A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators
<p>Redundant manipulators (RMs) have been gaining more attention thanks to their excellent merits of operating flexibility and precision. Inverse kinematics (IK) study is critical to the design, trajectory planning, and control of RMs, while it is usually more complicated to solve IK problems...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2021-03-01
|
| Series: | Mechanical Sciences |
| Online Access: | https://ms.copernicus.org/articles/12/259/2021/ms-12-259-2021.pdf |
| _version_ | 1818728538950336512 |
|---|---|
| author | H. Dong H. Dong C. Li W. Wu L. Yao L. Yao H. Sun H. Sun |
| author_facet | H. Dong H. Dong C. Li W. Wu L. Yao L. Yao H. Sun H. Sun |
| author_sort | H. Dong |
| collection | DOAJ |
| description | <p>Redundant manipulators (RMs) have been gaining more attention thanks to their excellent merits of operating flexibility and precision. Inverse kinematics (IK) study is critical to the design, trajectory planning, and control of RMs, while it is usually more complicated to solve IK problems which may inherently have innumerable solutions. In this work, a novel approach for solving the IK problems for RMs while retaining the redundancy characteristics has been proposed. By employing a constraint function, the method delicately reduces the infinite IK solutions of a RM to a finite set. Furthermore, the workspace of RMs is divided into nonlinear partitions through diverse joint angle intervals, which have further simplified the mapping correlations between the desired point and manipulators' joint angles. For each partition, a pre-trained neural network (NN) model is established to acquire its IK solutions with high efficiency and precision. After combing all nonlinear partitions, multiple reasonable IK solutions are available. The presented method offers a possible selection of the most appropriate solution for trajectory planning and energy consumption and therefore has the potential for facilitating novel robot development.</p> |
| first_indexed | 2024-12-17T22:31:36Z |
| format | Article |
| id | doaj.art-6d717cd5c5df4f55913ee6bc4bc2c755 |
| institution | Directory Open Access Journal |
| issn | 2191-9151 2191-916X |
| language | English |
| last_indexed | 2024-12-17T22:31:36Z |
| publishDate | 2021-03-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Mechanical Sciences |
| spelling | doaj.art-6d717cd5c5df4f55913ee6bc4bc2c7552022-12-21T21:30:11ZengCopernicus PublicationsMechanical Sciences2191-91512191-916X2021-03-011225926710.5194/ms-12-259-2021A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulatorsH. Dong0H. Dong1C. Li2W. Wu3L. Yao4L. Yao5H. Sun6H. Sun7School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350116, ChinaFujian Provincial Collaborative Innovation Center of High-End Equipment Manufacturing, Fuzhou, 350001, ChinaSchool of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350116, ChinaSchool of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350116, ChinaSchool of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350116, ChinaFujian Provincial Collaborative Innovation Center of High-End Equipment Manufacturing, Fuzhou, 350001, ChinaSchool of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350116, ChinaFujian Provincial Collaborative Innovation Center of High-End Equipment Manufacturing, Fuzhou, 350001, China<p>Redundant manipulators (RMs) have been gaining more attention thanks to their excellent merits of operating flexibility and precision. Inverse kinematics (IK) study is critical to the design, trajectory planning, and control of RMs, while it is usually more complicated to solve IK problems which may inherently have innumerable solutions. In this work, a novel approach for solving the IK problems for RMs while retaining the redundancy characteristics has been proposed. By employing a constraint function, the method delicately reduces the infinite IK solutions of a RM to a finite set. Furthermore, the workspace of RMs is divided into nonlinear partitions through diverse joint angle intervals, which have further simplified the mapping correlations between the desired point and manipulators' joint angles. For each partition, a pre-trained neural network (NN) model is established to acquire its IK solutions with high efficiency and precision. After combing all nonlinear partitions, multiple reasonable IK solutions are available. The presented method offers a possible selection of the most appropriate solution for trajectory planning and energy consumption and therefore has the potential for facilitating novel robot development.</p>https://ms.copernicus.org/articles/12/259/2021/ms-12-259-2021.pdf |
| spellingShingle | H. Dong H. Dong C. Li W. Wu L. Yao L. Yao H. Sun H. Sun A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators Mechanical Sciences |
| title | A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators |
| title_full | A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators |
| title_fullStr | A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators |
| title_full_unstemmed | A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators |
| title_short | A novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators |
| title_sort | novel algorithm by combining nonlinear workspace partition with neural networks for solving the inverse kinematics problem of redundant manipulators |
| url | https://ms.copernicus.org/articles/12/259/2021/ms-12-259-2021.pdf |
| work_keys_str_mv | AT hdong anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hdong anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT cli anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT wwu anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT lyao anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT lyao anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hsun anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hsun anovelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hdong novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hdong novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT cli novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT wwu novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT lyao novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT lyao novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hsun novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators AT hsun novelalgorithmbycombiningnonlinearworkspacepartitionwithneuralnetworksforsolvingtheinversekinematicsproblemofredundantmanipulators |