From data extraction to data-driven dynamic modeling for cobots: A method using multi-objective optimization Navarro-Cabrera, Diego García-Guzmán, Juan H. Calvo Cruz, Nicolás Ros Vidal, Eduardo Luque Sola, Niceto Rafael Valencia Vidal, Brayan Torque control Dynamic modeling Genetic algorithms PD control Machine learning Supervised learning This study was supported by the EU with the IMOCOe4.0 [EU H2020RIA-101007311] project and by Spanish national funding [PCI2021-121925]. This project has received funding from the ECSEL Joint Undertaking (JU) under Grant Agreement No 101007311. This study was also supported by SPIKEAGE [PID2020-113422GA-I00] by the Spanish Ministry of Science and Innovation MCIN/AEI/10.13039/501100011033, awarded to NRL; DLROB [TED2021-131294B-I00] funded by MCIN/AEI/ 10.13039/501100011033 and by the European Union NextGenerationEU/PRTR, awarded to NRL; MUSCLEBOT [CNS2022-135243] funded by MCIN/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR, awarded to NRL; Grant PID2022-140095NB-I00 funded by MICIU/AEI /10.13039/501100011033/ and FEDER, UE. Grant PID2022-140095NB-I00 funded by MICIU/AEI / 10.13039/501100011033/ and FEDER, UE awarded to ER. N.C. Cruz is supported by the Ministry of Economic Transformation, Industry, Knowledge and Universities from the Andalusian government (PAIDI 2021: POSTDOC_21_00124). Controlling collaborative robots (cobots) is a new and challenging paradigm within the field of robot motion control and safe human–robot interaction (HRI). The safety measures needed for a reliable interaction between the robot and its environment hinder the use of classical position control methods, pushing researchers to explore alternative motor control techniques, with a strong focus on those rooted in machine learning (ML). While reinforcement learning has emerged as the predominant approach for creating intelligent controllers for cobots, supervised learning represents a promising alternative in developing data-driven model-based ML controllers in a faster and safer way. In this work, we study several aspects of the methodology needed to create a dataset for learning the dynamics of a robot. To this aim, we fine-tune several PD controllers across different benchmark trajectories using multi-objective evolutionary algorithms (MOEAs) that take into account controller accuracy, and compliance in terms of low torques in the framework of safe HRI. We delve into various aspects of the data extraction methodology including the selection and calibration of the MOEAs. We also demonstrate the need to tune controllers individually for each trajectory and how the speed of a trajectory influences both the tuning process and the resulting dynamics of the robot. Finally, we create a novel dataset and validate its use by feeding all the extracted dynamic data into an inverse dynamic robot model and integrating it into a feedforward control loop. Our approach significantly outperforms individual standard PD controllers previously tuned, thus illustrating the effectiveness of the proposed methodology. 2025-05-06T07:12:06Z 2025-05-06T07:12:06Z 2025-04-25 journal article D. Navarro-Cabrera et al. Robotics and Autonomous Systems 191 (2025) 105006. https://doi.org/10.1016/j.robot.2025.105006 https://hdl.handle.net/10481/103953 10.1016/j.robot.2025.105006 eng http://creativecommons.org/licenses/by/4.0/ open access Atribución 4.0 Internacional Elsevier