Bio-inspired visual relative localization for large swarms of UAVs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00373576" target="_blank" >RIV/68407700:21230/24:00373576 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICRA57147.2024.10610100" target="_blank" >https://doi.org/10.1109/ICRA57147.2024.10610100</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICRA57147.2024.10610100" target="_blank" >10.1109/ICRA57147.2024.10610100</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Bio-inspired visual relative localization for large swarms of UAVs

Popis výsledku v původním jazyce

We propose a new approach to visual perception for relative localization of agents within large-scale swarms of UAVs. Inspired by biological perception utilized by schools of sardines, swarms of bees, and other large groups of animals capable of moving in a decentralized yet coherent manner, our method does not rely on detecting individual neighbors by each agent and estimating their relative position, but rather we propose to regress a neighbor density over distance. This allows for a more accurate distance estimation as well as better scalability with respect to the number of neighbors. Additionally, a novel swarm control algorithm is proposed to make it compatible with the new relative localization method. We provide a thorough evaluation of the presented methods and demonstrate that the regressing approach to distance estimation is more robust to varying relative pose of the targets and that it is suitable to be used as the main source of relative localization for swarm stabilization.

Název v anglickém jazyce

Bio-inspired visual relative localization for large swarms of UAVs

Popis výsledku anglicky

We propose a new approach to visual perception for relative localization of agents within large-scale swarms of UAVs. Inspired by biological perception utilized by schools of sardines, swarms of bees, and other large groups of animals capable of moving in a decentralized yet coherent manner, our method does not rely on detecting individual neighbors by each agent and estimating their relative position, but rather we propose to regress a neighbor density over distance. This allows for a more accurate distance estimation as well as better scalability with respect to the number of neighbors. Additionally, a novel swarm control algorithm is proposed to make it compatible with the new relative localization method. We provide a thorough evaluation of the presented methods and demonstrate that the regressing approach to distance estimation is more robust to varying relative pose of the targets and that it is suitable to be used as the main source of relative localization for swarm stabilization.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

2024 IEEE International Conference on Robotics and Automation (ICRA)

ISBN

979-8-3503-8457-4

ISSN

1050-4729

e-ISSN

2577-087X

Počet stran výsledku

7

Strana od-do

11825-11831

Název nakladatele

IEEE Industrial Electronic Society

Místo vydání

Vienna

Místo konání akce

Yokohama

Datum konání akce

13. 5. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001369728002056