João M. Lemos

The problem addressed in this article consists of the motion control of a quadrotor affected by model disturbances and uncertainties. In order to tackle model uncertainty, adaptive control based on reinforcement learning is used. The distinctive feature of this article, in comparison with other works on quadrotor control using reinforcement learning, is the exploration of the underlying optimal control problem in which a quadratic cost and a linear dynamics allow for an algorithm that runs in real time. Instead of identifying a plant model, adaptation is obtained by approximating the performance index given by the Q-function using directional forgetting recursive least squares that rely on a linear regressor built from quadratic functions of input/output data. The adaptive algorithm proposed is tested in simulation in a cascade control structure that drives a quadrotor. Simulations show the improvement in performance that results when the proposed algorithm is turned on.