Using a robot calibration approach toward fitting a human arm model

In the context of Industry 4.0, the human-robot interaction (HRI) can be improved by tracking the human arm in the workspace shared with the robot. This goal takes advantage of a customized human arm modeling and it should be conveniently achieved with a limited number of sensors and a reduced computational time. In this paper, considering the analogy between human and robotic arms, a new method for the identification of a custom-made human arm model was inspired by a robot calibration process. The Denavit-Hartenberg (DH) parameters of the arm model were estimated recording a suitable number of hand poses. Hence, a robotic arm was exploited to test the new method. To simplify the fitting procedure of a reliable robot model, the minimum number of the necessary end-effector (EE) poses was investigated. Through an optoelectronic system, the EE pose trajectory of a UR3 robot was recorded. The optimization of the DH parameters was repeatedly run decreasing the downsampling frequency of the acquired data and then the trajectory error was evaluated. A new reference dataset of robot configurations was acquired permutating the joints degrees of freedom among values of 0, +90, or −90°. Hence, the method to fit the model considering few EE poses was tested on six robot configurations randomly selected from the dataset. Overall, trajectory errors highlighted the applicability of this method in the context of HRI.