Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array
As an essential perceptual device, the tactile sensor can efficiently improve robot intelligence by providing contact force perception to develop algorithms based on contact force feedback. However, current tactile grasping technology lacks high-performance sensors and high-precision grasping predic...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Machines |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-1702/9/6/119 |
id |
doaj-f6f0cda6d17747f98c67ceb8a490a5b8 |
---|---|
record_format |
Article |
spelling |
doaj-f6f0cda6d17747f98c67ceb8a490a5b82021-07-01T00:28:08ZengMDPI AGMachines2075-17022021-06-01911911910.3390/machines9060119Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor ArrayTong Li0Xuguang Sun1Xin Shu2Chunkai Wang3Yifan Wang4Gang Chen5Ning Xue6School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaState Key Laboratory of Transducer Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaAs an essential perceptual device, the tactile sensor can efficiently improve robot intelligence by providing contact force perception to develop algorithms based on contact force feedback. However, current tactile grasping technology lacks high-performance sensors and high-precision grasping prediction models, which limits its broad application. Herein, an intelligent robot grasping system that combines a highly sensitive tactile sensor array was constructed. A dataset that can reflect the grasping contact force of various objects was set up by multiple grasping operation feedback from a tactile sensor array. The stability state of each grasping operation was also recorded. On this basis, grasp stability prediction models with good performance in grasp state judgment were proposed. By feeding training data into different machine learning algorithms and comparing the judgment results, the best grasp prediction model for different scenes can be obtained. The model was validated to be efficient, and the judgment accuracy was over 98% in grasp stability prediction with limited training data. Further, experiments prove that the real-time contact force input based on the feedback of the tactile sensor array can periodically control robots to realize stable grasping according to the real-time grasping state of the prediction model.https://www.mdpi.com/2075-1702/9/6/119robot grasping systemtactile sensor arraymachine learninggrasp stability prediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tong Li Xuguang Sun Xin Shu Chunkai Wang Yifan Wang Gang Chen Ning Xue |
spellingShingle |
Tong Li Xuguang Sun Xin Shu Chunkai Wang Yifan Wang Gang Chen Ning Xue Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array Machines robot grasping system tactile sensor array machine learning grasp stability prediction |
author_facet |
Tong Li Xuguang Sun Xin Shu Chunkai Wang Yifan Wang Gang Chen Ning Xue |
author_sort |
Tong Li |
title |
Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array |
title_short |
Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array |
title_full |
Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array |
title_fullStr |
Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array |
title_full_unstemmed |
Robot Grasping System and Grasp Stability Prediction Based on Flexible Tactile Sensor Array |
title_sort |
robot grasping system and grasp stability prediction based on flexible tactile sensor array |
publisher |
MDPI AG |
series |
Machines |
issn |
2075-1702 |
publishDate |
2021-06-01 |
description |
As an essential perceptual device, the tactile sensor can efficiently improve robot intelligence by providing contact force perception to develop algorithms based on contact force feedback. However, current tactile grasping technology lacks high-performance sensors and high-precision grasping prediction models, which limits its broad application. Herein, an intelligent robot grasping system that combines a highly sensitive tactile sensor array was constructed. A dataset that can reflect the grasping contact force of various objects was set up by multiple grasping operation feedback from a tactile sensor array. The stability state of each grasping operation was also recorded. On this basis, grasp stability prediction models with good performance in grasp state judgment were proposed. By feeding training data into different machine learning algorithms and comparing the judgment results, the best grasp prediction model for different scenes can be obtained. The model was validated to be efficient, and the judgment accuracy was over 98% in grasp stability prediction with limited training data. Further, experiments prove that the real-time contact force input based on the feedback of the tactile sensor array can periodically control robots to realize stable grasping according to the real-time grasping state of the prediction model. |
topic |
robot grasping system tactile sensor array machine learning grasp stability prediction |
url |
https://www.mdpi.com/2075-1702/9/6/119 |
work_keys_str_mv |
AT tongli robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray AT xuguangsun robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray AT xinshu robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray AT chunkaiwang robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray AT yifanwang robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray AT gangchen robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray AT ningxue robotgraspingsystemandgraspstabilitypredictionbasedonflexibletactilesensorarray |
_version_ |
1721348566039920640 |