Trajectory Optimization and Control Method Based on Multistage Nonlinear Model Predictive Control

Abstract

To improve the trajectory optimization efficiency of robot manipulators, this paper proposes a novel approach for trajectory optimization and control of manipulators based on multistage nonlinear model predictive control (msNLMPC). This approach is realized by using a neural state space model as the prediction model of nonlinear model predictive control (NLMPC). The simulation results show that the actual trajectory of the manipulator in our proposed scheme coincides with the desired trajectory. The manipulator achieves the control task of following the optimal trajectory. Our proposed method improves the trajectory optimization efficiency of the robot manipulator.