An Interpretable Data-Driven Model of the Flight Dynamics of Hawks

2026-02-22

AI Summary

Existing models of avian flight dynamics lack generative capacity and verifiability, hindering insights into the multi-objective coordination underlying agile flight. This study addresses this gap by leveraging high-fidelity motion capture data from eagles to construct an interpretable, data-driven model using Dynamic Mode Decomposition (DMD). Complex behaviors—such as flapping, turning, and gliding—are represented as linear combinations of a shared set of low-dimensional dynamic modes. Remarkably, the research reveals that diverse eagle individuals utilize a common modal basis, enabling accurate reconstruction and extrapolation of natural flight trajectories with only three to four parameters: three capturing flapping dynamics and one integrating turning maneuvers. By circumventing the restrictive assumptions and limited testability of traditional physics-based models, this approach establishes a novel paradigm for modeling biological flight.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Despite significant analysis of bird flight, generative physics models for flight dynamics do not currently exist. Yet the underlying mechanisms responsible for various flight manoeuvres are important for understanding how agile flight can be accomplished. Even in a simple flight, multiple objectives are at play, complicating analysis of the overall flight mechanism. Using the data-driven method of dynamic mode decomposition (DMD) on motion capture recordings of hawks, we show that multiple behavioral states such as flapping, turning, landing, and gliding, can be modeled by simple and interpretable modal structures (i.e. the underlying wing-tail shape) which can be linearly combined to reproduce the experimental flight observations. Moreover, the DMD model can be used to extrapolate naturalistic flapping. Flight is highly individual, with differences in style across the hawks, but we find they share a common set of dynamic modes. The DMD model is a direct fit to data, unlike traditional models constructed from physics principles which can rarely be tested on real data and whose assumptions are typically invalid in real flight. The DMD approach gives a highly accurate reconstruction of the flight dynamics with only three parameters needed to characterize flapping, and a fourth to integrate turning manoeuvres. The DMD analysis further shows that the underlying mechanism of flight, much like simplest walking models, displays a parametric coupling between dominant modes suggesting efficiency for locomotion.

Problem

• flight dynamics
• bird flight
• agile flight
• maneuverability
• generative models

Innovation

• Dynamic Mode Decomposition
• interpretable modeling
• avian flight dynamics
• data-driven biomechanics
• modal decomposition