Spiking neural controllers in multi-agent competitive systems for adaptive targeted motor learning

Vitanza, A.; Patane, L.; Arena, P.

doi:10.1016/j.jfranklin.2015.04.014

The proposedworkintroducesaneuralcontrolstrategyforguidingadaptationinspikingneuralstructures acting asnonlinearcontrollersinagroupofbio-inspiredrobotswhichcompeteinreachingtargetsina virtual environment.Theneuralstructuresembeddedintoeachagentareinspiredbyaspecific partofthe insect brain,namelyCentralComplex,devotedtodetect,learnandmemorizevisualfeaturesfortargeted motor control.Areduced-ordermodelofaspikingneuronisusedasthebasicbuildingblockfortheneural controller. Thecontrolmethodologyemploysbio-inspired,correlationbasedlearningmechanismslike Spike timingdependentplasticity with theadditionofareward/punishment-basedmethodexperimentally found ininsects.Thereferencesignalfortheoverallmulti-agentcontrolsystemisimposedbyaglobal reward, whichguidesmotorlearningtodirecteachagenttowardsspecific visualtargets.Theneural controllers withintheagentsstartfromidenticalconditions:thelearningstrategyinduceseachrobottoshow anticipated targetingactionsuponspecific visualstimuli.Thewholecontrolstructurealsocontributesto make therobotsrefractoryormoresensitivetospecific visualstimuli,showingdistinctpreferencesinfuture choices. Thisleadstoanenvironmentallyinduced,targetedmotorcontrol,evenwithoutadirect communication amongtheagents,givingrobots,whilerunning,theabilitytoperformadaptationinreal- time. Experiments,carriedoutinadynamicsimulationenvironment,showthesuitabilityoftheproposed approach. Specific performanceindexes,likeShannon'sEntropy,areadoptedtoquantitativelyanalyze diversity andspecializationwithinthegroup.

Titolo:	Spiking neural controllers in multi-agent competitive systems for adaptive targeted motor learning
Autori:	Vitanza A. PATANE', Luca Arena P. mostra contributor esterni nascondi contributor esterni
Data di pubblicazione:	2015
Rivista:	JOURNAL OF THE FRANKLIN INSTITUTE
Abstract:	The proposedworkintroducesaneuralcontrolstrategyforguidingadaptationinspikingneuralstructures acting asnonlinearcontrollersinagroupofbio-inspiredrobotswhichcompeteinreachingtargetsina virtual environment.Theneuralstructuresembeddedintoeachagentareinspiredbyaspecific partofthe insect brain,namelyCentralComplex,devotedtodetect,learnandmemorizevisualfeaturesfortargeted motor control.Areduced-ordermodelofaspikingneuronisusedasthebasicbuildingblockfortheneural controller. Thecontrolmethodologyemploysbio-inspired,correlationbasedlearningmechanismslike Spike timingdependentplasticity with theadditionofareward/punishment-basedmethodexperimentally found ininsects.Thereferencesignalfortheoverallmulti-agentcontrolsystemisimposedbyaglobal reward, whichguidesmotorlearningtodirecteachagenttowardsspecific visualtargets.Theneural controllers withintheagentsstartfromidenticalconditions:thelearningstrategyinduceseachrobottoshow anticipated targetingactionsuponspecific visualstimuli.Thewholecontrolstructurealsocontributesto make therobotsrefractoryormoresensitivetospecific visualstimuli,showingdistinctpreferencesinfuture choices. Thisleadstoanenvironmentallyinduced,targetedmotorcontrol,evenwithoutadirect communication amongtheagents,givingrobots,whilerunning,theabilitytoperformadaptationinreal- time. Experiments,carriedoutinadynamicsimulationenvironment,showthesuitabilityoftheproposed approach. Specific performanceindexes,likeShannon'sEntropy,areadoptedtoquantitativelyanalyze diversity andspecializationwithinthegroup.
Handle:	http://hdl.handle.net/11570/3148488
Appare nelle tipologie:	14.a.1 Articolo su rivista

File in questo prodotto:

Non ci sono file associati a questo prodotto.

Utilizza questo identificativo per citare o creare un link a questo documento:
http://hdl.handle.net/11570/3148488

Citazioni

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

CINECA IRIS Institutional Research Information System

File in questo prodotto: