NeuroBEM: Hybrid Aerodynamic Quadrotor Model

TL;DR

NeuroBEM introduces a hybrid modeling approach combining first principles and learning to accurately predict aerodynamic effects in high-speed quadrotor flight, surpassing existing models in accuracy and generalization.

Contribution

The paper presents a novel hybrid modeling method that unifies physics-based and data-driven techniques to improve quadrotor aerodynamic modeling at high speeds.

Findings

50% reduction in prediction errors compared to existing models

Accurately captures aerodynamic thrust, torques, and parasitic effects

Demonstrates strong generalization beyond training conditions

Abstract

Quadrotors are extremely agile, so much in fact, that classic first-principle-models come to their limits. Aerodynamic effects, while insignificant at low speeds, become the dominant model defect during high speeds or agile maneuvers. Accurate modeling is needed to design robust high-performance control systems and enable flying close to the platform's physical limits. We propose a hybrid approach fusing first principles and learning to model quadrotors and their aerodynamic effects with unprecedented accuracy. First principles fail to capture such aerodynamic effects, rendering traditional approaches inaccurate when used for simulation or controller tuning. Data-driven approaches try to capture aerodynamic effects with blackbox modeling, such as neural networks; however, they struggle to robustly generalize to arbitrary flight conditions. Our hybrid approach unifies and outperforms both first-principles blade-element theory and learned residual dynamics. It is evaluated in one of the world's largest motion-capture systems, using autonomous-quadrotor-flight data at speeds up to 65km/h. The resulting model captures the aerodynamic thrust, torques, and parasitic effects with astonishing accuracy, outperforming existing models with 50% reduced prediction errors, and shows strong generalization capabilities beyond the training set.