Adaptive neural-fuzzy control for a nonholonomic mobile modular manipulator moving on a slope

This paper addresses the task-space trajectory following issue for a nonholonomic mobile modular manipulator, which is composed of a 4-degree-of-freedom (DOF) modular manipulator and a 3-wheeled nonholonomic mobile platform. An adaptive neural-fuzzy controller (ANFC) is presented to control the end-effector to follow a desired spacial trajectory in a 3-D space. The proposed algorithm does not need exact dynamic parameters in advance, and can suppress bounded external disturbances effectively. No off-line training process is needed for the ANFC, and all the adjustable parameters can be initialized according to expert's experience but not selected randomly. Simulation results demonstrate that the proposed controller is effective.