Human Memory/Learning Inspired Control Method for Flapping-Wing Micro Air Vehicles

The problem of flapping motion control of Micro Air Vehicles (MAVs) with flapping wings was studied in this paper. Based upon the knowledge of skeletal and muscular components of hummingbird, a dynamic model for flapping wing was developed. A control scheme inspired by human memory and learning concept was constructed for wing motion control of MAVs. The salient feature of the proposed control lies in its capabilities to improve the control performance by learning from experience and observation on its current and past behaviors, without the need for system dynamic information. Furthermore, the overall control scheme has a fairly simple structure and demands little online computations, making it attractive for real-time implementation on MAVs. Both theoretical analysis and computer simulation confirms its effectiveness.