An Improved Data-Driven Calibration Method with High Efficiency for a 6-DOF Hybrid Robot

This paper proposes an improved data-driven calibration method for a six degrees of freedom (DOF) hybrid robot. It focuses mainly on improving the measurement efficiency and practicability of existing data-driven calibration methods through the following approaches. (1) The arbitrary motion of the hybrid robot is equivalently decomposed into three independent sub-motions by motion decomposition. Sequentially, the sub-motions are combined according to specific motion rules. Then, a large number of robot poses can be acquired in the whole workspace via a limited number of measurements, effectively solving the curse of dimensionality in measurement. (2) A mapping between the nominal joint variables and joint compensation values is established using a back propagation neural network (BPNN), which is trained directly using the measurement data through a unique algorithm involving inverse kinematics. Thus, the practicability of data-driven calibration is significantly improved. The validation experiments are carried out on a TriMule-200 robot. The results show that the robot's maximal position/orientation errors are reduced by 91.16%/88.17% to 0.085 mm/0.022 deg, respectively, after calibration.