Hybrid Reinforcement Learning Control for a Micro Quadrotor Flight

This letter presents a combination of reinforcement learning (RL) and deterministic controllers to learn a quadrotor control. Learning the quadrotor flight in a standard RL approach requires many iterations of trial and error, which may bring about risky exploration and battery consumption. In this letter, we integrate a classical controller such as PD (proportional and derivative) or LQR (linear quadratic regulator) with a RL policy using their linear combination. The proposed method is not only simple to use, but also fast in learning convergence. When the algorithm is evaluated for a quadrotor trajectory tracking by means of a velocity control for both simulation and experiment, it demonstrates the faster convergence rate and better control performance in comparison with an existing rapid model-based RL method.

Automated summary

The proposed method combines reinforcement learning and deterministic controllers to learn quadrotor control, which is not only simple to use but also fast in learning convergence. It demonstrates faster convergence rate and better control performance compared to an existing rapid model-based RL method when evaluated for quadrotor trajectory tracking.