Intro
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