Cooperative Transportation of Slender Payload with Two Quadrotors Using Deep Learning–Based Control

The cooperative aerial transportation of cable-suspended payloads using multiple quadrotors has emerged as a critical area of research due to its broad applications. However, precise position control and effective swing suppression of the payload remain significant challenges, primarily due to the highly nonlinear and coupled dynamics of the system as well as the external disturbances. To address these issues, this study proposes a deep learning–based control framework for a two-quadrotor system transporting a cable-suspended slender payload. A Lagrangian model is chosen to describe such a cooperative transportation system, and a nonlinear model predictive control (NMPC) scheme combined with a proportional-derivative (PD) controller is employed to generate high-quality training data. A deep neural network (DNN) is then trained to approximate the NMPC controller, enabling real-time control for precise quadrotor positioning and payload swing suppression. Simulation and experimental results are presented to validate the effectiveness and robustness of the proposed control strategy.