Robot Control and Calibration: Innovative Control Schemes and Calibration Algorithms (SpringerBriefs in Computer Science)

✍ Scribed by Xin Luo, Zhibin Li, Long Jin, Shuai Li

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 132
• Edition: 1st ed. 2023
• Category: Library

✦ Synopsis

This book mainly shows readers how to calibrate and control robots. In this regard, it proposes three control schemes: an error-summation enhanced Newton algorithm for model predictive control; RNN for solving perturbed time-varying underdetermined linear systems; and a new joint-drift-free scheme aided with projected ZNN, which can effectively improve robot control accuracy. Moreover, the book develops four advanced algorithms for robot calibration – Levenberg-Marquarelt with diversified regularizations; improved covariance matrix adaptive evolution strategy; quadratic interpolated beetle antennae search algorithm; and a novel variable step-size Levenberg-Marquardt algorithm – which can effectively enhance robot positioning accuracy.

In addition, it is exceedingly difficult for experts in other fields to conduct robot arm calibration studies without calibration data. Thus, this book provides a publicly available dataset to assist researchers from other fields in conducting calibration experiments and validating their ideas. The book also discusses six regularization schemes based on its robot error models, i.e., L1, L2, dropout, elastic, log, and swish. Robots’ positioning accuracy is significantly improved after calibration. Using the control and calibration methods developed here, readers will be ready to conduct their own research and experiments.

✦ Table of Contents

Preface
Acknowledgments
Contents
Chapter 1: Introduction
1.1 Overview
1.2 Preliminaries
1.2.1 Kinematic Control Problem of the Robot
1.2.2 Robot Kinematic Calibration
1.3 Book Organization
References
Chapter 2: A Novel Model Predictive Control Scheme Based on an Improved Newton Algorithm
2.1 Overview
2.2 QP Problem
2.2.1 Model Predictive Control Scheme
2.2.2 ESEN Model Construction
2.3 Theoretical Verifications for ESEN Algorithm
2.3.1 Preconditions
2.3.2 Convergence Analysis
2.4 Simulations Based on MPC Scheme
2.4.1 Without Extraneous Disturbance
2.4.2 With Extraneous Disturbance
2.5 Conclusion
References
Chapter 3: A Novel Recurrent Neural Network for Robot Control
3.1 Overview
3.2 Time-Varying Description
3.2.1 Problem Formulation
3.2.2 RNN Model
3.3 Theoretical Analysis of RNN Model
3.4 Experiments for RNN Model
3.4.1 Simulations
3.4.2 The Applications of Robot
3.5 Conclusions
References
Chapter 4: A Projected Zeroing Neural Network Model for the Motion Generation and Control
4.1 Overview
4.2 Feedback-Considered Scheme
4.3 Neural Network Design
4.3.1 Neural Network Design
4.3.2 Theoretical Analysis without Noise
4.3.3 Theoretical Analysis in Constant-Noise Condition
4.3.4 Theoretical Analysis in Bounded Random-Noise Condition
4.4 Experimental Validations for the Developed PZNN Model
4.4.1 Simulations
4.4.2 Experiments for a Kinova JACO2 Robot
4.5 Conclusions
References
Chapter 5: A Regularization Ensemble Based on Levenberg-Marquardt Algorithm for Robot Calibration
5.1 Overview
5.2 Diversified Regularized LM Algorithm
5.2.1 Regularized Robot Kinematic Error Model
LM Algorithm
L1-Regularized LM Algorithm
L2-Regularized LM Algorithm
Elastic Net-Regularized LM Algorithm
Dropout-Regularized LM Algorithm
Log-Regularized LM Algorithm
Swish-Regularized LM Algorithm
5.2.2 Ensemble
5.3 Experimental Results Based on the Proposed Ensemble
5.3.1 General Settings
Evaluation Metrics
Dataset
Experimental Device
Experimental Process
5.3.2 Experimental Calibration Performance for M1-6
5.3.3 Experimental Calibration Performance for Compared Algorithms
5.4 Conclusions
References
Chapter 6: Novel Evolutionary Computing Algorithms for Robot Calibration
6.1 Overview
6.2 EKF-ICMA-ES Algorithm
6.2.1 Extended Kalman Filter (EKF)
6.2.2 Improved Covariance Matrix Adaptive Evolution Strategy (ICMA-ES)
6.2.3 Quadratic Interpolated Beetle Antennae Search (QIBAS)
6.3 Experimental Results for EKF-ICMA-ES and EKF-QIBAS
6.3.1 General Settings
Evaluation Metrics
Dataset
6.3.2 Experimental Performance
Experimental Performance for EKF-ICMA-ES
Experimental Performance for EKF-QIBAS
6.4 Conclusions
References
Chapter 7: A Highly Accurate Calibrator Based on a Novel Variable Step-Size Levenberg-Marquardt Algorithm
7.1 Overview
7.2 UKF-VSLM Algorithm
7.2.1 Unscented Kalman Filter (UKF)
7.2.2 Variable Step-Size Levenberg-Marquardt Algorithm (VSLM)
7.3 Experiments for UKF-VSLM Algorithm
7.3.1 General Settings
Evaluation Metrics
Dataset
7.3.2 Calibration Performance
7.4 Conclusions
References
Chapter 8: Conclusion and Future Work
8.1 Conclusion
8.2 Future Work
References