Robot Three-Finger Grasping Strategy Based on DeeplabV3+
Researchers all over the world are aiming to make robots with accurate and stable human-like grasp capabilities, which will expand the application field of robots, and development of a reasonable grasping strategy is the premise of this function. In this paper, the improved deeplabV3+ semantic segme...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Actuators |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-0825/10/12/328 |
| _version_ | 1797507076030726144 |
|---|---|
| author | Qiang Bai Shaobo Li Jing Yang Mingming Shen Sanlong Jiang Xingxing Zhang |
| author_facet | Qiang Bai Shaobo Li Jing Yang Mingming Shen Sanlong Jiang Xingxing Zhang |
| author_sort | Qiang Bai |
| collection | DOAJ |
| description | Researchers all over the world are aiming to make robots with accurate and stable human-like grasp capabilities, which will expand the application field of robots, and development of a reasonable grasping strategy is the premise of this function. In this paper, the improved deeplabV3+ semantic segmentation algorithm is used to predict a triangle grasp strategy. The improved model was trained on the relabeled Cornell grasp datasets and tested on self-collected datasets. Compared with the existing rectangular grasp strategy, the proposed algorithm and triangle grasp strategy have achieved outstanding performance in stability, accuracy, and speed. Finally, based on the ROS platform, this paper deploys the trained model and verifies the real effect of the trained grasping strategy prediction model, and achieves excellent grasping effect. |
| first_indexed | 2024-03-10T04:41:30Z |
| format | Article |
| id | doaj.art-611f72ead6744b4493fe18a348c7bcd6 |
| institution | Directory Open Access Journal |
| issn | 2076-0825 |
| language | English |
| last_indexed | 2024-03-10T04:41:30Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Actuators |
| spelling | doaj.art-611f72ead6744b4493fe18a348c7bcd62023-11-23T03:16:41ZengMDPI AGActuators2076-08252021-12-01101232810.3390/act10120328Robot Three-Finger Grasping Strategy Based on DeeplabV3+Qiang Bai0Shaobo Li1Jing Yang2Mingming Shen3Sanlong Jiang4Xingxing Zhang5School of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaState Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaState Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, ChinaResearchers all over the world are aiming to make robots with accurate and stable human-like grasp capabilities, which will expand the application field of robots, and development of a reasonable grasping strategy is the premise of this function. In this paper, the improved deeplabV3+ semantic segmentation algorithm is used to predict a triangle grasp strategy. The improved model was trained on the relabeled Cornell grasp datasets and tested on self-collected datasets. Compared with the existing rectangular grasp strategy, the proposed algorithm and triangle grasp strategy have achieved outstanding performance in stability, accuracy, and speed. Finally, based on the ROS platform, this paper deploys the trained model and verifies the real effect of the trained grasping strategy prediction model, and achieves excellent grasping effect.https://www.mdpi.com/2076-0825/10/12/328semantic segmentationgrasp strategytriangleSPProbot |
| spellingShingle | Qiang Bai Shaobo Li Jing Yang Mingming Shen Sanlong Jiang Xingxing Zhang Robot Three-Finger Grasping Strategy Based on DeeplabV3+ Actuators semantic segmentation grasp strategy triangle SPP robot |
| title | Robot Three-Finger Grasping Strategy Based on DeeplabV3+ |
| title_full | Robot Three-Finger Grasping Strategy Based on DeeplabV3+ |
| title_fullStr | Robot Three-Finger Grasping Strategy Based on DeeplabV3+ |
| title_full_unstemmed | Robot Three-Finger Grasping Strategy Based on DeeplabV3+ |
| title_short | Robot Three-Finger Grasping Strategy Based on DeeplabV3+ |
| title_sort | robot three finger grasping strategy based on deeplabv3 |
| topic | semantic segmentation grasp strategy triangle SPP robot |
| url | https://www.mdpi.com/2076-0825/10/12/328 |
| work_keys_str_mv | AT qiangbai robotthreefingergraspingstrategybasedondeeplabv3 AT shaoboli robotthreefingergraspingstrategybasedondeeplabv3 AT jingyang robotthreefingergraspingstrategybasedondeeplabv3 AT mingmingshen robotthreefingergraspingstrategybasedondeeplabv3 AT sanlongjiang robotthreefingergraspingstrategybasedondeeplabv3 AT xingxingzhang robotthreefingergraspingstrategybasedondeeplabv3 |