Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network
In robot control with physical interaction, like robot-assisted surgery and bilateral teleoperation, the availability of reliable interaction force information has proved to be capable of increasing the control precision and of dealing with the surrounding complex environments. Usually, force sensor...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/17/3636 |
| _version_ | 1798005224813625344 |
|---|---|
| author | Hang Su Wen Qi Yingbai Hu Juan Sandoval Longbin Zhang Yunus Schmirander Guang Chen Andrea Aliverti Alois Knoll Giancarlo Ferrigno Elena De Momi |
| author_facet | Hang Su Wen Qi Yingbai Hu Juan Sandoval Longbin Zhang Yunus Schmirander Guang Chen Andrea Aliverti Alois Knoll Giancarlo Ferrigno Elena De Momi |
| author_sort | Hang Su |
| collection | DOAJ |
| description | In robot control with physical interaction, like robot-assisted surgery and bilateral teleoperation, the availability of reliable interaction force information has proved to be capable of increasing the control precision and of dealing with the surrounding complex environments. Usually, force sensors are mounted between the end effector of the robot manipulator and the tool for measuring the interaction forces on the tooltip. In this case, the force acquired from the force sensor includes not only the interaction force but also the gravity force of the tool. Hence the tool dynamic identification is required for accurate dynamic simulation and model-based control. Although model-based techniques have already been widely used in traditional robotic arms control, their accuracy is limited due to the lack of specific dynamic models. This work proposes a model-free technique for dynamic identification using multi-layer neural networks (MNN). It utilizes two types of MNN architectures based on both feed-forward networks (FF-MNN) and cascade-forward networks (CF-MNN) to model the tool dynamics. Compared with the model-based technique, i.e., curve fitting (CF), the accuracy of the tool identification is improved. After the identification and calibration, a further demonstration of bilateral teleoperation is presented using a serial robot (LWR4+, KUKA, Germany) and a haptic manipulator (SIGMA 7, Force Dimension, Switzerland). Results demonstrate the promising performance of the model-free tool identification technique using MNN, improving the results provided by model-based methods. |
| first_indexed | 2024-04-11T12:35:43Z |
| format | Article |
| id | doaj.art-94fd2c8a2e524143a501f148c0ff9927 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:35:43Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-94fd2c8a2e524143a501f148c0ff99272022-12-22T04:23:37ZengMDPI AGSensors1424-82202019-08-011917363610.3390/s19173636s19173636Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural NetworkHang Su0Wen Qi1Yingbai Hu2Juan Sandoval3Longbin Zhang4Yunus Schmirander5Guang Chen6Andrea Aliverti7Alois Knoll8Giancarlo Ferrigno9Elena De Momi10Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, ItalyDipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, ItalyDepartment of Informatics, Technical University of Munich, 85748 Munich, GermanyDepartment of GMSC, Pprime Institute, CNRS, ENSMA, University of Poitiers, UPR 3346 Poitiers, FranceBioMEx Center & KTH Mechanics, KTH Royal Institute of Technology, SE-100 44 Stockholm, SwedenDipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, ItalyCollege of Automotive Engineering, Tongji University, Shanghai 201804, ChinaDipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, ItalyDepartment of Informatics, Technical University of Munich, 85748 Munich, GermanyDipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, ItalyDipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milano, ItalyIn robot control with physical interaction, like robot-assisted surgery and bilateral teleoperation, the availability of reliable interaction force information has proved to be capable of increasing the control precision and of dealing with the surrounding complex environments. Usually, force sensors are mounted between the end effector of the robot manipulator and the tool for measuring the interaction forces on the tooltip. In this case, the force acquired from the force sensor includes not only the interaction force but also the gravity force of the tool. Hence the tool dynamic identification is required for accurate dynamic simulation and model-based control. Although model-based techniques have already been widely used in traditional robotic arms control, their accuracy is limited due to the lack of specific dynamic models. This work proposes a model-free technique for dynamic identification using multi-layer neural networks (MNN). It utilizes two types of MNN architectures based on both feed-forward networks (FF-MNN) and cascade-forward networks (CF-MNN) to model the tool dynamics. Compared with the model-based technique, i.e., curve fitting (CF), the accuracy of the tool identification is improved. After the identification and calibration, a further demonstration of bilateral teleoperation is presented using a serial robot (LWR4+, KUKA, Germany) and a haptic manipulator (SIGMA 7, Force Dimension, Switzerland). Results demonstrate the promising performance of the model-free tool identification technique using MNN, improving the results provided by model-based methods.https://www.mdpi.com/1424-8220/19/17/3636multi-layer neural networkmodel-freecalibrationtool dynamic identification |
| spellingShingle | Hang Su Wen Qi Yingbai Hu Juan Sandoval Longbin Zhang Yunus Schmirander Guang Chen Andrea Aliverti Alois Knoll Giancarlo Ferrigno Elena De Momi Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network Sensors multi-layer neural network model-free calibration tool dynamic identification |
| title | Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network |
| title_full | Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network |
| title_fullStr | Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network |
| title_full_unstemmed | Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network |
| title_short | Towards Model-Free Tool Dynamic Identification and Calibration Using Multi-Layer Neural Network |
| title_sort | towards model free tool dynamic identification and calibration using multi layer neural network |
| topic | multi-layer neural network model-free calibration tool dynamic identification |
| url | https://www.mdpi.com/1424-8220/19/17/3636 |
| work_keys_str_mv | AT hangsu towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT wenqi towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT yingbaihu towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT juansandoval towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT longbinzhang towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT yunusschmirander towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT guangchen towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT andreaaliverti towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT aloisknoll towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT giancarloferrigno towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork AT elenademomi towardsmodelfreetooldynamicidentificationandcalibrationusingmultilayerneuralnetwork |