Exploring the power of heterogeneous UAV swarms through reinforcement learning

Yosyp Albrekht () and Andrii Pysarenko
Additional contact information
Yosyp Albrekht: National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute»
Andrii Pysarenko: National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute»

Technology audit and production reserves, 2023, vol. 6, issue 2(74), 6-10

Abstract: The object of research is heterogeneous and homogeneous swarms of unmanned aerial vehicles (UAVs). The primary focus of this study is the comparison between heterogeneous and homogeneous UAV swarms, examining their performance in a simulated environment designed using the Python Gym library. The research involves implementing reinforcement learning algorithms, specifically the Proximal Policy Optimization (PPO), to train and evaluate the swarms.The central issue addressed by this research is to determine which type of UAV swarm – heterogeneous or homogeneous – exhibits better performance in a defined task. The chosen task involves searching for groups of objects in an unknown area, emphasizing the ability of the swarm to adapt and efficiently locate objects in dynamic environments.The obtained results reveal an advantage for heterogeneous UAV swarms over their homogeneous counterparts. The heterogeneous swarm has a steeper learning curve and achieves higher rewards in fewer episodes during the training phase. The key finding indicates that the varied skill set within the heterogeneous swarm allows for quicker adaptation to changing environmental conditions. The superior performance of the heterogeneous swarm is attributed to the diversity of capabilities among its UAV agents, enabling them to leverage their individual strengths to achieve better overall performance in the given task.The practical application of these results is contingent upon the task requirements and environmental conditions. In scenarios where tasks demand diverse skills and adaptability to changing conditions, heterogeneous UAV swarms are recommended. The results suggest their efficacy in applications such as search and rescue operations, environmental monitoring, and other dynamic tasks.In conclusion, this research provides valuable insights into optimizing UAV swarm composition for specific tasks. The results contribute both theoretically and practically by highlighting the advantages of heterogeneity in swarm capabilities.

Keywords: reinforcement learning; robot swarms; heterogeneous swarms; UAV swarms; heterogeneous UAV swarms (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.uran.ua/tarp/article/download/293063/286094 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:baq:taprar:v:6:y:2023:i:2:p:6-10

DOI: 10.15587/2706-5448.2023.293063

Access Statistics for this article

More articles in Technology audit and production reserves from PC TECHNOLOGY CENTER
Bibliographic data for series maintained by Iryna Prudius ().