The book provides three control schemes, RNN, and four advanced algorithms for robot calibration, as well as a publicly available dataset to assist researchers from other fields in conducting calibration experiments and validating their ideas. It also discusses six regularization schemes based on its robot error models, which can significantly improve robot positioning accuracy.

Format: Paperback / softback
Length: 125 pages
Publication date: 26 September 2023
Publisher: Springer Verlag, Singapore

This book is a comprehensive guide to calibrating and controlling robots, offering three control schemes, four advanced algorithms, and a publicly available dataset for calibration experiments. It also discusses six regularization schemes based on its robot error models, which can significantly improve robot positioning accuracy. With these methods, readers will be able to conduct their own research and experiments in the field of robotics.

Calibration and Control of Robots

This book provides a comprehensive guide to calibrating and controlling robots, offering three control schemes, four advanced algorithms, and a publicly available dataset for calibration experiments. It also discusses six regularization schemes based on its robot error models, which can significantly improve robot positioning accuracy. With these methods, readers will be able to conduct their own research and experiments in the field of robotics.

Control Schemes

The book 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. The error-summation enhanced Newton algorithm is designed to improve the accuracy of model predictive control by reducing the error summation in each iteration. The RNN is used to solve perturbed time-varying underdetermined linear systems, which are common in robotics. The new joint-drift-free scheme is aided with projected ZNN, which can effectively improve robot control accuracy. These control schemes can be applied to a wide range of robots and applications.

Advanced Algorithms

The book also 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. These algorithms can effectively enhance robot positioning accuracy. The Levenberg-Marquarelt algorithm with diversified regularizations is used to improve the accuracy of robot calibration by considering different regularization methods. The improved covariance matrix adaptive evolution strategy is used to optimize the calibration parameters. The quadratic interpolated beetle antennae search algorithm is used to find the optimal calibration parameters. The novel variable step-size Levenberg-Marquardt algorithm is used to improve the convergence speed of the calibration process. These algorithms can be applied to a wide range of robots and applications.

Publicly Available Dataset

The book also provides a publicly available dataset to assist researchers from other fields in conducting calibration experiments and validating their ideas. The dataset includes data from different robots and applications, and it can be used to train and test machine learning models. This dataset can help researchers to improve their understanding of robot calibration and control.

Regularization Schemes

The book discusses six regularization schemes based on its robot error models: L1, L2, dropout, elastic, log, and swish. These regularization schemes can be used to improve the accuracy of robot calibration. L1 regularization is used to reduce the weight of the parameters in the calibration model. L2 regularization is used to reduce the variance of the parameters in the calibration model. Dropout regularization is used to randomly drop out some of the parameters in the calibration model. Elastic regularization is used to add a penalty term to the calibration model. Log regularization is used to add a logarithmic term to the calibration model. Swish regularization is used to add a sigmoid term to the calibration model. These regularization schemes can be used to improve the accuracy of robot calibration by reducing the error in the calibration model.

Robots Positioning Accuracy

Robots positioning accuracy is significantly improved after calibration. The control and calibration methods developed here can be used to improve the accuracy of robot positioning in a wide range of applications, such as manufacturing, logistics, and healthcare. By using these methods, robots can be more efficient and accurate in their tasks, which can lead to increased productivity and reduced costs. In addition, the publicly available dataset can help researchers to improve their understanding of robot calibration and control, which can lead to new research and development opportunities.

Conclusion

In conclusion, this book is a comprehensive guide to calibrating and controlling robots, offering three control schemes, four advanced algorithms, and a publicly available dataset for calibration experiments. It also discusses six regularization schemes based on its robot error models, which can significantly improve robot positioning accuracy. With these methods, readers will be able to conduct their own research and experiments in the field of robotics.

Dimension: 235 x 155 (mm)
ISBN-13: 9789819957651
Edition number: 1st ed. 2023