Learning control for underwater robot manipulators

摘要

We propose a learning control for underwater robot manipulators. Th the water, the additional forces and moments called added mass, hydrodynamic damping and buoyancy act on the manipulator and it is difficult to estimate these forces and moments. The input torque pattern of the learning control is modified by the tracking error without estimating added mass, hydrodynamic damping and buoyancy. In this paper, the problem of convergence of tracking errors is discussed and the effectiveness of the learning control in the water is demonstrated through experimental results.