The invention discloses a six-axes
robot kinetic parameter identification method based on a neural network. The six-axes
robot kinetic parameter identification method comprises the following steps that firstly,
robot kinetic modeling and
linearization are conducted; secondly, motivation
trajectory optimization is conducted, and specifically a motivation trajectory is optimized through an
artificial immune algorithm; thirdly, experiment sampling is conducted, specifically a robot moves along the motivation trajectory, and multiple sets of observation matrices and joint torque are obtained as experiment data; fourthly,
data processing is conducted, the data collected in an experiment are preprocessed through a three standard deviation norm and a median
average filter method, and the influence brought by
data noise is lowered; fifthly, kinetic parameter
estimation is conducted, and kinetic parameters are estimated through the neural network; and sixthly, parameter
verification is conducted, the robot follows an
executable trajectory different from the motivation trajectory, experiment data are sampled again, theoretical joint torque is predicted according to kinetic parameters obtained by identification, and reliability of the identified kinetic parameters is evaluated with the torque residual root.