Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking
The Delta robot is an over-actuated parallel robot with highly nonlinear kinematics and dynamics. Designing the control for a Delta robot to carry out various operations is a challenging task. Various advanced control algorithms, such as adaptive control, sliding mode control, and model predictive c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/17/3/113 |
| _version_ | 1827307379388055552 |
|---|---|
| author | Anni Zhao Arash Toudeshki Reza Ehsani Joshua H. Viers Jian-Qiao Sun |
| author_facet | Anni Zhao Arash Toudeshki Reza Ehsani Joshua H. Viers Jian-Qiao Sun |
| author_sort | Anni Zhao |
| collection | DOAJ |
| description | The Delta robot is an over-actuated parallel robot with highly nonlinear kinematics and dynamics. Designing the control for a Delta robot to carry out various operations is a challenging task. Various advanced control algorithms, such as adaptive control, sliding mode control, and model predictive control, have been investigated for trajectory tracking of the Delta robot. However, these control algorithms require a reliable input–output model of the Delta robot. To address this issue, we have created a control-affine neural network model of the Delta robot with stepper motors. This is a completely data-driven model intended for control design consideration and is not derivable from Newton’s law or Lagrange’s equation. The neural networks are trained with randomly sampled data in a sufficiently large workspace. The sliding mode control for trajectory tracking is then designed with the help of the neural network model. Extensive numerical results are obtained to show that the neural network model together with the sliding mode control exhibits outstanding performance, achieving a trajectory tracking error below 5 cm on average for the Delta robot. Future work will include experimental validation of the proposed neural network input–output model for control design for the Delta robot. Furthermore, transfer learnings can be conducted to further refine the neural network input–output model and the sliding mode control when new experimental data become available. |
| first_indexed | 2024-04-24T18:38:03Z |
| format | Article |
| id | doaj.art-bb5c0e04fab9412ebcd2a82e83e3871f |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-04-24T18:38:03Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-bb5c0e04fab9412ebcd2a82e83e3871f2024-03-27T13:17:25ZengMDPI AGAlgorithms1999-48932024-03-0117311310.3390/a17030113Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory TrackingAnni Zhao0Arash Toudeshki1Reza Ehsani2Joshua H. Viers3Jian-Qiao Sun4Department of Mechanical Engineering, University of California, Merced, CA 95343, USADepartment of Mechanical Engineering, University of California, Merced, CA 95343, USADepartment of Mechanical Engineering, University of California, Merced, CA 95343, USADepartment of Civil & Environmental Engineering, School of Engineering, University of California, Merced, CA 95343, USADepartment of Mechanical Engineering, University of California, Merced, CA 95343, USAThe Delta robot is an over-actuated parallel robot with highly nonlinear kinematics and dynamics. Designing the control for a Delta robot to carry out various operations is a challenging task. Various advanced control algorithms, such as adaptive control, sliding mode control, and model predictive control, have been investigated for trajectory tracking of the Delta robot. However, these control algorithms require a reliable input–output model of the Delta robot. To address this issue, we have created a control-affine neural network model of the Delta robot with stepper motors. This is a completely data-driven model intended for control design consideration and is not derivable from Newton’s law or Lagrange’s equation. The neural networks are trained with randomly sampled data in a sufficiently large workspace. The sliding mode control for trajectory tracking is then designed with the help of the neural network model. Extensive numerical results are obtained to show that the neural network model together with the sliding mode control exhibits outstanding performance, achieving a trajectory tracking error below 5 cm on average for the Delta robot. Future work will include experimental validation of the proposed neural network input–output model for control design for the Delta robot. Furthermore, transfer learnings can be conducted to further refine the neural network input–output model and the sliding mode control when new experimental data become available.https://www.mdpi.com/1999-4893/17/3/113delta robotsliding mode controlneural networks |
| spellingShingle | Anni Zhao Arash Toudeshki Reza Ehsani Joshua H. Viers Jian-Qiao Sun Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking Algorithms delta robot sliding mode control neural networks |
| title | Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking |
| title_full | Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking |
| title_fullStr | Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking |
| title_full_unstemmed | Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking |
| title_short | Evaluation of Neural Network Effectiveness on Sliding Mode Control of Delta Robot for Trajectory Tracking |
| title_sort | evaluation of neural network effectiveness on sliding mode control of delta robot for trajectory tracking |
| topic | delta robot sliding mode control neural networks |
| url | https://www.mdpi.com/1999-4893/17/3/113 |
| work_keys_str_mv | AT annizhao evaluationofneuralnetworkeffectivenessonslidingmodecontrolofdeltarobotfortrajectorytracking AT arashtoudeshki evaluationofneuralnetworkeffectivenessonslidingmodecontrolofdeltarobotfortrajectorytracking AT rezaehsani evaluationofneuralnetworkeffectivenessonslidingmodecontrolofdeltarobotfortrajectorytracking AT joshuahviers evaluationofneuralnetworkeffectivenessonslidingmodecontrolofdeltarobotfortrajectorytracking AT jianqiaosun evaluationofneuralnetworkeffectivenessonslidingmodecontrolofdeltarobotfortrajectorytracking |