MyGym: Modular Toolkit for Visuomotor Robotic Tasks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F21%3A00354192" target="_blank" >RIV/68407700:21730/21:00354192 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICTAI52525.2021.00046" target="_blank" >https://doi.org/10.1109/ICTAI52525.2021.00046</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICTAI52525.2021.00046" target="_blank" >10.1109/ICTAI52525.2021.00046</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MyGym: Modular Toolkit for Visuomotor Robotic Tasks

Popis výsledku v původním jazyce

We introduce myGym, a toolkit suitable for fast prototyping of neural networks in the area of robotic manipulation and navigation. Our toolbox is fully modular, enabling users to train their algorithms on different robots, environments, and tasks. We also include pretrained neural network modules for the real-time vision that allows training visuomotor tasks with sim2real transfer. The visual modules can be easily retrained using the dataset generation pipeline with domain augmentation and randomization. Moreover, myGym provides automatic evaluation methods and baselines that help the user to directly compare their trained model with the state-of-the-art algorithms. We additionally present a novel metric, called learnability, to compare the general learning capability of algorithms in different settings, where the complexity of the environment, robot, and the task is systematically manipulated. The learnability score tracks differences between the performance of algorithms in increasingly challenging setup conditions, and thus allows the user to compare different models in a more systematic fashion. The code is accessible at https://github.com/incognite-lab/myGym

Název v anglickém jazyce

MyGym: Modular Toolkit for Visuomotor Robotic Tasks

Popis výsledku anglicky

We introduce myGym, a toolkit suitable for fast prototyping of neural networks in the area of robotic manipulation and navigation. Our toolbox is fully modular, enabling users to train their algorithms on different robots, environments, and tasks. We also include pretrained neural network modules for the real-time vision that allows training visuomotor tasks with sim2real transfer. The visual modules can be easily retrained using the dataset generation pipeline with domain augmentation and randomization. Moreover, myGym provides automatic evaluation methods and baselines that help the user to directly compare their trained model with the state-of-the-art algorithms. We additionally present a novel metric, called learnability, to compare the general learning capability of algorithms in different settings, where the complexity of the environment, robot, and the task is systematically manipulated. The learnability score tracks differences between the performance of algorithms in increasingly challenging setup conditions, and thus allows the user to compare different models in a more systematic fashion. The code is accessible at https://github.com/incognite-lab/myGym

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

<a href="/cs/project/EF16_019%2F0000766" target="_blank" >EF16_019/0000766: Inženýrské aplikace fyziky mikrosvěta</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI)

ISBN

978-1-6654-0898-1

ISSN

1082-3409

e-ISSN

2375-0197

Počet stran výsledku

5

Strana od-do

279-283

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Washington

Datum konání akce

1. 11. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000747482300038