GRU neural network robot flexible joint compensation control method based on feedback correction

The invention discloses a GRU neural network robot flexible joint compensation control method based on feedback correction, and the method comprises the steps: describing the hysteresis characteristics of a joint under different loads through the characteristics between a motor drive current reflecting the load size change and a joint torsion angle under the condition of a load torque sensor; a feedback structure is introduced on the basis of a GRU neural network, and a compensation amount is formed by using an error between a model output value and an expected output value and is fed back to a GRU neural network model for correcting an output value of the GRU neural network model so as to improve the precision of the GRU neural network model of the joint. The flexible joint hysteresis model predicts a torsion angle changing along with a load, the torsion angle is used as a compensation amount, an angle set value of a joint is modified, and effective compensation for errors caused by joint hysteresis characte