Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Urinary tract infection caused by rare yeast <i>Vanrija humicola</i> in a urothelial carcinoma patient: a case report and literature review.

Frontiers in immunology·2026
Same author

Correction: Urinary tract infection caused by rare yeast <i>Vanrija humicola</i> in a urothelial carcinoma patient: a case report and literature review.

Frontiers in immunology·2026
Same author

Post-infarction KLHL40-mediated regulation of cardiac sarcomeric integrity and function.

PeerJ·2026
Same author

Discovery of Schiff base-triazole-pleuromutilin conjugates as broad-spectrum antibacterial agents with potent anti-MRSA activity.

Bioorganic chemistry·2026
Same author

Sodium Butyrate Attenuates Isoprenaline-Induced Myocardial Injury via Restoring the Gut-Heart Axis and Suppressing TLR4/NF-κB Signaling.

Current issues in molecular biology·2026
Same author

Epidemiology, Risk Factors, and Routine Blood Biomarkers of Aspergillosis in Cancer Patients in Jiangxi, China.

Infection and drug resistance·2026

相关实验视频

Updated: Jul 1, 2025

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K

在堆叠场景中,用于连续机器人抓握的双阶段抓握检测方法.

Jing Zhang1,2, Baoqun Yin1, Yu Zhong2

  • 1Department of Automation, University of Science and Technology of China, Hefei 230027, China.

Mathematical biosciences and engineering : MBE
|March 8, 2024
PubMed
概括

本研究介绍了对堆叠对象的两相机器人抓取方法,在模拟和现实世界的实验中取得了高的成功率. 这种方法在复杂的堆叠场景中增强了机器人操纵能力.

关键词:
深度学习是一种深度学习.抓住的姿势估计估计.多对象检测多对象检测机器人抓取方式 机器人抓取堆叠的对象对象是堆叠的对象.

更多相关视频

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace
09:11

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace

Published on: August 8, 2019

5.7K
Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans
10:51

Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans

Published on: January 15, 2018

8.4K

相关实验视频

Last Updated: Jul 1, 2025

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K
Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace
09:11

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace

Published on: August 8, 2019

5.7K
Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans
10:51

Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans

Published on: January 15, 2018

8.4K

科学领域:

  • 机器人技术 机器人技术 机器人技术
  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 巧妙的抓取对于机器人精细操纵至关重要,但在堆叠场景中具有挑战性.
  • 现有的方法在对堆叠的对象进行顺序抓取方面遇到了困难.

研究的目的:

  • 提出一种新的两相方法,用于连续的机器人抓取堆叠任务的抓取检测.
  • 为了提高机器人掌握在复杂堆叠环境中的准确性和成功率.

主要方法:

  • 开发了一个旋转YOLOv3 (R-YOLOv3) 模型,用于在堆叠的场景中检测顶层物体.
  • 创建了一个堆叠的场景数据集用于培训和测试R-YOLOv3网络.
  • 使用G-ResNet50模型来确定最上层物体的最佳抓取姿势.

主要成果:

  • 在康奈尔大学掌握数据集上,R-YOLOv3模型实现了96.60%的平均掌握预测成功率.
  • 在现实世界的实验中,机器人在堆叠的场景中实现了95.00%的最大抓取成功率和83.93%的平均处理成功率.

结论:

  • 拟议的两阶段方法有效地使机器人能够在复杂的堆叠环境中执行顺序抓取.
  • 该方法在涉及堆叠对象的机器人操纵任务中表现出高效率和竞争力.