Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning
For traditional machine learning algorithms, visual recognition algorithms have low recognition accuracy and slow running time. This research studies the scene of the robot doing housework in the family scene, and uses the RGB image information as input to complete the grasping pose estimation of th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2024-03-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.03.023 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841546952390475776 |
|---|---|
| author | Li Wanyan Ruan Guanqiang Zhang Zhendong |
| author_facet | Li Wanyan Ruan Guanqiang Zhang Zhendong |
| author_sort | Li Wanyan |
| collection | DOAJ |
| description | For traditional machine learning algorithms, visual recognition algorithms have low recognition accuracy and slow running time. This research studies the scene of the robot doing housework in the family scene, and uses the RGB image information as input to complete the grasping pose estimation of the target object. Based on the object detection model YOLOv5s, the network architecture is built by combining data enhancement and transfer learning with its advantages of lightweight and fast speed. After building a family scene data set to enhance the data of a small number of training samples, the model is trained on the target data set using transfer learning, and the parameters are fine-tuned at the same time. The positioning information of the target object is transformed into the grasping pose of the robotic arm through coordinate transformation, and the robotic arm is controlled to finally complete the grasping task with a fixed grasping posture. Finally, the effectiveness of the algorithm is verified by building an experimental platform and manipulating the UR5 robotic arm to carry out actual grasping experiments. The proposed method based on target detection is fast, has high real-time performance, and has a false/missed recognition rate of less than 2%. The application in the robotic arm can efficiently complete the task. |
| format | Article |
| id | doaj-art-9bbd3c4da0a54b3892bf31c9d6c301d2 |
| institution | Kabale University |
| issn | 1004-2539 |
| language | zho |
| publishDate | 2024-03-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj-art-9bbd3c4da0a54b3892bf31c9d6c301d22025-01-10T15:00:02ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392024-03-014817017650737548Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer LearningLi WanyanRuan GuanqiangZhang ZhendongFor traditional machine learning algorithms, visual recognition algorithms have low recognition accuracy and slow running time. This research studies the scene of the robot doing housework in the family scene, and uses the RGB image information as input to complete the grasping pose estimation of the target object. Based on the object detection model YOLOv5s, the network architecture is built by combining data enhancement and transfer learning with its advantages of lightweight and fast speed. After building a family scene data set to enhance the data of a small number of training samples, the model is trained on the target data set using transfer learning, and the parameters are fine-tuned at the same time. The positioning information of the target object is transformed into the grasping pose of the robotic arm through coordinate transformation, and the robotic arm is controlled to finally complete the grasping task with a fixed grasping posture. Finally, the effectiveness of the algorithm is verified by building an experimental platform and manipulating the UR5 robotic arm to carry out actual grasping experiments. The proposed method based on target detection is fast, has high real-time performance, and has a false/missed recognition rate of less than 2%. The application in the robotic arm can efficiently complete the task.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.03.023YOLOv5sRobotic armPose estimationTarget detectionTransfer learning |
| spellingShingle | Li Wanyan Ruan Guanqiang Zhang Zhendong Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning Jixie chuandong YOLOv5s Robotic arm Pose estimation Target detection Transfer learning |
| title | Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning |
| title_full | Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning |
| title_fullStr | Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning |
| title_full_unstemmed | Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning |
| title_short | Target Detection and Robotic Arm Grasp Pose Estimation Based on YOLOv5 and Transfer Learning |
| title_sort | target detection and robotic arm grasp pose estimation based on yolov5 and transfer learning |
| topic | YOLOv5s Robotic arm Pose estimation Target detection Transfer learning |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2024.03.023 |
| work_keys_str_mv | AT liwanyan targetdetectionandroboticarmgraspposeestimationbasedonyolov5andtransferlearning AT ruanguanqiang targetdetectionandroboticarmgraspposeestimationbasedonyolov5andtransferlearning AT zhangzhendong targetdetectionandroboticarmgraspposeestimationbasedonyolov5andtransferlearning |