EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions
Inverse Kinematics (IK) is essential for robot control but suffers from computational complexity as the number of links and end-effectors increases, thereby affecting real-time control accuracy and performance. In this letter, we propose a neural network-based IK approach to efficiently address the...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10872929/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857154960916480 |
|---|---|
| author | Youn-Jae Go Jun Moon |
| author_facet | Youn-Jae Go Jun Moon |
| author_sort | Youn-Jae Go |
| collection | DOAJ |
| description | Inverse Kinematics (IK) is essential for robot control but suffers from computational complexity as the number of links and end-effectors increases, thereby affecting real-time control accuracy and performance. In this letter, we propose a neural network-based IK approach to efficiently address the IK challenges in complex robotic systems with multiple end-effectors and methods for obtaining multiple solutions. The proposed method is constructed via interconnected Gaussian Mixture Models (GMM), which consist of two main components: (i) a hierarchical computation framework for calculating joint angles while considering joint limits, and (ii) a ‘sub-link’ concept to reduce the hierarchical computation. The experimental results of 7-Degrees of Freedom (DOF) robot arm manipulator with a single end-effector and 22-DOF robot arm-hand manipulator with multiple end-effectors show that the proposed method reduces both Euclidean Distance and Angular Distance as well as the Run-time, compared with the model-based numerical and earlier neural network methods. We also verify multiple solutions obtained through hierarchical computation of GMM. |
| format | Article |
| id | doaj-art-b42e9dce02084afca1b5718cad18b59d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b42e9dce02084afca1b5718cad18b59d2025-02-12T00:01:17ZengIEEEIEEE Access2169-35362025-01-0113250872509610.1109/ACCESS.2025.353902210872929EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple SolutionsYoun-Jae Go0https://orcid.org/0000-0002-4312-4674Jun Moon1https://orcid.org/0000-0002-8877-9519Department of Artificial Intelligence, Hanyang University, Seoul, South KoreaDepartment of Artificial Intelligence, Hanyang University, Seoul, South KoreaInverse Kinematics (IK) is essential for robot control but suffers from computational complexity as the number of links and end-effectors increases, thereby affecting real-time control accuracy and performance. In this letter, we propose a neural network-based IK approach to efficiently address the IK challenges in complex robotic systems with multiple end-effectors and methods for obtaining multiple solutions. The proposed method is constructed via interconnected Gaussian Mixture Models (GMM), which consist of two main components: (i) a hierarchical computation framework for calculating joint angles while considering joint limits, and (ii) a ‘sub-link’ concept to reduce the hierarchical computation. The experimental results of 7-Degrees of Freedom (DOF) robot arm manipulator with a single end-effector and 22-DOF robot arm-hand manipulator with multiple end-effectors show that the proposed method reduces both Euclidean Distance and Angular Distance as well as the Run-time, compared with the model-based numerical and earlier neural network methods. We also verify multiple solutions obtained through hierarchical computation of GMM.https://ieeexplore.ieee.org/document/10872929/Deep learning methodskinematicsmotion control |
| spellingShingle | Youn-Jae Go Jun Moon EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions IEEE Access Deep learning methods kinematics motion control |
| title | EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions |
| title_full | EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions |
| title_fullStr | EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions |
| title_full_unstemmed | EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions |
| title_short | EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions |
| title_sort | emiknet expanding multiple instance inverse kinematics network for multiple end effector and multiple solutions |
| topic | Deep learning methods kinematics motion control |
| url | https://ieeexplore.ieee.org/document/10872929/ |
| work_keys_str_mv | AT younjaego emiknetexpandingmultipleinstanceinversekinematicsnetworkformultipleendeffectorandmultiplesolutions AT junmoon emiknetexpandingmultipleinstanceinversekinematicsnetworkformultipleendeffectorandmultiplesolutions |