Distributionally robust model predictive control for constrained robotic manipulators based on neural network modeling

A distributionally robust model predictive control (DRMPC) scheme is proposed based on neural network (NN) modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraints. First, an NN is used to fit the motion data of robot manipulators for data-driven dynamic modeling, converting it into a linear prediction model through gradients. Then, by statistically analyzing the stochastic characteristics of the NN modeling errors, a distributionally robust model predictive controller is designed based on the chance constraints, and the optimization problem is transformed into a tractable quadratic programming (QP) problem under the distributionally robust optimization (DRO) framework. The recursive feasibility and convergence of the proposed algorithm are proven. Finally, the effectiveness of the proposed algorithm is verified through numerical simulation.