A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations
As an increasing number of robotic manipulators possess seven or more degrees-of-freedom (DoF), solving inverse kinematic (IK) for kinematically redundant manipulators is becoming critical. Numerical optimizations are commonly used to solve the problem due to their generality and accuracy. Unfortuna...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10005285/ |
| _version_ | 1828067600102326272 |
|---|---|
| author | Chi-Kai Ho Li-Wei Chan Chung-Ta King Ting-Yu Yen |
| author_facet | Chi-Kai Ho Li-Wei Chan Chung-Ta King Ting-Yu Yen |
| author_sort | Chi-Kai Ho |
| collection | DOAJ |
| description | As an increasing number of robotic manipulators possess seven or more degrees-of-freedom (DoF), solving inverse kinematic (IK) for kinematically redundant manipulators is becoming critical. Numerical optimizations are commonly used to solve the problem due to their generality and accuracy. Unfortunately, they typically only generate one joint solution at a time, despite the multiple joint configurations that redundant manipulators can provide to move the end-effector to a target position. The long iterative optimization process is also a concern, particularly if extra constraints such as obstacle avoidance have to be evaluated. In this paper, we show that numerical methods may be complemented by deep learning to overcome these limitations. Through deep learning, the solution space of redundant IK may be learned with neural networks (NNs), which allows multiple distinct joint solutions corresponding to a given target position to be obtained by navigating the solution space. The main challenge is to overcome the one-to-one functional mapping of NNs. This paper solves this problem with a novel probabilistic encoding of manipulator poses and their corresponding infinite number of joint solutions. Two examples are presented to demonstrate the application of the proposed method to facilitate numerical IK computations: (1) finding a good initial joint solution to bootstrap the numerical IK calculation, and (2) evaluating extra constraints, such as obstacle avoidance, off the optimization iterations. Experiments show that the proposed method can accelerate the execution of different numerical IK modules in the popular IKpy package up to 50% for a 7-DoF manipulator, depending on the accuracy required. |
| first_indexed | 2024-04-10T23:48:02Z |
| format | Article |
| id | doaj.art-64123cabef9b4c9b8b843b3334d914ea |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T23:48:02Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-64123cabef9b4c9b8b843b3334d914ea2023-01-11T00:00:33ZengIEEEIEEE Access2169-35362023-01-01112274229010.1109/ACCESS.2023.323410410005285A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK ComputationsChi-Kai Ho0https://orcid.org/0000-0002-2158-5947Li-Wei Chan1Chung-Ta King2https://orcid.org/0000-0002-5041-5795Ting-Yu Yen3Department of Computer Science, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanAs an increasing number of robotic manipulators possess seven or more degrees-of-freedom (DoF), solving inverse kinematic (IK) for kinematically redundant manipulators is becoming critical. Numerical optimizations are commonly used to solve the problem due to their generality and accuracy. Unfortunately, they typically only generate one joint solution at a time, despite the multiple joint configurations that redundant manipulators can provide to move the end-effector to a target position. The long iterative optimization process is also a concern, particularly if extra constraints such as obstacle avoidance have to be evaluated. In this paper, we show that numerical methods may be complemented by deep learning to overcome these limitations. Through deep learning, the solution space of redundant IK may be learned with neural networks (NNs), which allows multiple distinct joint solutions corresponding to a given target position to be obtained by navigating the solution space. The main challenge is to overcome the one-to-one functional mapping of NNs. This paper solves this problem with a novel probabilistic encoding of manipulator poses and their corresponding infinite number of joint solutions. Two examples are presented to demonstrate the application of the proposed method to facilitate numerical IK computations: (1) finding a good initial joint solution to bootstrap the numerical IK calculation, and (2) evaluating extra constraints, such as obstacle avoidance, off the optimization iterations. Experiments show that the proposed method can accelerate the execution of different numerical IK modules in the popular IKpy package up to 50% for a 7-DoF manipulator, depending on the accuracy required.https://ieeexplore.ieee.org/document/10005285/Feature encodinginverse kinematicsredundant robotic manipulatorsunsupervised learning |
| spellingShingle | Chi-Kai Ho Li-Wei Chan Chung-Ta King Ting-Yu Yen A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations IEEE Access Feature encoding inverse kinematics redundant robotic manipulators unsupervised learning |
| title | A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations |
| title_full | A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations |
| title_fullStr | A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations |
| title_full_unstemmed | A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations |
| title_short | A Deep Learning Approach to Navigating the Joint Solution Space of Redundant Inverse Kinematics and Its Applications to Numerical IK Computations |
| title_sort | deep learning approach to navigating the joint solution space of redundant inverse kinematics and its applications to numerical ik computations |
| topic | Feature encoding inverse kinematics redundant robotic manipulators unsupervised learning |
| url | https://ieeexplore.ieee.org/document/10005285/ |
| work_keys_str_mv | AT chikaiho adeeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT liweichan adeeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT chungtaking adeeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT tingyuyen adeeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT chikaiho deeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT liweichan deeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT chungtaking deeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations AT tingyuyen deeplearningapproachtonavigatingthejointsolutionspaceofredundantinversekinematicsanditsapplicationstonumericalikcomputations |