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

PLA Reinforced with Limestone Waste: A Way to Sustainable Polymer Composites.

Polymers·2025
Same author

Domain Adaptation with Contrastive Simultaneous Multi-Loss Training for Hand Gesture Recognition.

Sensors (Basel, Switzerland)·2023
Same author

ATOM Calibration Framework: Interaction and Visualization Functionalities.

Sensors (Basel, Switzerland)·2023
Same author

Trends of Human-Robot Collaboration in Industry Contexts: Handover, Learning, and Metrics.

Sensors (Basel, Switzerland)·2021
Same author

Robust Texture Mapping Using RGB-D Cameras.

Sensors (Basel, Switzerland)·2021
Same author

Geographic access to COVID-19 healthcare in Brazil using a balanced float catchment area approach.

Social science & medicine (1982)·2021

相关实验视频

Updated: Jul 11, 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

使用深度学习识别捕捉模式,用于人机协作.

Pedro Amaral1, Filipe Silva1, Vítor Santos2

  • 1Department of Electronics, Telecommunications and Informatics (DETI), Institute of Electronics and Informatics Engineering of Aveiro (IEETA), University of Aveiro, 3810-193 Aveiro, Portugal.

Sensors (Basel, Switzerland)
|November 14, 2023
PubMed
概括

这项研究引入了一个新的人工智能框架,用于辅助机器人识别使用手和手指关节数据的人类操作员持有的物体. 该研究比较了深度学习模型,显示了有效的对象识别,以改善人机协作.

关键词:
协作式机器人协作式机器人抓住的姿势 抓住的姿势手物体的交互作用.关键点的分类关键点的分类对象识别对象识别器

更多相关视频

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.2K
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

546

相关实验视频

Last Updated: Jul 11, 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
Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.2K
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

546

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:

  • 协作机器人需要对共享任务进行预测和预期的能力.
  • 机器人准确的对象识别对于理解人类操作员的意图至关重要.

研究的目的:

  • 开发一种基于学习的框架,让辅助机器人能够使用手和手指关节模式识别抓住的物体.
  • 为了比较卷积神经网络 (CNN) 和变压器对象识别的性能.

主要方法:

  • 使用MediaPipe来检测RGB图像中的手地标.
  • 开发了一个深度的多类分类器,以从提取的关键点预测对象.
  • 根据准确性,精度,回忆和F1分数来评估CNN和变压器架构.

主要成果:

  • 拟议的框架展示了有效的对象识别能力.
  • 两种CNN和变压器模型都显示了不同的性能指标.
  • 获得了对影响模型概括的因素的见解.

结论:

  • 开发的框架成功使辅助机器人能够识别人类操纵的物体.
  • 该研究提供了对这项任务的深度学习架构的比较分析.
  • 研究结果强调了在人机交互系统中概括的重要性.