An Empirical Investigation on Variational Autoencoder-Based Dynamic Modeling of Deformable Objects from RGB Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00376303" target="_blank" >RIV/68407700:21730/24:00376303 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/MED61351.2024.10566173" target="_blank" >https://doi.org/10.1109/MED61351.2024.10566173</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/MED61351.2024.10566173" target="_blank" >10.1109/MED61351.2024.10566173</a>

Jazyk výsledku

angličtina

Název v původním jazyce

An Empirical Investigation on Variational Autoencoder-Based Dynamic Modeling of Deformable Objects from RGB Data

Popis výsledku v původním jazyce

Formulating the dynamics of continuously deformable objects and other mechanical systems analytically from first principles is an exceedingly challenging task, often impractical in real-world scenarios. What makes this challenge even harder to solve is that, usually, the object has not been observed previously, and the only information that we can get from it is a stream of RGB camera data. In this study, we explore the use of deep learning techniques to solve this nonlinear identification problem. We specifically focus on extracting dynamic models of simple deformable objects from the high-dimensional sensor input coming from an RGB camera. We investigate a two-stage approach to achieve this goal. First, we train a variational autoencoder to extract an extremely low-dimensional representation of the object configuration. Then, we learn a dynamic model that predicts the evolution of these latent space variables. The proposed architecture can accurately predict the object's state up to one second into the future.

Název v anglickém jazyce

An Empirical Investigation on Variational Autoencoder-Based Dynamic Modeling of Deformable Objects from RGB Data

Popis výsledku anglicky

Formulating the dynamics of continuously deformable objects and other mechanical systems analytically from first principles is an exceedingly challenging task, often impractical in real-world scenarios. What makes this challenge even harder to solve is that, usually, the object has not been observed previously, and the only information that we can get from it is a stream of RGB camera data. In this study, we explore the use of deep learning techniques to solve this nonlinear identification problem. We specifically focus on extracting dynamic models of simple deformable objects from the high-dimensional sensor input coming from an RGB camera. We investigate a two-stage approach to achieve this goal. First, we train a variational autoencoder to extract an extremely low-dimensional representation of the object configuration. Then, we learn a dynamic model that predicts the evolution of these latent space variables. The proposed architecture can accurately predict the object's state up to one second into the future.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

32nd Mediterranean Conference on Control and Automation (MED)

ISBN

979-8-3503-9545-7

ISSN

2325-369X

e-ISSN

2473-3504

Počet stran výsledku

8

Strana od-do

921-928

Název nakladatele

IEEE Xplore

Místo vydání

—

Místo konání akce

Chania, Kréta

Datum konání akce

11. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—