# Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control

arXiv: https://arxiv.org/abs/2610.06874 · HTML: https://mlsanity.com/paper/2610.06874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 53 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control](https://mlsanity.com/paper/2103.02142/) (2021)
- [What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study](https://mlsanity.com/paper/2412.11764/) (2024)
- [Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking](https://mlsanity.com/paper/2506.17832/) (2025)
- [Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows](https://mlsanity.com/paper/2408.14685/) (2024)
- [Semi-global Exponential Stability for Dual Quaternion Based Rigid-Body Tracking Control](https://mlsanity.com/paper/2305.15573/) (2023)
- [Online Adaptation for Flying Quadrotors in Tight Formations](https://mlsanity.com/paper/2506.17488/) (2025)
- [PI-WAN: A Physics-Informed Wind-Adaptive Network for Quadrotor Dynamics Prediction in Unknown Environments](https://mlsanity.com/paper/2507.00816/) (2025)
- [Wind-Aware Reinforcement Learning Control of a Small Quadrotor Using Learned Onboard Wind Estimation in Simulated Atmospheric Turbulence](https://mlsanity.com/paper/2607.01528/) (2026)

## Abstract (arXiv)

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.