Deep Reinforcement Learning-Based Adaptive Controller for Trajectory Tracking and Altitude Control of an Aerial Robot

摘要

This research study presents a new adaptive attitude and altitude controller for an aerial robot. The proposed controlling approach employs a reinforcement learning-based algorithm to actively estimate the controller parameters of the aerial robot. In dealing with highly nonlinear systems and parameter uncertainty, the proposed RL-based adaptive control algorithm has advantages over some types of standard control approaches. When compared to the conventional proportional integral derivative (PID) controllers, the results of the numerical simulation demonstrate the effectiveness of this intelligent control strategy, which can improve the control performance of the whole system, resulting in accurate trajectory tracking and altitude control of the vehicle.