Attitude feedforward neural controller in quaternion algebra

In the paper. in order to deal with the attitude control problem of a rigid body in a 3-D space, a new control strategy in hypercomplex algebra is dev eloped. The proposed approach is based on two parallel controllers derived in quaternion algebra. The first one is a feedback controller of PD type, w hile the second is a feed-forward controller implemented by means of an hyp ercomplex multilayer perceptron (HMLP) neural network. Quaternion algebra a llows to simplify the computational complexity of the controllers and leads to a more efficient learning algorithm for the neural network. Several sim ulations and comparisons with other control strategies show the suitability of the proposed approach.