Wing-strain-based flight control of flapping-wing drones through reinforcement learning

Current drone technology struggles to replicate the dynamic control and wind-sensing capabilities of biological flight. This research demonstrates a wing-strain-based flight controller for flapping-wing drones, using reinforcement learning to leverage aerodynamic forces for flight data acquisition (attitude and airflow) without traditional sensors (accelerometers and gyroscopic sensors). Through five experiments – sensor validation, single/two degree-of-freedom control, position control in wind, and precise flight path manipulation – the researchers successfully controlled a flapping drone in varied environments using only wing strain sensors. This adaptable system improves gust resistance and enables wind-assisted flight for autonomous robots.

Taewi Kim, Insic Hong, Sunghoon Im, Seungeun Rho, Minho Kim, Yeonwook Roh, Changhwan Kim, Jieun Park, Daseul Lim, Doohoe Lee, Seunggon Lee, Jingoo Lee, Inryeol Back, Junggwang Cho, Myung Rae Hong, Sanghun Kang, Joonho Lee, Sungchul Seo, Uikyum Kim, Young-Man Choi, Je-sung Koh, Seungyong Han, Daeshik Kang