中国邮电高校学报(英文) ›› 2021, Vol. 28 ›› Issue (6): 48-54.doi: 10.19682/j.cnki.1005-8885.2021.1009

• Artificial Intelligence • 上一篇    下一篇

Research on robot grabbing system based on hybrid cloud

Sheng Haiyan, Wei Shimin, Yu Xiuli, Tang Ling   

  1. 1. School of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, China
    2. Century College, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • 收稿日期:2020-06-02 修回日期:2021-07-11 出版日期:2021-12-30 发布日期:2021-12-30
  • 通讯作者: 盛海燕 E-mail:179744213@qq.com

Research on robot grabbing system based on hybrid cloud

  1. 1. School of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, China
    2. Century College, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2020-06-02 Revised:2021-07-11 Online:2021-12-30 Published:2021-12-30

摘要:

Robot grabbing has been successfully applied to a range of challenging environments but met the resource bottleneck. To answer this question, a hybrid cloud-based robot grabbing system is proposed, which supports centralized bin-picking management and deployment, large-scale storage, and communication technologies. The hybrid cloud combines the powerful computational capabilities through massive parallel computation and higher data storage facilities in the public cloud with data privacy in the private data center. The benchmark tasks against a public cloud based on robot grabbing method are evaluated, whose results indicate that the whole system reduces the data collection time and increases elastic resource scheduling and is adapted in the real industry.

关键词: grabbing, hybrid cloud robotic, object segmentation and recognition, microservice

Abstract: Robot grabbing has been successfully applied to a range of challenging environments but met the resource bottleneck. To answer this question, a hybrid cloud-based robot grabbing system is proposed, which supports centralized bin-picking management and deployment, large-scale storage, and communication technologies. The hybrid cloud combines the powerful computational capabilities through massive parallel computation and higher data storage facilities in the public cloud with data privacy in the private data center. The benchmark tasks against a public cloud based on robot grabbing method are evaluated, whose results indicate that the whole system reduces the data collection time and increases elastic resource scheduling and is adapted in the real industry.

Key words: grabbing, hybrid cloud robotic, object segmentation and recognition, microservice

中图分类号: