Learning to reach to own body from spontaneous self-touch using a generative model

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00362238" target="_blank" >RIV/68407700:21230/22:00362238 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICDL53763.2022.9962186" target="_blank" >https://doi.org/10.1109/ICDL53763.2022.9962186</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICDL53763.2022.9962186" target="_blank" >10.1109/ICDL53763.2022.9962186</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning to reach to own body from spontaneous self-touch using a generative model

Popis výsledku v původním jazyce

When leaving the aquatic constrained environment of the womb, newborns are thrown into the world with essentially new laws and regularities that govern their interactions with the environment. Here, we study how spontaneous self-contacts can provide material for learning implicit models of the body and its action possibilities in the environment. Specifically, we investigate the space of only somatosensory (tactile and proprioceptive) activations during self-touch configurations in a simple model agent. Using biologically motivated overlapping receptive fields in these modalities, a variational autoencoder (VAE) in a denoising framework is trained on these inputs. The denoising properties of the VAE can be exploited to fill in the missing information. In particular, if tactile stimulation is provided on a single body part, the model provides a configuration that is closer to a previously experienced self-contact configuration. Iterative passes through the VAE reconstructions create a control loop that brings about reaching for stimuli on the body. Furthermore, due to the generative properties of the model, previously unsampled proprioceptive-tactile configurations can also be achieved. In the future, we will seek a closer comparison with empirical data on the kinematics of spontaneous self-touch in infants and the results of reaching for stimuli on the body.

Název v anglickém jazyce

Learning to reach to own body from spontaneous self-touch using a generative model

Popis výsledku anglicky

When leaving the aquatic constrained environment of the womb, newborns are thrown into the world with essentially new laws and regularities that govern their interactions with the environment. Here, we study how spontaneous self-contacts can provide material for learning implicit models of the body and its action possibilities in the environment. Specifically, we investigate the space of only somatosensory (tactile and proprioceptive) activations during self-touch configurations in a simple model agent. Using biologically motivated overlapping receptive fields in these modalities, a variational autoencoder (VAE) in a denoising framework is trained on these inputs. The denoising properties of the VAE can be exploited to fill in the missing information. In particular, if tactile stimulation is provided on a single body part, the model provides a configuration that is closer to a previously experienced self-contact configuration. Iterative passes through the VAE reconstructions create a control loop that brings about reaching for stimuli on the body. Furthermore, due to the generative properties of the model, previously unsampled proprioceptive-tactile configurations can also be achieved. In the future, we will seek a closer comparison with empirical data on the kinematics of spontaneous self-touch in infants and the results of reaching for stimuli on the body.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

<a href="/cs/project/GX20-24186X" target="_blank" >GX20-24186X: Vědomí celého povrchu těla pro bezpečnou a přirozenou interakci: od mozku ke kolaborativním robotům</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2022 IEEE International Conference on Development and Learning (ICDL)

ISBN

978-1-6654-1311-4

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

328-335

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

London

Datum konání akce

12. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—