Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00373781" target="_blank" >RIV/68407700:21230/23:00373781 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TCDS.2023.3239815" target="_blank" >https://doi.org/10.1109/TCDS.2023.3239815</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TCDS.2023.3239815" target="_blank" >10.1109/TCDS.2023.3239815</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

Popis výsledku v původním jazyce

The recent advancement of deep reinforcement learning (DRL) contributed to robotics by allowing automatic controller design. The automatic controller design is a crucial approach for designing swarm robotic systems, which require more complex controllers than a single robot system to lead a desired collective behavior. Although the DRL-based controller design method showed its effectiveness for swarm robotic systems, the reliance on the central training server is a critical problem in real-world environments where robot-server communication is unstable or limited. We propose a novel federated learning (FL)-based DRL training strategy federated learning DDPG (FLDDPG) for use in swarm robotic applications. Through the comparison with baseline strategies under a limited communication bandwidth scenario, it is shown that the FLDDPG method resulted in higher robustness and generalization ability into a different environment and real robots, while the baseline strategies suffer from the limitation of communication bandwidth. This result suggests that the proposed method can benefit swarm robotic systems operating in environments with limited communication bandwidth, e.g., in high radiation, underwater, or subterranean environments.

Název v anglickém jazyce

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

Popis výsledku anglicky

The recent advancement of deep reinforcement learning (DRL) contributed to robotics by allowing automatic controller design. The automatic controller design is a crucial approach for designing swarm robotic systems, which require more complex controllers than a single robot system to lead a desired collective behavior. Although the DRL-based controller design method showed its effectiveness for swarm robotic systems, the reliance on the central training server is a critical problem in real-world environments where robot-server communication is unstable or limited. We propose a novel federated learning (FL)-based DRL training strategy federated learning DDPG (FLDDPG) for use in swarm robotic applications. Through the comparison with baseline strategies under a limited communication bandwidth scenario, it is shown that the FLDDPG method resulted in higher robustness and generalization ability into a different environment and real robots, while the baseline strategies suffer from the limitation of communication bandwidth. This result suggests that the proposed method can benefit swarm robotic systems operating in environments with limited communication bandwidth, e.g., in high radiation, underwater, or subterranean environments.

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

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

2023

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Cognitive and Developmental Systems

ISSN

2379-8920

e-ISSN

2379-8939

Svazek periodika

15

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

10

Strana od-do

2122-2131

Kód UT WoS článku

001126639000051

EID výsledku v databázi Scopus

2-s2.0-85147295543