Figure 5
From: A biologically inspired neural network controller for ballistic arm movements
Diagram of the exploration and the learning process. (1) The arm starts in the position defined by the angle q1 and q2(Cartesian position xs, ys), while the desired target position is defined by q1d and q2d (Cartesian position xd and yd). The angles q1' and q2' univocally define the spatial configuration of the arm in the arrival point (Cartesian position xa, ya) (2), that in the early phases of the learning process is different from the desired one: the ANN learns the association between the starting point and the arrival point (3).