Zero-copy architecture for Micro-ROS deployment on Heterogeneous Multi-core Processor

• Item type: Symposium(1)
• 公開日: 2024-12-27
• タイトル: Zero-copy architecture for Micro-ROS deployment on Heterogeneous Multi-core Processor
• タイトル / 言語: en
• タイトル: Zero-copy architecture for Micro-ROS deployment on Heterogeneous Multi-core Processor
• 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: Nanzan University
• 著者所属: Nanzan University
• 著者所属: Nanzan University
• 著者所属(英): en
• 著者所属(英): Nanzan University
• 著者所属(英): en
• 著者所属(英): Nanzan University
• 著者所属(英): en
• 著者所属(英): Nanzan University
• 著者名: Vincent, Conus; Shinya, Honda; Shinkichi, Inagaki
• 著者名(英): Vincent, Conus; Shinya, Honda; Shinkichi, Inagaki
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Integration of a variety of systems on a chip has become possible in recent years, making heterogeneous multi-core processors (HMP) available as development targets. In this article, the implementation and deployment of the Robot Operating System (ROS) and micro-ROS on an HMP is presented, as these are very popular choices as middleware in robotics, automotive and beyond. We are focusing here on the improvement over our initial implementation of OpenAMP shared-memory system as a mean of communication. In this new iteration, a User space mappable DMA Buffer is used to transfer data while OpenAMP's RPMsg became a notification system. The early result and measurements for data transfer speed improvement and data throughput compared to communication using the original implementation is discussed.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Integration of a variety of systems on a chip has become possible in recent years, making heterogeneous multi-core processors (HMP) available as development targets. In this article, the implementation and deployment of the Robot Operating System (ROS) and micro-ROS on an HMP is presented, as these are very popular choices as middleware in robotics, automotive and beyond. We are focusing here on the improvement over our initial implementation of OpenAMP shared-memory system as a mean of communication. In this new iteration, a User space mappable DMA Buffer is used to transfer data while OpenAMP's RPMsg became a notification system. The early result and measurements for data transfer speed improvement and data throughput compared to communication using the original implementation is discussed.
• 書誌情報: Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform; 巻 2024, p. 29-36, 発行日 2024-12-27
• 出版者 / 言語: ja
• 出版者: 情報処理学会