What are you trying to achieve exactly? If you want to do inverse kinematics it's easier to just write the algorithm by hand, and you only need 3 inputs for the coordinates.
lfrtsa
joined 11 months ago
What are you trying to achieve exactly? If you want to do inverse kinematics it's easier to just write the algorithm by hand, and you only need 3 inputs for the coordinates.
Then you just need to do regular inverse kinematics for the position of the hand and discount the angles of the arms when setting the rotation of the hand, there's no need for machine learning at all.