Adaptive NN motion control and predictive coordinate planning for aerial manipulators

Abstract

The aerial manipulator has attracted great interest since it can interact with the environment through its end-effector. This paper divides the end-effector position tracking control task for the aerial manipulator into two subtasks. The first is motion control, and the second is coordinate planning so that the end-effector of the aerial manipulator can precisely track the given trajectory. The motion control of the aerial manipulator is solved by a partially coupled approach and divided into a multirotor controller and a manipulator controller. The motion controller is designed by the adaptive neural network control. By resorting to radial basis function neural networks with adaptive weight estimation laws, the dynamic couplings between the multirotor and the manipulator can be compensated in real time. With the support of Lyapunov stability criteria, it is proved that the desired trajectories can be boundedly tracked by the multirotor under the proposed controller. Then, a novel predictive coordinate planning method is proposed based on the move blocking method. This method ensures that the solution satisfies physical limits of the aerial manipulator and can be executed in real time. Simulations and comparisons demonstrate effectiveness and performance of the proposed methods.