From data extraction to data-driven dynamic modeling for cobots: A method using multi-objective optimization
Abstract
This work presents a methodology for creating a dataset to learn the dynamics of a collaborative robot. It fine-tunes proportional-derivative controllers across benchmark trajectories through multi-objective evolutionary algorithms that balance accuracy and low torque for safe human–robot interaction. The resulting data-driven inverse dynamic model is validated in a feedforward control loop and outperforms the individually tuned standard controllers.
Diego Navarro
PhD Student
PhD student at the Applied Computational Neuroscience Research Group at the University of Granada.
Juan Helios García Guzmán
PhD Student
PhD student at the Applied Computational Neuroscience Research Group at the University of Granada.
Brayan Alfonso Valencia Vidal
Postdoctoral Researcher
Postdoctoral researcher in the Applied Computational Neuroscience Group, working on bio-inspired robotics and control.
Niceto R. Luque
Associate Professor
Associate Professor at the Department of Computer Engineering, Automation and Robotics and Principal Investigator at the Applied Computational Neuroscience Group.
Eduardo Ros
Full Professor
Full professor in computer architecture, principal investigator at the Computational Neuroscience and Neurorobotics Lab and principal investigator of the VALERIA lab of the University of Granada.