AI-Based Keypoint Detection for Remote Robot Operation with Improved Safety

• Item type: Symposium(1)
• 公開日: 2023-12-20
• タイトル: AI-Based Keypoint Detection for Remote Robot Operation with Improved Safety
• タイトル / 言語: en
• タイトル: AI-Based Keypoint Detection for Remote Robot Operation with Improved Safety
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: Kumamoto University
• 著者所属: Kumamoto University
• 著者所属(英): en
• 著者所属(英): Kumamoto University
• 著者所属(英): en
• 著者所属(英): Kumamoto University
• 著者名: Ludi, Wang; Takeshi, Ohkawa
• 著者名(英): Ludi, Wang; Takeshi, Ohkawa
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This study introduces a keypoint detection AI system developed through transfer learning, with a pre-trained ResNet-50 neural network serving as its foundational framework. The system is designed to assist in remote robotic arm manipulation by capturing keypoints from network camera images, computing their coordinates, and using joint angles to control arm movements precisely. This research strives to contribute to the enhancement of accuracy and efficiency in remote robotic arm operations, while also highlighting the adaptability of transfer learning in customizing pre-trained ResNet-50 models for specific applications, offering novel technological solutions for robotics control
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This study introduces a keypoint detection AI system developed through transfer learning, with a pre-trained ResNet-50 neural network serving as its foundational framework. The system is designed to assist in remote robotic arm manipulation by capturing keypoints from network camera images, computing their coordinates, and using joint angles to control arm movements precisely. This research strives to contribute to the enhancement of accuracy and efficiency in remote robotic arm operations, while also highlighting the adaptability of transfer learning in customizing pre-trained ResNet-50 models for specific applications, offering novel technological solutions for robotics control
• 書誌情報: Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform; 巻 2023, p. 69-70, 発行日 2023-12-20
• 出版者 / 言語: ja
• 出版者: 情報処理学会