The inverse kinematics problem in robotics can be formulated as a time-vary
ing quadratic optimization problem. A new recurrent neural network, called
the dual network, is presented in this paper. The proposed neural network i
s composed of a single layer of neurons, and the number of neurons is equal
to the dimensionality of the workspace. The proposed dual network is prove
n to be globally exponentially stable. The proposed dual network is also sh
own to be capable of asymptotic tracking for the motion control of kinemati
cally redundant manipulators.