计算机视觉
人工智能
校准
计算机科学
机器人
机器视觉
数学
统计
作者
Tao Jiang,Wenjun Deng,Le Yin,Kaicheng Yang,Yanfen Wang,Hong Zhou
标识
DOI:10.1088/1361-6501/ad3a07
摘要
Abstract Recently, visual sensing measurement and its application in industrial robot operations have been widely researched, promoting the development of instrumentation and automation. This study proposes a combined vision sensor system for robot grasping, focusing on combined sensor system calibration and bracket pose measurements. The system configuration and working strategy of the combined vision system are introduced. Thereafter, the calibration of the combined vision coordinate systems is presented, wherein a global vision system acts as the external measuring equipment for accurately calibrating the local vision. Furthermore, a pose estimation method using a local vision system (LVS) is proposed, including morphology-based image enhancement and principal component analysis based corner recognition methods. Verification experiments, including combined calibration and bracket pose measurements, were performed to validate the effectiveness and accuracy of the proposed combined vision measurement strategy. The results demonstrated that the proposed system applies to industrial robot grasping of brackets. In addition, the proposed robot-sensor calibration method improves calibration accuracy. Finally, the proposed corner detection method is effective and accurate for different bracket detection applications. This study provides a system that improves robot grasping results by considering key factors, such as vision measurement accuracy, and calibration methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI