Towards Real-World Neurorobotics: Integrated Neuromorphic Visual Attention

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

  • External authors:
  • Samantha V Adams
  • Alexander D Rast
  • Cameron Patterson
  • Francesco Galluppi
  • Kevin Brohan
  • José-Antonio Pérez-Carrasco
  • Thomas Wennekers
  • Angelo Cangelosi

Abstract

Neuromorphic hardware and cognitive robots seem like an obvious fit, yet progress to date has been frustrated by a lack of tangible progress in achieving useful real-world behaviour. System limitations: the simple and usually proprietary nature of neuromorphic and robotic platforms, have often been the fundamental barrier. Here we present an integration of a mature “neuromimetic” chip, SpiNNaker, with the humanoid iCub robot using a direct AER - address-event representation - interface that overcomes the need for complex proprietary protocols by sending information as UDP-encoded spikes over an Ethernet link. Using an existing neural model devised for visual object selection, we enable the robot to perform a real-world task: fixating attention upon a selected stimulus. Results demonstrate the effectiveness of interface and model in being able to control the robot towards stimulus-specific object selection. Using SpiNNaker as an embeddable neuromorphic device illustrates the importance of two design features in a prospective neurorobot: universal configurability that allows the chip to be conformed to the requirements of the robot rather than the other way ’round, and standard interfaces that eliminate difficult low-level issues of connectors, cabling, signal voltages, and protocols. While this study is only a building block towards that goal, the iCub-SpiNNaker system demonstrates a path towards meaningful behaviour in robots controlled by neural network chips.

Bibliographical metadata

Original languageEnglish
Title of host publication21st International Conference, ICONIP 2014, Proceedings, Part III
Place of PublicationSpringer International Publishing Switzerland
PublisherSpringer Nature
Pages563-570
Number of pages8
Volume8836
ISBN (Print)978-3-319-12642-5
DOIs
Publication statusPublished - 3 Nov 2014
Event21st International Conference, ICONIP 2014 - Kuching, Malaysia
Event duration: 3 Nov 20146 Nov 2014

Publication series

NameNeural Information Processing, Lecture Notes in Computer Science

Conference

Conference21st International Conference, ICONIP 2014
CityKuching, Malaysia
Period3/11/146/11/14