The memorization of in-line sensorimotor invariants: toward behavioral ontogeny and enactive agents
| Autor: | Kristen Manac'H, Pierre Chevaillier, Pierre De Loor |
|---|---|
| Přispěvatelé: | Lab-STICC_ENIB_CID_IHSEV, Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC), École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-Télécom Bretagne-Institut Brestois du Numérique et des Mathématiques (IBNM), Université de Brest (UBO)-Université européenne de Bretagne - European University of Brittany (UEB)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS) |
| Rok vydání: | 2014 |
| Předmět: |
Computer science
Evolutionary algorithm Evolutionary robotics [SCCO.COMP]Cognitive science/Computer science 02 engineering and technology computer.software_genre 050105 experimental psychology General Biochemistry Genetics and Molecular Biology Memorization Embodied agent Memory Artificial Intelligence 0202 electrical engineering electronic engineering information engineering 0501 psychology and cognitive sciences Sensorimotor invariants CTRNN business.industry Field (Bourdieu) 05 social sciences Recurrent neural network Ontogeny Line (geometry) Enaction 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | Artificial Life and Robotics Artificial Life and Robotics, Springer Verlag, 2014, 19 (2), pp.127-135. ⟨10.1007/s10015-014-0143-3⟩ |
| ISSN: | 1614-7456 1433-5298 |
| DOI: | 10.1007/s10015-014-0143-3 |
| Popis: | International audience; This paper presents a behavioral ontogeny for artificial agents based on the interactive memorization of sensorimotor invariants. The agents are controlled by continuous timed recurrent neural networks (CTRNNs) which bind their sensors and motors within a dynamic system. The behavioral ontogenesis is based on a phylo- genetic approach: memorization occurs during the agent's lifetime and an evolutionary algorithm discovers CTRNN parameters. This shows that sensorimotor invariants can be durably modified through interaction with a guiding agent. After this phase has finished, agents are able to adopt new sensorimotor invariants relative to the environment with no further guidance. We obtained these kinds of behaviors for CTRNNs with 3-6 units, and this paper examines the functioning of those CTRNNs. For instance, they are able to internally simulate guidance when it is externally absent, in line with theories of simulation in neuroscience and the enactive field of cognitive science. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink