Approaching Collaborative Manipulation by Pushing-Grasping Fusion

Smart manipulation is always the desired performance for the interesting researches in the field of robotic control. The complicated fusion among motion primitives could offer the advanced adaptions in presence of highly success rate or unknown objects. In this paper, a hierarchical framework for pu...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu Anh Duy Phan, Dang Quy Phan, The Tri Bui, Phuong H. Le, Dinh Tuan Tran, Joo-Ho Lee, Ha Quang Thinh Ngo
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11016017/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849336546529902592
author Lu Anh Duy Phan
Dang Quy Phan
The Tri Bui
Phuong H. Le
Dinh Tuan Tran
Joo-Ho Lee
Ha Quang Thinh Ngo
author_facet Lu Anh Duy Phan
Dang Quy Phan
The Tri Bui
Phuong H. Le
Dinh Tuan Tran
Joo-Ho Lee
Ha Quang Thinh Ngo
author_sort Lu Anh Duy Phan
collection DOAJ
description Smart manipulation is always the desired performance for the interesting researches in the field of robotic control. The complicated fusion among motion primitives could offer the advanced adaptions in presence of highly success rate or unknown objects. In this paper, a hierarchical framework for pushing-grasping fusion in the cluttered environment is demonstrated. Our method involves three-phase training process, integration of masks and the reinforcement learning scheme. Both simulation and experimentation are undertaken to validate the efficacy and feasibility of the proposed methodology. Our contributions in this work are (i) to propose both grasp mask and push mask for encouraging the model to focus on exploiting, adjusting the proper grasping posture in the desired target area as well as avoiding the phenomenon of the gripper slipping on the surface of an object, (ii) to recommend the reinforcement learning scheme without object model, and (iii) to release a hierarchical training method to enhance the interactive efficiency between grasping and pushing actions.
format Article
id doaj-art-1380745375644bf6a33d880fa6a667bc
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1380745375644bf6a33d880fa6a667bc2025-08-20T03:44:57ZengIEEEIEEE Access2169-35362025-01-0113976939770710.1109/ACCESS.2025.357401811016017Approaching Collaborative Manipulation by Pushing-Grasping FusionLu Anh Duy Phan0Dang Quy Phan1https://orcid.org/0000-0001-6360-6446The Tri Bui2https://orcid.org/0000-0001-6350-3172Phuong H. Le3Dinh Tuan Tran4https://orcid.org/0000-0001-7443-9102Joo-Ho Lee5https://orcid.org/0000-0003-1015-5615Ha Quang Thinh Ngo6https://orcid.org/0000-0002-7898-1107Faculty of Mechanical Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamFaculty of Mechanical Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamFaculty of Mechanical Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamVietnam National University-Ho Chi Minh City (VNU-HCM),Thu Duc City, Ho Chi Minh City, VietnamFaculty of Data Science, Shiga University, Hikone, JapanCollege of Information Science and Engineering, Ritsumeikan University, Kyoto, JapanFaculty of Mechanical Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, VietnamSmart manipulation is always the desired performance for the interesting researches in the field of robotic control. The complicated fusion among motion primitives could offer the advanced adaptions in presence of highly success rate or unknown objects. In this paper, a hierarchical framework for pushing-grasping fusion in the cluttered environment is demonstrated. Our method involves three-phase training process, integration of masks and the reinforcement learning scheme. Both simulation and experimentation are undertaken to validate the efficacy and feasibility of the proposed methodology. Our contributions in this work are (i) to propose both grasp mask and push mask for encouraging the model to focus on exploiting, adjusting the proper grasping posture in the desired target area as well as avoiding the phenomenon of the gripper slipping on the surface of an object, (ii) to recommend the reinforcement learning scheme without object model, and (iii) to release a hierarchical training method to enhance the interactive efficiency between grasping and pushing actions.https://ieeexplore.ieee.org/document/11016017/Deep learningrobotic manipulationpushing-grasping fusionMarkov decision processvisual pushing and grasping
spellingShingle Lu Anh Duy Phan
Dang Quy Phan
The Tri Bui
Phuong H. Le
Dinh Tuan Tran
Joo-Ho Lee
Ha Quang Thinh Ngo
Approaching Collaborative Manipulation by Pushing-Grasping Fusion
IEEE Access
Deep learning
robotic manipulation
pushing-grasping fusion
Markov decision process
visual pushing and grasping
title Approaching Collaborative Manipulation by Pushing-Grasping Fusion
title_full Approaching Collaborative Manipulation by Pushing-Grasping Fusion
title_fullStr Approaching Collaborative Manipulation by Pushing-Grasping Fusion
title_full_unstemmed Approaching Collaborative Manipulation by Pushing-Grasping Fusion
title_short Approaching Collaborative Manipulation by Pushing-Grasping Fusion
title_sort approaching collaborative manipulation by pushing grasping fusion
topic Deep learning
robotic manipulation
pushing-grasping fusion
Markov decision process
visual pushing and grasping
url https://ieeexplore.ieee.org/document/11016017/
work_keys_str_mv AT luanhduyphan approachingcollaborativemanipulationbypushinggraspingfusion
AT dangquyphan approachingcollaborativemanipulationbypushinggraspingfusion
AT thetribui approachingcollaborativemanipulationbypushinggraspingfusion
AT phuonghle approachingcollaborativemanipulationbypushinggraspingfusion
AT dinhtuantran approachingcollaborativemanipulationbypushinggraspingfusion
AT jooholee approachingcollaborativemanipulationbypushinggraspingfusion
AT haquangthinhngo approachingcollaborativemanipulationbypushinggraspingfusion