Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE
In this paper we present a complete spike-based architecture: from a Dynamic Vision Sensor (retina) to a stereo head robotic platform. The aim of this research is to reproduce intended movements performed by humans taking into account as many features as possible from the biological point of view. T...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2013-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/13/11/15805 |
| _version_ | 1828150054451412992 |
|---|---|
| author | Fernando Perez-Peña Arturo Morgado-Estevez Alejandro Linares-Barranco Angel Jimenez-Fernandez Francisco Gomez-Rodriguez Gabriel Jimenez-Moreno Juan Lopez-Coronado |
| author_facet | Fernando Perez-Peña Arturo Morgado-Estevez Alejandro Linares-Barranco Angel Jimenez-Fernandez Francisco Gomez-Rodriguez Gabriel Jimenez-Moreno Juan Lopez-Coronado |
| author_sort | Fernando Perez-Peña |
| collection | DOAJ |
| description | In this paper we present a complete spike-based architecture: from a Dynamic Vision Sensor (retina) to a stereo head robotic platform. The aim of this research is to reproduce intended movements performed by humans taking into account as many features as possible from the biological point of view. This paper fills the gap between current spike silicon sensors and robotic actuators by applying a spike processing strategy to the data flows in real time. The architecture is divided into layers: the retina, visual information processing, the trajectory generator layer which uses a neuroinspired algorithm (SVITE) that can be replicated into as many times as DoF the robot has; and finally the actuation layer to supply the spikes to the robot (using PFM). All the layers do their tasks in a spike-processing mode, and they communicate each other through the neuro-inspired AER protocol. The open-loop controller is implemented on FPGA using AER interfaces developed by RTC Lab. Experimental results reveal the viability of this spike-based controller. Two main advantages are: low hardware resources (2% of a Xilinx Spartan 6) and power requirements (3.4 W) to control a robot with a high number of DoF (up to 100 for a Xilinx Spartan 6). It also evidences the suitable use of AER as a communication protocol between processing and actuation. |
| first_indexed | 2024-04-11T21:37:50Z |
| format | Article |
| id | doaj.art-b6d65553cf314fa891c90e44915dae85 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:37:50Z |
| publishDate | 2013-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b6d65553cf314fa891c90e44915dae852022-12-22T04:01:41ZengMDPI AGSensors1424-82202013-11-011311158051583210.3390/s131115805s131115805Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITEFernando Perez-Peña0Arturo Morgado-Estevez1Alejandro Linares-Barranco2Angel Jimenez-Fernandez3Francisco Gomez-Rodriguez4Gabriel Jimenez-Moreno5Juan Lopez-Coronado6Computer Architecture and Technology Area, Universidad de Cádiz, School of Engineering, Calle Chile, 1, Cadiz 11002, SpainComputer Architecture and Technology Area, Universidad de Cádiz, School of Engineering, Calle Chile, 1, Cadiz 11002, SpainRobotic and Technology of Computers Lab (RTC), Universidad de Sevilla, ETSI Informática, Avd. Reina Mercedes s/n, Sevilla 41012, SpainRobotic and Technology of Computers Lab (RTC), Universidad de Sevilla, ETSI Informática, Avd. Reina Mercedes s/n, Sevilla 41012, SpainRobotic and Technology of Computers Lab (RTC), Universidad de Sevilla, ETSI Informática, Avd. Reina Mercedes s/n, Sevilla 41012, SpainRobotic and Technology of Computers Lab (RTC), Universidad de Sevilla, ETSI Informática, Avd. Reina Mercedes s/n, Sevilla 41012, SpainAutomation and System Engineering Department, Polytechnic University of Cartagena, Campus Muralla del Mar, Cartagena, 30202, SpainIn this paper we present a complete spike-based architecture: from a Dynamic Vision Sensor (retina) to a stereo head robotic platform. The aim of this research is to reproduce intended movements performed by humans taking into account as many features as possible from the biological point of view. This paper fills the gap between current spike silicon sensors and robotic actuators by applying a spike processing strategy to the data flows in real time. The architecture is divided into layers: the retina, visual information processing, the trajectory generator layer which uses a neuroinspired algorithm (SVITE) that can be replicated into as many times as DoF the robot has; and finally the actuation layer to supply the spikes to the robot (using PFM). All the layers do their tasks in a spike-processing mode, and they communicate each other through the neuro-inspired AER protocol. The open-loop controller is implemented on FPGA using AER interfaces developed by RTC Lab. Experimental results reveal the viability of this spike-based controller. Two main advantages are: low hardware resources (2% of a Xilinx Spartan 6) and power requirements (3.4 W) to control a robot with a high number of DoF (up to 100 for a Xilinx Spartan 6). It also evidences the suitable use of AER as a communication protocol between processing and actuation.http://www.mdpi.com/1424-8220/13/11/15805spike systemsmotor controlVITEaddress event representationneuro-inspiredneuromorphic engineeringanthropomorphic robots |
| spellingShingle | Fernando Perez-Peña Arturo Morgado-Estevez Alejandro Linares-Barranco Angel Jimenez-Fernandez Francisco Gomez-Rodriguez Gabriel Jimenez-Moreno Juan Lopez-Coronado Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE Sensors spike systems motor control VITE address event representation neuro-inspired neuromorphic engineering anthropomorphic robots |
| title | Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE |
| title_full | Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE |
| title_fullStr | Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE |
| title_full_unstemmed | Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE |
| title_short | Neuro-Inspired Spike-Based Motion: From Dynamic Vision Sensor to Robot Motor Open-Loop Control through Spike-VITE |
| title_sort | neuro inspired spike based motion from dynamic vision sensor to robot motor open loop control through spike vite |
| topic | spike systems motor control VITE address event representation neuro-inspired neuromorphic engineering anthropomorphic robots |
| url | http://www.mdpi.com/1424-8220/13/11/15805 |
| work_keys_str_mv | AT fernandoperezpena neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite AT arturomorgadoestevez neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite AT alejandrolinaresbarranco neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite AT angeljimenezfernandez neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite AT franciscogomezrodriguez neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite AT gabrieljimenezmoreno neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite AT juanlopezcoronado neuroinspiredspikebasedmotionfromdynamicvisionsensortorobotmotoropenloopcontrolthroughspikevite |