.png){kind=icon}
返回
Humanoid robot fetching objects using monocular vision unit
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-022-13602-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The aim of this paper is to establish an object fetching way formed by a monocular vision unit through the analysis of robot target fetching based on vision. The position distance between the target object and the robot by an NAO robot video camera is measured roughly; however, it is not necessary to measure precisely. Compared with the general steady object fetching way, it is easy to calculate and realize in the algorithm by this paper's vision fetching way and can avoid the problems generated by the general steady object fetching way, including having difficulty in locating a target, a complicated and difficult image calibration, a high requirement for precision, and so on. There are five different fetching ways including the vertical, horizontal, holding by the two-hand, independently and respectively fetching by the two-hands, and holding the book by two-hands fetching modes. It is proved by the test that this paper's fetching way has a good recognition capacity, can keep the fetching processing stable, and successfully fetches the various objects by a control approach with positive and inverse kinematics.
Keyword:
NAO robot
Object fetching way
Image calibration
Control approach
Positive and inverse kinematics
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
暂无机构信息
引用论文
Towards an Accessible Mathematics Working Environment Based on Isabelle/VSCode基于Isabelle/VSCode的可访问数学工作环境构建
OAAI
OAAI分享收藏Cit-emotionnet: CNN interactive transformer network for EEG emotion recognitionCit-emotionnet: 用于脑电图情绪识别的CNN交互式Transformer网络.png)
OAAI
IF0
OAAI分享收藏
Oral Idarubicin as a Single Agent Therapy in Patients with Relapsed or Resistant Multiple Myeloma
PREAI
分享收藏
查看更多内容