Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control
Abstract
Reinforcement-learning quadrotor controllers are usually trained under simplified wind models, yet the impact of wind-field fidelity, as opposed to magnitude, on policy robustness remains unquantified. This paper compares five disturbance-fidelity levels, from wind-free flight and discrete 1-cosine gusts through statistical turbulence and synthetic coherent structures to large-eddy-simulation fields of the atmospheric boundary layer, in a full cross-fidelity train test evaluation of proximal policy optimization (PPO) agents, with cascaded PID and geometric SE(3) controllers as training-free references, over a 0-12 m/s wind sweep. Before any controller comparison is made, all disturbance data are validated: every synthetic generator is checked quantitatively against its analytical or certification-standard reference, and the large-eddy-simulation fields against the imposed log law. On a racing-class quadrotor in hover, the train test matrix is remarkably flat, and the cheapest structured training wind, which is discrete-gust domain randomization, ranks first in every test column, a ranking replicated on a wind-sensitive 27 g platform; a once-tuned geometric controller brackets the learned PPO policies at zero crash rate. Mechanism diagnostics show that control authority, not wind realism, bounds robustness, so wind-fidelity investment should scale with platform wind sensitivity.
Related
- Residual-activated smooth sliding-mode control for actuator-limited quadrotor UAV attitude–altitude tracking
- Full Poincaré Beam Through Fresnel-Scaled FSO Turbulence: An Experimental Statistical Investigation and Performance Analysis
- A high-fidelity numerical database for free-stream-turbulence-induced transition under varying pressure gradients
- Integrable turbulence and statistical properties of chaotic wave fields in the complex modified Korteweg-de Vries equation
- Dynamical and statistical properties of large scales in turbulence
BibTeX
@misc{huang2026statistical,
title = {{Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control}},
author = {Xun Huang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.06874},
eprint = {2610.06874},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.06874},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control
AU - Xun Huang
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.06874
UR - https://arxiv.org/abs/2610.06874
AB - Reinforcement-learning quadrotor controllers are usually trained under simplified wind models, yet the impact of wind-field fidelity, as opposed to magnitude, on policy robustness remains unquantified. This paper compares five disturbance-fidelity levels, from wind-free flight and discrete 1-cosine gusts through statistical turbulence and synthetic coherent structures to large-eddy-simulation fields of the atmospheric boundary layer, in a full cross-fidelity train test evaluation of proximal policy optimization (PPO) agents, with cascaded PID and geometric SE(3) controllers as training-free references, over a 0-12 m/s wind sweep. Before any controller comparison is made, all disturbance data are validated: every synthetic generator is checked quantitatively against its analytical or certification-standard reference, and the large-eddy-simulation fields against the imposed log law. On a racing-class quadrotor in hover, the train test matrix is remarkably flat, and the cheapest structured training wind, which is discrete-gust domain randomization, ranks first in every test column, a ranking replicated on a wind-sensitive 27 g platform; a once-tuned geometric controller brackets the learned PPO policies at zero crash rate. Mechanism diagnostics show that control authority, not wind realism, bounds robustness, so wind-fidelity investment should scale with platform wind sensitivity.
ER -