Image-to-Action Translations Based Object Grasping Strategy without Depth Information and Robot Kinematics Analysis

Yu Wei Lin*, Yi Hsing Chien, Min Jie Hsu, Wei Yen Wang, Cheng Kai Lu, Chen Chien Hsu

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

The main objective of this paper is to utilize only RGB images to let a robotic arm grasp a target object without the related 3D position information. The advantages of the proposed method include image-to-action translations that apply to a class of general robotic arms, and the mathematical analysis of the inverse kinematics is not necessary. We employ the RGB images and the proximal policy optimization (PPO) algorithm to train the reinforcement learning network in the Gazebo simulated environment. Finally, an illustrative example shows how effective the proposed strategy is.

原文英語
主出版物標題2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面53-54
頁數2
ISBN(電子)9798350324174
DOIs
出版狀態已發佈 - 2023
事件2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Pingtung, 臺灣
持續時間: 2023 7月 172023 7月 19

出版系列

名字2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings

會議

會議2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023
國家/地區臺灣
城市Pingtung
期間2023/07/172023/07/19

ASJC Scopus subject areas

  • 人工智慧
  • 人機介面
  • 資訊系統
  • 資訊系統與管理
  • 電氣與電子工程
  • 媒體技術
  • 儀器

指紋

深入研究「Image-to-Action Translations Based Object Grasping Strategy without Depth Information and Robot Kinematics Analysis」主題。共同形成了獨特的指紋。

引用此