Seminar on "Highly Accurate Manipulator Calibration via Extended Kalman Filter-Incorporated Residual Neural Network"
IEEE SMC and RAS Chapter Joint Seminar on
Highly Accurate Manipulator Calibration via Extended Kalman Filter-Incorporated Residual Neural Network
Shuai Li, Ph.D. & Professor
Faculty of Information Technology and Electrical Engineering at the University of Oulu, Oulu, Finland;
VTT (National Research Centre of Finland), Oulu, Finland
Place: ECEC 202, NJIT
Time: 9am, Dec. 18, 2024
Zoom: https://njit-edu.zoom.us/j/9735966282?pwd=QlZtZFlOZ2FMZjlXemQwNmVUci9yUT09
Hosts:
Weitian Wang, Ph.D. & Associate Professor, Senior Member, IEEE, Chair of IEEE SMCS Chapter
MengChu Zhou, Ph.D. & Dist. Professor, Fellow of IEEE, IFAC, AAAS, CAA and NAI, Chair of IEEE RAS Chapter
Abstract
With the rapid advancement and widespread use of industrial manipulators, ensuring high absolute positioning accuracy has become a critical concern. While manipulator calibration models have proven effective in enhancing positioning accuracy, many existing approaches suffer from limited precision due to their failure to account for nongeometric errors. To address this challenge, this article introduces a novel calibration model that integrates an Extended Kalman Filter (EKF) with a Residual Neural Network for kinematic calibration. The key innovations of the model are: 1) utilizing the EKF to correct geometric errors in the manipulator, and 2) incorporating a residual neural network, working in tandem with the EKF, to mitigate nongeometric errors. Comprehensive experiments conducted on three real industrial manipulator datasets show that the proposed ERC model significantly outperforms several state-of-the-art calibration techniques in terms of accuracy.
Bio:
Shuai Li is currently a Full Professor in the Faculty of Information Technology and Electrical Engineering at the University of Oulu, Oulu, Finland, and is also affiliated with VTT (National Research Centre of Finland), Oulu, Finland. He received his Bachelor's degree from Hefei University of Technology, Hefei, China, in 2015, his Master's degree from the University of Science and Technology of China, Hefei, China, in 2008, and his Ph.D. degree from the Stevens Institute of Technology, Hoboken, NJ, USA, in 2014, all in electrical and computer engineering.
His main research focuses on the optimization and control of intelligent systems, including robot calibration and control, recommender systems, and dynamic manipulation. He is an author of over 300 publications, including books, book chapters, and peer-review journal papers (including over 120 IEEE Transactions papers).
Prof. Li currently serves as an Associate Editor for the journals IEEE/CAA Journal of Automatica Sinica, IEEE Transactions on Circuits and Systems for Video Technology, Neural Networks, Journal of Field Robotics, European Journal of Control, etc.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- Newark, New Jersey
- United States
- Starts 18 November 2024 05:00 PM UTC
- Ends 17 December 2024 05:00 AM UTC
- No Admission Charge