A Learning-Based Anti-Swing Trajectory Refinement Approach for UAVs With Cable-Suspended Payload Without Offline Training

Abstract

In this article, a learning-based anti-swing trajectory refinement approach for unmanned aerial vehicles (UAVs) with cable-suspended payload is proposed to achieve the quadrotor's actual position and the payload's swing suppression. Specifically, the proposed trajectory is composed of two parts, one is for guaranteeing the position of the quadrotor, and the other is for suppressing the payload's swing online. The first part of the generated trajectory is related to an arbitrary given trajectory, and the second part is a neural network based term with designed online updating weights. The convergence of the quadrotor position error and payload swing angles are proved by Lyapunov-based analysis. Simulation results are presented to validate the effectiveness of the proposed method.