• Home
  • Search
  • From data extraction to data-driven dynamic modeling for cobots: A method using multi-objective optimization
  • https://doi.org/10.1016/j.robot.2025.105006Copy DOI Icon

From data extraction to data-driven dynamic modeling for cobots: A method using multi-objective optimization

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

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. • A methodology for dataset creation of a data-driven dynamic model. • Comparison among different MOEAs for tuning PD controllers. • Improving PD torque control by using a data-driven feedforward controller. • Comparison between the use of fine-tuned data and generic data for dynamic model training.

Similar Papers
  • PDF
  • Research Article
  • Citations13

Improving prediction of tacrolimus concentration using a combination of population pharmacokinetic modeling and machine learning in chinese renal transplant recipients.

  • May 09, 2024
  • Frontiers in Pharmacology
  • Yu-Ping Wang +5
  • Book Chapter
  • Citations4

A Multi-objective Evolutionary Algorithm for Tuning Type-2 Fuzzy Sets with Rule and Condition Selection on Fuzzy Rule-Based Classification System

  • Sep 02, 2017
  • Edward Hinojosa Cárdenas +1
  • Research Article
  • Citations23

Age-hardening behavior guided by the multi-objective evolutionary algorithm and machine learning

  • Sep 28, 2021
  • Journal of Alloys and Compounds
  • Russlan Jaafreh +3
  • Research Article
  • Citations53

Robust multiobjective evolutionary feature subset selection algorithm for binary classification using machine learning techniques

  • Feb 11, 2017
  • Neurocomputing
  • Ayça Deniz +3
  • Conference Article
  • Citations8

Multi-objective evolutionary algorithms embedded with machine learning — A survey

  • Jul 01, 2016
  • Zhun Fan +5
  • Research Article
  • Citations9

Dynamic Modeling and Torque Feedforward based Optimal Fuzzy PD control of a High-Speed Parallel Manipulator

  • Jan 01, 2021
  • Journal of Robotics and Control (JRC)
  • Zirong Lin +2
  • Research Article
  • Citations9

Dynamic Modeling and Torque Feedforward based Optimal Fuzzy PD control of a High-Speed Parallel Manipulator

  • Jan 01, 2021
  • Journal of Robotics and Control (JRC)
  • Guanglei Wu +1
  • Conference Article
  • Citations2

Surrogate Model for Adaptive Control of Optical Amplifier Operating Point based on Machine Learning

  • Nov 17, 2021
  • Leandro M De Freitas +3
  • Conference Article

Stability evaluation of the PUMA-560 robot arm under model mismatch

  • Feb 01, 1991
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Thomas Larsson +3
  • Research Article
  • Citations149

Spatio-temporal simulation and prediction of land-use change using conventional and machine learning models: a review.

  • Mar 05, 2019
  • Environmental Monitoring and Assessment
  • Maher Milad Aburas +2
  • PDF
  • Research Article
  • Citations41

Enhancing multi-objective evolutionary algorithms with machine learning for scheduling problems: recent advances and survey

  • Feb 28, 2024
  • Frontiers in Industrial Engineering
  • Wenqiang Zhang +6
  • Research Article
  • Citations84

Data-Driven Dynamic Modeling for a Swimming Robotic Fish

  • Sep 01, 2016
  • IEEE Transactions on Industrial Electronics
  • Junzhi Yu +3
  • Research Article
  • Citations42

Machine Learning Models for the Seasonal Forecast of Winter Surface Air Temperature in North America

  • Aug 01, 2020
  • Earth and Space Science
  • Qi Feng Qian +2
  • PDF
  • Research Article
  • Citations10

Comparison of synchronous and asynchronous parallelization of extreme surrogate-assisted multi-objective evolutionary algorithm

  • Sep 18, 2020
  • Natural Computing
  • Tomohiro Harada +2
  • Conference Article
  • Citations12

Using PlatEMO to Solve Multi-Objective Optimization Problems in Applications: A Case Study on Feature Selection

  • Jun 01, 2019
  • Ye Tian +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.