Sim-to-Real Transfer in Reinforcement Learning for Maneuver Control of a Variable-Pitch MAV
IEEE Transactions on Industrial Electronics · 2025-10 · 72 (10) · 10445-10454
DOI: 10.1109/tie.2025.3558030 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Industrial Electronics, 2025-10. Verfasst von Zhikun Wang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Reinforcement learning (RL) algorithms can enable high-maneuverability in unmanned aerial vehicles (MAVs), but transferring them from simulation to real-world use is challenging. Variable-pitch propeller (VPP) MAVs offer greater agility, yet their complex dynamics complicate the sim-to-real transfer. This article introduces a novel RL framework to overcome these challenges, enabling VPP MAVs to perform advanced aerial maneuvers in real-world settings. Our approach includes real-to-sim transfer techniques, such as system identification, domain randomization, and curriculum learning to create robust training simulations and a sim-to-real transfer strategy combining a cascade control system with a fast-response low-level controller for reliable deployment. Results demonstrate the effectiveness of this framework in achieving zero-shot deployment, enabling MAVs to perform complex maneuvers such as flips and wall-backtracking.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, Z., & Zhao, S. (2025). Sim-to-Real Transfer in Reinforcement Learning for Maneuver Control of a Variable-Pitch MAV. IEEE Transactions on Industrial Electronics, 72(10), 10445-10454. https://doi.org/10.1109/tie.2025.3558030
Vancouver
Wang Z, Zhao S. Sim-to-Real Transfer in Reinforcement Learning for Maneuver Control of a Variable-Pitch MAV. IEEE Transactions on Industrial Electronics. 2025;72(10):10445-10454. doi:10.1109/tie.2025.3558030
BibTeX
@article{Wang2025,
author = {Wang, Zhikun and Zhao, Shiyu},
title = {Sim-to-Real Transfer in Reinforcement Learning for Maneuver Control of a Variable-Pitch MAV},
journal = {IEEE Transactions on Industrial Electronics},
year = {2025},
volume = {72},
number = {10},
pages = {10445--10454},
doi = {10.1109/tie.2025.3558030}
}
EUVIMED