Predictive Data Acquisition for Lifelong Visual Teach, Repeat and Learn

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376055" target="_blank" >RIV/68407700:21230/24:00376055 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/LRA.2024.3421193" target="_blank" >https://doi.org/10.1109/LRA.2024.3421193</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/LRA.2024.3421193" target="_blank" >10.1109/LRA.2024.3421193</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Predictive Data Acquisition for Lifelong Visual Teach, Repeat and Learn

Popis výsledku v původním jazyce

Nowadays, robots can operate in environments which are not tailored for them. This allows their deployments in changing and human-populated environments, which recent advances in machine learning methods enabled. The efficiency of these methods is largely determined by the quality of their training data. An up-to-date and well-balanced training dataset is paramount for achieving robust robot operation. To achieve long-term operation, the robot has to deal with perpetual environmental changes, forcing it to keep its models up-to-date. We present an exploration method allowing a mobile robot to gather high-quality data to update its models both while performing its duties and when idle, maximizing effectivity. The robot evaluates the quality of the data gathered in the past and based on that, it creates preferences which influence how often these locations are visited. This exploration method was integrated with a self-supervised visual teach-and-repeat pipeline. We show the precision and robustness of visual-based navigation to improve when using machine-learned models trained by our exploration method. Our research resulted in a robotic navigation system that can not only annotate its training data but also ensure that its training dataset is balanced and up-to-date. The codes, datasets, trained models and examples for our experiments can be found online for better reproducibility at .

Název v anglickém jazyce

Predictive Data Acquisition for Lifelong Visual Teach, Repeat and Learn

Popis výsledku anglicky

Nowadays, robots can operate in environments which are not tailored for them. This allows their deployments in changing and human-populated environments, which recent advances in machine learning methods enabled. The efficiency of these methods is largely determined by the quality of their training data. An up-to-date and well-balanced training dataset is paramount for achieving robust robot operation. To achieve long-term operation, the robot has to deal with perpetual environmental changes, forcing it to keep its models up-to-date. We present an exploration method allowing a mobile robot to gather high-quality data to update its models both while performing its duties and when idle, maximizing effectivity. The robot evaluates the quality of the data gathered in the past and based on that, it creates preferences which influence how often these locations are visited. This exploration method was integrated with a self-supervised visual teach-and-repeat pipeline. We show the precision and robustness of visual-based navigation to improve when using machine-learned models trained by our exploration method. Our research resulted in a robotic navigation system that can not only annotate its training data but also ensure that its training dataset is balanced and up-to-date. The codes, datasets, trained models and examples for our experiments can be found online for better reproducibility at .

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</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

2024

Kód důvěrnosti údajů

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

Název periodika

IEEE Robotics and Automation Letters

ISSN

2377-3766

e-ISSN

2377-3766

Svazek periodika

9

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

8

Strana od-do

10042-10049

Kód UT WoS článku

001329045100010

EID výsledku v databázi Scopus

2-s2.0-85197555308