Search papers, labs, and topics across Lattice.
This paper introduces an online learning algorithm that optimizes airflow control in a multi-fan vertical wind tunnel, crucial for testing unmanned aerial vehicles (UAVs) in tailored environments. By integrating a simplified physical model with iterative, measurement-based learning, the method achieves sample-efficient convergence to complex airflow profiles, including those specifically designed for passive soaring. The results demonstrate significant enhancements in flight performance, showcasing the algorithm's adaptability and robustness across varying fan configurations.
Tailored airflow profiles for UAVs can now be generated on-the-fly, dramatically improving flight performance and experimental efficiency.
The development and testing of advanced aerial robots require experiments in controlled environments with tailored airflow profiles. This paper presents an online learning algorithm for controlling the complex airflow field in a multi-fan vertical wind tunnel. Our method combines a simplified physical model with iterative, measurement-based learning, enabling sample-efficient convergence to desired airflow distributions. We demonstrate the method's versatility by generating complex airflow, such as uniform, Gaussian, and parabolic profiles. Crucially, we show that our algorithm can produce an airflow profile specifically designed for passive soaring, greatly enhancing flight performance of a soaring robot. Variability, practical utility, and robustness of our approach are further highlighted by successful operation with a varying number of fans.
