User: Guest  Login
Title:

Serendipitous Offline Learning in a Neuromorphic Robot

Document type:
Zeitschriftenaufsatz
Author(s):
Stewart, T. C.; Mundy, A.; Kleinhans, A.; Conradt, J.
Abstract:
We demonstrate a hybrid neuromorphic learning paradigm that learns complex sensorimotor mappings based on a small set of hard-coded reflex behaviours. A mobile robot is first controlled by a basic set of reflexive hand-designed behaviours. 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 rand...     »
Keywords:
adaptive systems, mobile robotics, neurocontrollers, Neuromorphics, robot control
Journal title:
Frontiers in Neurorobotics
Year:
2016
Journal volume:
10
Journal issue:
01
Reviewed:
ja
Language:
en
Fulltext / DOI:
doi:10.3389/fnbot.2016.00001
Notes:
Citation: Stewart TC, Kleinhans A, Mundy A and Conradt J (2016) Serendipitous Offline Learning in a Neuromorphic Robot. Front. Neurorobot. 10:1. doi: 10.3389/fnbot.2016.00001
Submitted:
13.09.2015
Accepted:
26.01.2016
Date of publication:
15.02.2016
Copyright statement:
© 2016 Stewart, Mundy, Kleinhans and Conradt. 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.
Semester:
WS 15-16
TUM Institution:
Juniorprofessur für Neurowissenschaftliche Systemtheorie
 BibTeX