FlapKAD provides aligned data on wing motion and flight forces
FlapKAD: A Simulation Dataset of Coupled Wing Kinematics and Aerodynamic Dynamics for Flapping-Wing Aerial Vehicles
Robotics
Summary
Flying robots with flapping wings are hard to study because wing movements and their effects on flight happen very quickly and are tricky to measure together. To solve this, the authors created FlapKAD, a large simulated dataset that perfectly matches wing motions and the resulting forces and flight states over time. They also tested different computer models to predict forces from wing movements and vice versa but found that more complex models don't always do better. This dataset makes it easier to understand and improve flapping-wing flight by giving a clear and large source of data.
What this means in practice
- •For aerial robotics developers: Access a large, well-aligned dataset for training and testing models that predict forces and wing movements in flapping-wing drones.
- •For drone control engineers: Use the dataset to improve control algorithms by better understanding the link between wing motions and resulting aerodynamic forces.
Authors
Haichuan Li
Abstract
Experimental investigation and modeling of flapping-wing aerial vehicles are limited by the scarcity of large-scale records that temporally align wing kinematics, aerodynamic responses, and flight states. Existing datasets are often limited in scale and affected by measurement noise and temporal misalignment between rapidly varying wing motion and the associated dynamic response, particularly during high-frequency flapping. We introduce FlapKAD, an episode-structured simulation dataset comprising 2,000 rigid-wing flight episodes and 720,152 valid time steps, with bilateral wing kinematics, aerodynamic responses, and flight states recorded synchronously within a common clock. FlapKAD supports a unified bidirectional sequence-prediction benchmark constructed from the same temporally aligned episodes. The forward task predicts future vertical force coefficients and body vertical velocity from histories of realized flap and twist angles, whereas the inverse task reconstructs future flap- and twist-angle trajectories from the corresponding response histories. A benchmark of eight representative time-series architectures across multiple prediction horizons reveals direction- and horizon-dependent model behavior, systematically higher reconstruction errors for twist angle than for flap angle, and no consistent advantage from increased architectural complexity. FlapKAD provides a reproducible dataset and benchmark for studying coupled wing-kinematic, aerodynamic, and flight-state dynamics in flapping-wing aerial vehicles.