A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution

The robotic arm frequently performs grasping tasks in unstructured environments. However, due to the complex network architecture and constantly changing operational environments, balancing between grasping accuracy and speed poses significant challenges. Unlike fixed robotic arms, mobile robotic ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianguo Duan, Chuyan Ye, Qin Wang, Qinglei Zhang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/14/2/50
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080325193957376
author Jianguo Duan
Chuyan Ye
Qin Wang
Qinglei Zhang
author_facet Jianguo Duan
Chuyan Ye
Qin Wang
Qinglei Zhang
author_sort Jianguo Duan
collection DOAJ
description The robotic arm frequently performs grasping tasks in unstructured environments. However, due to the complex network architecture and constantly changing operational environments, balancing between grasping accuracy and speed poses significant challenges. Unlike fixed robotic arms, mobile robotic arms offer flexibility but suffer from relatively unstable bases, necessitating improvements in disturbance resistance for grasping tasks. To address these issues, this paper proposes a light-weight grasping pose estimation method called Grasp-DSC, specifically tailored for mobile robotic arms. This method integrates the deep residual shrinkage network and depthwise separable convolution. Attention mechanisms and soft thresholding are employed to improve the arm’s ability to filter out interference, while parallel convolutions enhance computational efficiency. These innovations collectively enhance the grasping decision accuracy and efficiency of mobile robotic arms in complex environments. Grasp-DSC is evaluated using the Cornell Grasp Dataset and Jacquard Grasp Dataset, achieving 96.6% accuracy and a speed of 14.4 ms on the former one. Finally, grasping experiments conducted on the MR2000-UR5 validate the practical applicability of Grasp-DSC in practical scenarios, achieving an average grasping success rate of 96%.
format Article
id doaj-art-11dd7725b2e8440eb1ffb00fe088d36a
institution DOAJ
issn 2076-0825
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-11dd7725b2e8440eb1ffb00fe088d36a2025-08-20T02:44:57ZengMDPI AGActuators2076-08252025-01-011425010.3390/act14020050A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable ConvolutionJianguo Duan0Chuyan Ye1Qin Wang2Qinglei Zhang3China Institute of FTZ Supply Chain, Shanghai Maritime University, Shanghai 201306, ChinaLogistics Engineering College, Shanghai Maritime University, Shanghai 201306, ChinaEconomics and Management College, Shanghai Maritime University, Shanghai 201306, ChinaChina Institute of FTZ Supply Chain, Shanghai Maritime University, Shanghai 201306, ChinaThe robotic arm frequently performs grasping tasks in unstructured environments. However, due to the complex network architecture and constantly changing operational environments, balancing between grasping accuracy and speed poses significant challenges. Unlike fixed robotic arms, mobile robotic arms offer flexibility but suffer from relatively unstable bases, necessitating improvements in disturbance resistance for grasping tasks. To address these issues, this paper proposes a light-weight grasping pose estimation method called Grasp-DSC, specifically tailored for mobile robotic arms. This method integrates the deep residual shrinkage network and depthwise separable convolution. Attention mechanisms and soft thresholding are employed to improve the arm’s ability to filter out interference, while parallel convolutions enhance computational efficiency. These innovations collectively enhance the grasping decision accuracy and efficiency of mobile robotic arms in complex environments. Grasp-DSC is evaluated using the Cornell Grasp Dataset and Jacquard Grasp Dataset, achieving 96.6% accuracy and a speed of 14.4 ms on the former one. Finally, grasping experiments conducted on the MR2000-UR5 validate the practical applicability of Grasp-DSC in practical scenarios, achieving an average grasping success rate of 96%.https://www.mdpi.com/2076-0825/14/2/50mobile robotic armgrasping posedeep residual shrinkage networkdepthwise separable convolutionlight-weight grasp
spellingShingle Jianguo Duan
Chuyan Ye
Qin Wang
Qinglei Zhang
A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution
Actuators
mobile robotic arm
grasping pose
deep residual shrinkage network
depthwise separable convolution
light-weight grasp
title A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution
title_full A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution
title_fullStr A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution
title_full_unstemmed A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution
title_short A Light-Weight Grasping Pose Estimation Method for Mobile Robotic Arms Based on Depthwise Separable Convolution
title_sort light weight grasping pose estimation method for mobile robotic arms based on depthwise separable convolution
topic mobile robotic arm
grasping pose
deep residual shrinkage network
depthwise separable convolution
light-weight grasp
url https://www.mdpi.com/2076-0825/14/2/50
work_keys_str_mv AT jianguoduan alightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT chuyanye alightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT qinwang alightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT qingleizhang alightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT jianguoduan lightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT chuyanye lightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT qinwang lightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution
AT qingleizhang lightweightgraspingposeestimationmethodformobileroboticarmsbasedondepthwiseseparableconvolution