Abstract
In this work, we present a new approach that enables rapid learning and design of the attitude controller for quadcopters. The proposed technique leverages the dynamic structure of the system to efficiently learn an accurate linear model around the hovering position from a small batch of flight data. An LQR-based attitude controller is designed based on the estimation accordingly. In our approach, we may not need to conduct multiple experiments to fine-tune the controller and can accomplish such a control design with a single experiment. We further develop this approach into an onboard design framework where the attitude controller can be directly learned online and recursively fine-tunes itself with the limited on board computation resources. The practicality and efficacy of the proposed approaches are demonstrated in both simulation and a physical quadcopter platform.
