Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning
In this paper, the robot grasping for stacked objects is studied based on object detection and grasping order planning. Firstly, a novel stacked object classification network (SOCN) is proposed to realize stacked object recognition. The network takes into account the visible volume of the objects to...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/5/706 |
| _version_ | 1797475313135910912 |
|---|---|
| author | Chenlu Liu Di Jiang Weiyang Lin Luis Gomes |
| author_facet | Chenlu Liu Di Jiang Weiyang Lin Luis Gomes |
| author_sort | Chenlu Liu |
| collection | DOAJ |
| description | In this paper, the robot grasping for stacked objects is studied based on object detection and grasping order planning. Firstly, a novel stacked object classification network (SOCN) is proposed to realize stacked object recognition. The network takes into account the visible volume of the objects to further adjust its inverse density parameters, which makes the training process faster and smoother. At the same time, SOCN adopts the transformer architecture and has a self-attention mechanism for feature learning. Subsequently, a grasping order planning method is investigated, which depends on the security score and extracts the geometric relations and dependencies between stacked objects, it calculates the security score based on object relation, classification, and size. The proposed method is evaluated by using a depth camera and a UR-10 robot to complete grasping tasks. The results show that our method has high accuracy for stacked object classification, and the grasping order effectively and successfully executes safely. |
| first_indexed | 2024-03-09T20:42:24Z |
| format | Article |
| id | doaj.art-043773451f4543b2b8c06c8dd5cfcb88 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T20:42:24Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-043773451f4543b2b8c06c8dd5cfcb882023-11-23T22:52:47ZengMDPI AGElectronics2079-92922022-02-0111570610.3390/electronics11050706Robot Grasping Based on Stacked Object Classification Network and Grasping Order PlanningChenlu Liu0Di Jiang1Weiyang Lin2Luis Gomes3Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, ChinaResearch Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, ChinaResearch Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, ChinaCentre of Technology and Systems, NOVA School of Sciences and Technology, NOVA University Lisbon/UNINOVA, 2829-516 Monte de Caparica, PortugalIn this paper, the robot grasping for stacked objects is studied based on object detection and grasping order planning. Firstly, a novel stacked object classification network (SOCN) is proposed to realize stacked object recognition. The network takes into account the visible volume of the objects to further adjust its inverse density parameters, which makes the training process faster and smoother. At the same time, SOCN adopts the transformer architecture and has a self-attention mechanism for feature learning. Subsequently, a grasping order planning method is investigated, which depends on the security score and extracts the geometric relations and dependencies between stacked objects, it calculates the security score based on object relation, classification, and size. The proposed method is evaluated by using a depth camera and a UR-10 robot to complete grasping tasks. The results show that our method has high accuracy for stacked object classification, and the grasping order effectively and successfully executes safely.https://www.mdpi.com/2079-9292/11/5/706robot graspingstacked object classificationgrasping order planning |
| spellingShingle | Chenlu Liu Di Jiang Weiyang Lin Luis Gomes Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning Electronics robot grasping stacked object classification grasping order planning |
| title | Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning |
| title_full | Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning |
| title_fullStr | Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning |
| title_full_unstemmed | Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning |
| title_short | Robot Grasping Based on Stacked Object Classification Network and Grasping Order Planning |
| title_sort | robot grasping based on stacked object classification network and grasping order planning |
| topic | robot grasping stacked object classification grasping order planning |
| url | https://www.mdpi.com/2079-9292/11/5/706 |
| work_keys_str_mv | AT chenluliu robotgraspingbasedonstackedobjectclassificationnetworkandgraspingorderplanning AT dijiang robotgraspingbasedonstackedobjectclassificationnetworkandgraspingorderplanning AT weiyanglin robotgraspingbasedonstackedobjectclassificationnetworkandgraspingorderplanning AT luisgomes robotgraspingbasedonstackedobjectclassificationnetworkandgraspingorderplanning |