Chattering Reduction of Sliding Mode Control for Quadrotor UAVs Based on Reinforcement Learning

Sliding mode control, an algorithm known for its stability and robustness, has been widely used in designing robot controllers. Such controllers inevitably exhibit chattering; numerous methods have proposed to deal with this problem the past decade. However, most scenarios, ensuring that specified form parameters selected are optimal system is challenging. In work, reinforcement-learning method adopted explore nonlinear function reduce chattering. Based on a conventional reference model sliding network output directly participates controller calculation without any restrictions. Additionally, two-step verification proposed, including simulation under input delay external disturbance actual experiments using quadrotor. Two types of classic chattering reduction implemented same basic comparison. The experiment results indicate could effectively better tracking performance.