Object Recognition and Grasping for Collaborative Robots Based on Vision
This study introduces a parallel YOLO–GG deep learning network for collaborative robot target recognition and grasping to enhance the efficiency and precision of visual classification and grasping for collaborative robots. First, the paper outlines the target classification and detection task, the g...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/1/195 |
| _version_ | 1797358149366185984 |
|---|---|
| author | Ruohuai Sun Chengdong Wu Xue Zhao Bin Zhao Yang Jiang |
| author_facet | Ruohuai Sun Chengdong Wu Xue Zhao Bin Zhao Yang Jiang |
| author_sort | Ruohuai Sun |
| collection | DOAJ |
| description | This study introduces a parallel YOLO–GG deep learning network for collaborative robot target recognition and grasping to enhance the efficiency and precision of visual classification and grasping for collaborative robots. First, the paper outlines the target classification and detection task, the grasping system of the robotic arm, and the dataset preprocessing method. The real-time recognition and grasping network can identify a diverse spectrum of unidentified objects and determine the target type and appropriate capture box. Secondly, we propose a parallel YOLO–GG deep vision network based on YOLO and GG-CNN. Thirdly, the YOLOv3 network, pre-trained with the COCO dataset, identifies the object category and position, while the GG-CNN network, trained using the Cornell Grasping dataset, predicts the grasping pose and scale. This study presents the processes for generating a target’s grasping frame and recognition type using GG-CNN and YOLO networks, respectively. This completes the investigation of parallel networks for target recognition and grasping in collaborative robots. Finally, the experimental results are evaluated on the self-constructed NEU-COCO dataset for target recognition and positional grasping. The speed of detection has improved by 14.1%, with an accuracy of 94%. This accuracy is 4.0% greater than that of YOLOv3. Experimental proof was obtained through a robot grasping actual objects. |
| first_indexed | 2024-03-08T14:57:41Z |
| format | Article |
| id | doaj.art-b78f48cdb39e4f1b87b5b4a592e72733 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T14:57:41Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b78f48cdb39e4f1b87b5b4a592e727332024-01-10T15:08:59ZengMDPI AGSensors1424-82202023-12-0124119510.3390/s24010195Object Recognition and Grasping for Collaborative Robots Based on VisionRuohuai Sun0Chengdong Wu1Xue Zhao2Bin Zhao3Yang Jiang4College of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaDaniel L. Goodwin College of Business, Benedict University, Chicago, IL 60601, USACollege of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaFaculty of Robot Science and Engineering, Northeastern University, Shenyang 110169, ChinaThis study introduces a parallel YOLO–GG deep learning network for collaborative robot target recognition and grasping to enhance the efficiency and precision of visual classification and grasping for collaborative robots. First, the paper outlines the target classification and detection task, the grasping system of the robotic arm, and the dataset preprocessing method. The real-time recognition and grasping network can identify a diverse spectrum of unidentified objects and determine the target type and appropriate capture box. Secondly, we propose a parallel YOLO–GG deep vision network based on YOLO and GG-CNN. Thirdly, the YOLOv3 network, pre-trained with the COCO dataset, identifies the object category and position, while the GG-CNN network, trained using the Cornell Grasping dataset, predicts the grasping pose and scale. This study presents the processes for generating a target’s grasping frame and recognition type using GG-CNN and YOLO networks, respectively. This completes the investigation of parallel networks for target recognition and grasping in collaborative robots. Finally, the experimental results are evaluated on the self-constructed NEU-COCO dataset for target recognition and positional grasping. The speed of detection has improved by 14.1%, with an accuracy of 94%. This accuracy is 4.0% greater than that of YOLOv3. Experimental proof was obtained through a robot grasping actual objects.https://www.mdpi.com/1424-8220/24/1/195deep learningcollaborative robotsparallel networksgrasping detection |
| spellingShingle | Ruohuai Sun Chengdong Wu Xue Zhao Bin Zhao Yang Jiang Object Recognition and Grasping for Collaborative Robots Based on Vision Sensors deep learning collaborative robots parallel networks grasping detection |
| title | Object Recognition and Grasping for Collaborative Robots Based on Vision |
| title_full | Object Recognition and Grasping for Collaborative Robots Based on Vision |
| title_fullStr | Object Recognition and Grasping for Collaborative Robots Based on Vision |
| title_full_unstemmed | Object Recognition and Grasping for Collaborative Robots Based on Vision |
| title_short | Object Recognition and Grasping for Collaborative Robots Based on Vision |
| title_sort | object recognition and grasping for collaborative robots based on vision |
| topic | deep learning collaborative robots parallel networks grasping detection |
| url | https://www.mdpi.com/1424-8220/24/1/195 |
| work_keys_str_mv | AT ruohuaisun objectrecognitionandgraspingforcollaborativerobotsbasedonvision AT chengdongwu objectrecognitionandgraspingforcollaborativerobotsbasedonvision AT xuezhao objectrecognitionandgraspingforcollaborativerobotsbasedonvision AT binzhao objectrecognitionandgraspingforcollaborativerobotsbasedonvision AT yangjiang objectrecognitionandgraspingforcollaborativerobotsbasedonvision |