Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning
Accurate dynamic model and response prediction of industrial robots (IRs) are prerequisites for production optimization before actual operation. In this study, a hybrid-driven dynamic position prediction (HDPP) approach integrating a parametric dynamic model (PDM) and learning-based residual error c...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/895 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589170771492864 |
|---|---|
| author | Hepeng Ni Cong Xu Yingxin Ye Bo Chen Shuangsheng Luo Shuai Ji |
| author_facet | Hepeng Ni Cong Xu Yingxin Ye Bo Chen Shuangsheng Luo Shuai Ji |
| author_sort | Hepeng Ni |
| collection | DOAJ |
| description | Accurate dynamic model and response prediction of industrial robots (IRs) are prerequisites for production optimization before actual operation. In this study, a hybrid-driven dynamic position prediction (HDPP) approach integrating a parametric dynamic model (PDM) and learning-based residual error compensators (RECs) is developed to estimate the actual position of a robot end-effector based on the reference input trajectory. Firstly, a PDM consisting of a flexible dynamic model of the mechanical system and a servo system model is constructed as the primary predictor in HDPP. Meanwhile, a reinforcement learning (RL)-based parameter identification method is presented to obtain independent dynamic parameters, which integrates a CAD model, least squares estimation, and RL. Then, an REC based on the temporal convolutional network long short-term memory (TCN-LSTM) is proposed for each joint to compensate for the residual error after PDM prediction. A TCN is employed as the input of LSTM to extract and compress the discontinuous features, which can enhance the compensator’s accuracy and stability. Additionally, a dynamics-integrated (DI) dataset construction scheme is developed for network training to boost the prediction accuracy. Finally, a series of experiments and comparative analysis are preformed to validate the performance of HDPP in terms of prediction accuracy and stability. |
| format | Article |
| id | doaj-art-27e8b277acdf452a86d0f87695c3cf9e |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-27e8b277acdf452a86d0f87695c3cf9e2025-01-24T13:21:15ZengMDPI AGApplied Sciences2076-34172025-01-0115289510.3390/app15020895Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine LearningHepeng Ni0Cong Xu1Yingxin Ye2Bo Chen3Shuangsheng Luo4Shuai Ji5School of Mechanical and Electronic Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electronic Engineering, Shandong Jianzhu University, Jinan 250101, ChinaSchool of Mechanical and Electronic Engineering, Shandong Jianzhu University, Jinan 250101, ChinaLingong Intelligent Information Technology Co., Ltd., Linyi 276034, ChinaLingong Intelligent Information Technology Co., Ltd., Linyi 276034, ChinaSchool of Mechanical Engineering, Shandong University, Jinan 250061, ChinaAccurate dynamic model and response prediction of industrial robots (IRs) are prerequisites for production optimization before actual operation. In this study, a hybrid-driven dynamic position prediction (HDPP) approach integrating a parametric dynamic model (PDM) and learning-based residual error compensators (RECs) is developed to estimate the actual position of a robot end-effector based on the reference input trajectory. Firstly, a PDM consisting of a flexible dynamic model of the mechanical system and a servo system model is constructed as the primary predictor in HDPP. Meanwhile, a reinforcement learning (RL)-based parameter identification method is presented to obtain independent dynamic parameters, which integrates a CAD model, least squares estimation, and RL. Then, an REC based on the temporal convolutional network long short-term memory (TCN-LSTM) is proposed for each joint to compensate for the residual error after PDM prediction. A TCN is employed as the input of LSTM to extract and compress the discontinuous features, which can enhance the compensator’s accuracy and stability. Additionally, a dynamics-integrated (DI) dataset construction scheme is developed for network training to boost the prediction accuracy. Finally, a series of experiments and comparative analysis are preformed to validate the performance of HDPP in terms of prediction accuracy and stability.https://www.mdpi.com/2076-3417/15/2/895robot dynamic position predictionhybrid-driven modelparametric dynamic modelreinforcement learning-based parameter identificationTCN-LSTM network |
| spellingShingle | Hepeng Ni Cong Xu Yingxin Ye Bo Chen Shuangsheng Luo Shuai Ji Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning Applied Sciences robot dynamic position prediction hybrid-driven model parametric dynamic model reinforcement learning-based parameter identification TCN-LSTM network |
| title | Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning |
| title_full | Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning |
| title_fullStr | Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning |
| title_full_unstemmed | Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning |
| title_short | Hybrid-Driven Dynamic Position Prediction of Robot End-Effector Integrating Parametric Dynamic Model and Machine Learning |
| title_sort | hybrid driven dynamic position prediction of robot end effector integrating parametric dynamic model and machine learning |
| topic | robot dynamic position prediction hybrid-driven model parametric dynamic model reinforcement learning-based parameter identification TCN-LSTM network |
| url | https://www.mdpi.com/2076-3417/15/2/895 |
| work_keys_str_mv | AT hepengni hybriddrivendynamicpositionpredictionofrobotendeffectorintegratingparametricdynamicmodelandmachinelearning AT congxu hybriddrivendynamicpositionpredictionofrobotendeffectorintegratingparametricdynamicmodelandmachinelearning AT yingxinye hybriddrivendynamicpositionpredictionofrobotendeffectorintegratingparametricdynamicmodelandmachinelearning AT bochen hybriddrivendynamicpositionpredictionofrobotendeffectorintegratingparametricdynamicmodelandmachinelearning AT shuangshengluo hybriddrivendynamicpositionpredictionofrobotendeffectorintegratingparametricdynamicmodelandmachinelearning AT shuaiji hybriddrivendynamicpositionpredictionofrobotendeffectorintegratingparametricdynamicmodelandmachinelearning |