EUVIMEDEUVIMED entdecken
Crossref

Digital Twin‐Enabled Deep Reinforcement Learning for Safety‐Guaranteed Flocking Motion of UAV Swarm

Zhilin Li, Lei Lei, Gaoqing Shen, Xiaochang Liu, Xiaojiao Liu

Transactions on Emerging Telecommunications Technologies · 2024-11 · 35 (11)

DOI: 10.1002/ett.70011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions on Emerging Telecommunications Technologies, online erschienen am 06.11.2024. Verfasst von Zhilin Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi‐agent deep reinforcement learning (MADRL) has become a typical paradigm for the flocking motion of UAV swarm in dynamic, stochastic environments. However, sim‐to‐real problems, such as reality gap, training efficiency, and safety issues, restrict the application of MADRL in flocking motion scenarios. To address these problems, we first propose a digital twin (DT)‐enabled training framework. With the assistance of high‐fidelity digital twin simulation, effective policies can be efficiently trained. Based on the multi‐agent proximal policy optimization (MAPPO) algorithm, we then design the learning approach for flocking motion with matching observation space, action space, and reward function. Afterward, we employ a distributed flocking center estimation algorithm based on position consensus. The estimated center is used as a policy input to improve the aggregation behavior. Moreover, we introduce a repulsion scheme, which applies an additional repulsion force to the action to prevent UAVs from colliding with neighbors and obstacles. Simulation results show that our method performs well in maintaining flocking formation and avoiding collisions, and has better decision‐making ability in near‐realistic environments.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Lei, L., Shen, G., Liu, X., & Liu, X. (2024). Digital Twin‐Enabled Deep Reinforcement Learning for Safety‐Guaranteed Flocking Motion of UAV Swarm. Transactions on Emerging Telecommunications Technologies, 35(11). https://doi.org/10.1002/ett.70011

Vancouver

Li Z, Lei L, Shen G, Liu X, Liu X. Digital Twin‐Enabled Deep Reinforcement Learning for Safety‐Guaranteed Flocking Motion of UAV Swarm. Transactions on Emerging Telecommunications Technologies. 2024;35(11). doi:10.1002/ett.70011

BibTeX
@article{Li2024,
  author = {Li, Zhilin and Lei, Lei and Shen, Gaoqing and Liu, Xiaochang and Liu, Xiaojiao},
  title = {Digital Twin‐Enabled Deep Reinforcement Learning for Safety‐Guaranteed Flocking Motion of UAV Swarm},
  journal = {Transactions on Emerging Telecommunications Technologies},
  year = {2024},
  volume = {35},
  number = {11},
  doi = {10.1002/ett.70011}
}
Kostenlos starten →