instances where the robot accidentally performs the desired action. Data recorded from the robot during these times is then used to update the neural control system, increasing the likelihood of the robot performing that task in the future, given a similar sensor state. As an example application of this general-purpose method of training, we demonstrate the robot learning to respond to novel sensory stimuli (a mirror) by turning right if it is present at an intersection, and otherwise turning left. In general, this system can learn arbitrary relations between sensory input and motor behavior. Frontiers Media S.A. 2016-02-15 /pmc/articles/PMC4753383/ /pubmed/26913002 http://dx.doi.org/10.3389/fnbot.2016.00001 Text en Copyright © 2016 Stewart, Kleinhans, Mundy and Conradt. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
repository_type	Open Access Journal
institution_category	Foreign Institution
institution	US National Center for Biotechnology Information
building	NCBI PubMed
collection	Online Access
language	English
format	Online
author	Stewart, Terrence C. Kleinhans, Ashley Mundy, Andrew Conradt, Jörg
spellingShingle	Stewart, Terrence C. Kleinhans, Ashley Mundy, Andrew Conradt, Jörg Serendipitous Offline Learning in a Neuromorphic Robot
author_facet	Stewart, Terrence C. Kleinhans, Ashley Mundy, Andrew Conradt, Jörg
author_sort	Stewart, Terrence C.
title	Serendipitous Offline Learning in a Neuromorphic Robot
title_short	Serendipitous Offline Learning in a Neuromorphic Robot
title_full	Serendipitous Offline Learning in a Neuromorphic Robot
title_fullStr	Serendipitous Offline Learning in a Neuromorphic Robot
title_full_unstemmed	Serendipitous Offline Learning in a Neuromorphic Robot
title_sort	serendipitous offline learning in a neuromorphic robot
description	We demonstrate a hybrid neuromorphic learning paradigm that learns complex sensorimotor mappings based on a small set of hard-coded reflex behaviors. A mobile robot is first controlled by a basic set of reflexive hand-designed behaviors. All sensor data is provided via a spike-based silicon retina camera (eDVS), and all control is implemented via spiking neurons simulated on neuromorphic hardware (SpiNNaker). Given this control system, the robot is capable of simple obstacle avoidance and random exploration. To train the robot to perform more complex tasks, we observe the robot and find instances where the robot accidentally performs the desired action. Data recorded from the robot during these times is then used to update the neural control system, increasing the likelihood of the robot performing that task in the future, given a similar sensor state. As an example application of this general-purpose method of training, we demonstrate the robot learning to respond to novel sensory stimuli (a mirror) by turning right if it is present at an intersection, and otherwise turning left. In general, this system can learn arbitrary relations between sensory input and motor behavior.
publisher	Frontiers Media S.A.
publishDate	2016
url	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4753383/
_version_	1613538448818307072

Serendipitous Offline Learning in a Neuromorphic Robot

Similar Items