Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging
As a typical visual positioning system, monocular ranging is widely used in various fields. However, when the distance increases, there is a greater error. YOLOv8 network has the advantages of fast recognition speed and high accuracy. This paper proposes a method by combining YOLOv8 network recognit...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/18/3981 |
_version_ | 1797580366797602816 |
---|---|
author | Yingrui Jin Zhaoyuan Shi Xinlong Xu Guang Wu Hengyi Li Shengjun Wen |
author_facet | Yingrui Jin Zhaoyuan Shi Xinlong Xu Guang Wu Hengyi Li Shengjun Wen |
author_sort | Yingrui Jin |
collection | DOAJ |
description | As a typical visual positioning system, monocular ranging is widely used in various fields. However, when the distance increases, there is a greater error. YOLOv8 network has the advantages of fast recognition speed and high accuracy. This paper proposes a method by combining YOLOv8 network recognition with a monocular ranging method to achieve target localization and grasping for the NAO robots. By establishing a visual distance error compensation model and applying it to correct the estimation results of the monocular distance measurement model, the accuracy of the NAO robot’s long-distance monocular visual positioning is improved. Additionally, a grasping control strategy based on pose interpolation is proposed. Throughout, the proposed method’s advantage in measurement accuracy was confirmed via experiments, and the grasping strategy has been implemented to accurately grasp the target object. |
first_indexed | 2024-03-10T22:49:57Z |
format | Article |
id | doaj.art-1e4658707fda4d64a6ddd7ea9ff75074 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T22:49:57Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-1e4658707fda4d64a6ddd7ea9ff750742023-11-19T10:24:04ZengMDPI AGElectronics2079-92922023-09-011218398110.3390/electronics12183981Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular RangingYingrui Jin0Zhaoyuan Shi1Xinlong Xu2Guang Wu3Hengyi Li4Shengjun Wen5School of Zhongyuan-Petersburg Aviation, Zhongyuan University of Technology, Zhengzhou 450007, ChinaSchool of Electronic and Information Engineering, Zhongyuan University of Technology, Zhengzhou 450007, ChinaSchool of Electronic and Information Engineering, Zhongyuan University of Technology, Zhengzhou 450007, ChinaSchool of Zhongyuan-Petersburg Aviation, Zhongyuan University of Technology, Zhengzhou 450007, ChinaDepartment of Electronic and Computer Engineering, Ritsumeikan University, Kusatsu 525-0058, Shiga, JapanSchool of Zhongyuan-Petersburg Aviation, Zhongyuan University of Technology, Zhengzhou 450007, ChinaAs a typical visual positioning system, monocular ranging is widely used in various fields. However, when the distance increases, there is a greater error. YOLOv8 network has the advantages of fast recognition speed and high accuracy. This paper proposes a method by combining YOLOv8 network recognition with a monocular ranging method to achieve target localization and grasping for the NAO robots. By establishing a visual distance error compensation model and applying it to correct the estimation results of the monocular distance measurement model, the accuracy of the NAO robot’s long-distance monocular visual positioning is improved. Additionally, a grasping control strategy based on pose interpolation is proposed. Throughout, the proposed method’s advantage in measurement accuracy was confirmed via experiments, and the grasping strategy has been implemented to accurately grasp the target object.https://www.mdpi.com/2079-9292/12/18/3981intelligent robotsobject recognitionYOLOv8visual odometryerror compensationpose estimation |
spellingShingle | Yingrui Jin Zhaoyuan Shi Xinlong Xu Guang Wu Hengyi Li Shengjun Wen Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging Electronics intelligent robots object recognition YOLOv8 visual odometry error compensation pose estimation |
title | Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging |
title_full | Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging |
title_fullStr | Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging |
title_full_unstemmed | Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging |
title_short | Target Localization and Grasping of NAO Robot Based on YOLOv8 Network and Monocular Ranging |
title_sort | target localization and grasping of nao robot based on yolov8 network and monocular ranging |
topic | intelligent robots object recognition YOLOv8 visual odometry error compensation pose estimation |
url | https://www.mdpi.com/2079-9292/12/18/3981 |
work_keys_str_mv | AT yingruijin targetlocalizationandgraspingofnaorobotbasedonyolov8networkandmonocularranging AT zhaoyuanshi targetlocalizationandgraspingofnaorobotbasedonyolov8networkandmonocularranging AT xinlongxu targetlocalizationandgraspingofnaorobotbasedonyolov8networkandmonocularranging AT guangwu targetlocalizationandgraspingofnaorobotbasedonyolov8networkandmonocularranging AT hengyili targetlocalizationandgraspingofnaorobotbasedonyolov8networkandmonocularranging AT shengjunwen targetlocalizationandgraspingofnaorobotbasedonyolov8networkandmonocularranging |