In this study we show how simulated robots evolved to display a navigation skills can spontaneously develop an internal model and rely on it to complete their task when sensory stimulation is temporarily unavailable. The analysis of some of the best evolved agents indicates that their internal model operates by anticipating functional properties of the next sensory state rather than the exact state that sensors would have assumed. The characteristics of the states that are anticipated and of the sensory-motor rules that determine how the agents react to the experienced states, however, ensure that the agents produce very similar behaviour during normal and blind phases in which sensory stimulation is available or is self-generated by the agent itself, respectively. The characteristics of the agents' internal models also ensure an effective transition during the phases in which agents' internal dynamics is decoupled and re-coupled with the sensory-motor flow.
Emergence of an internal model in evolving robots subjected to sensory deprivation
Pezzulo G;
2010
Abstract
In this study we show how simulated robots evolved to display a navigation skills can spontaneously develop an internal model and rely on it to complete their task when sensory stimulation is temporarily unavailable. The analysis of some of the best evolved agents indicates that their internal model operates by anticipating functional properties of the next sensory state rather than the exact state that sensors would have assumed. The characteristics of the states that are anticipated and of the sensory-motor rules that determine how the agents react to the experienced states, however, ensure that the agents produce very similar behaviour during normal and blind phases in which sensory stimulation is available or is self-generated by the agent itself, respectively. The characteristics of the agents' internal models also ensure an effective transition during the phases in which agents' internal dynamics is decoupled and re-coupled with the sensory-motor flow.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.orgunit | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | - |
| dc.authority.people | Gigliotta O | it |
| dc.authority.people | Pezzulo G | it |
| dc.authority.people | Nolfi S | it |
| dc.collection.id.s | 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d | * |
| dc.collection.name | 04.01 Contributo in Atti di convegno | * |
| dc.contributor.appartenenza | Istituto di Scienze e Tecnologie della Cognizione - ISTC | * |
| dc.contributor.appartenenza.mi | 986 | * |
| dc.date.accessioned | 2024/02/21 01:55:14 | - |
| dc.date.available | 2024/02/21 01:55:14 | - |
| dc.date.issued | 2010 | - |
| dc.description.abstracteng | In this study we show how simulated robots evolved to display a navigation skills can spontaneously develop an internal model and rely on it to complete their task when sensory stimulation is temporarily unavailable. The analysis of some of the best evolved agents indicates that their internal model operates by anticipating functional properties of the next sensory state rather than the exact state that sensors would have assumed. The characteristics of the states that are anticipated and of the sensory-motor rules that determine how the agents react to the experienced states, however, ensure that the agents produce very similar behaviour during normal and blind phases in which sensory stimulation is available or is self-generated by the agent itself, respectively. The characteristics of the agents' internal models also ensure an effective transition during the phases in which agents' internal dynamics is decoupled and re-coupled with the sensory-motor flow. | - |
| dc.description.affiliations | CNR-ISTC, Roma, CNR-ILC, Pisa | - |
| dc.description.allpeople | Gigliotta, O; Pezzulo, G; Nolfi, S | - |
| dc.description.allpeopleoriginal | Gigliotta O.; Pezzulo G.; Nolfi S. | - |
| dc.description.fulltext | none | en |
| dc.description.numberofauthors | 3 | - |
| dc.identifier.doi | 10.1007/978-3-642-15193-4_54 | - |
| dc.identifier.isbn | 978-3-642-15193-4 | - |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/50350 | - |
| dc.language.iso | eng | - |
| dc.relation.conferencedate | August 25-28, 2010 | - |
| dc.relation.conferencename | 11th International Conference on Simulation of Adaptive Behavior, SAB 2010 | - |
| dc.relation.conferenceplace | Paris | - |
| dc.relation.firstpage | 575 | - |
| dc.relation.ispartofbook | From Animals to Animats 11 | - |
| dc.relation.lastpage | 586 | - |
| dc.relation.volume | 6226 | - |
| dc.subject.keywords | internal model | - |
| dc.subject.keywords | neural networks | - |
| dc.subject.keywords | evolutionary robotics | - |
| dc.subject.singlekeyword | internal model | * |
| dc.subject.singlekeyword | neural networks | * |
| dc.subject.singlekeyword | evolutionary robotics | * |
| dc.title | Emergence of an internal model in evolving robots subjected to sensory deprivation | en |
| dc.type.driver | info:eu-repo/semantics/conferenceObject | - |
| dc.type.full | 04 Contributo in convegno::04.01 Contributo in Atti di convegno | it |
| dc.type.miur | 273 | - |
| dc.type.referee | Sì, ma tipo non specificato | - |
| dc.ugov.descaux1 | 30891 | - |
| iris.orcid.lastModifiedDate | 2024/04/04 11:23:09 | * |
| iris.orcid.lastModifiedMillisecond | 1712222589397 | * |
| iris.sitodocente.maxattempts | 1 | - |
| iris.unpaywall.doi | 10.1007/978-3-642-15193-4_54 | * |
| iris.unpaywall.isoa | false | * |
| iris.unpaywall.journalisindoaj | false | * |
| iris.unpaywall.metadataCallLastModified | 27/12/2025 03:43:20 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1766803400486 | - |
| iris.unpaywall.oastatus | closed | * |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
