通信学报2024，Vol.45Issue(8)：205-220,16.DOI:10.11959/j.issn.1000-436x.2024133
TSDSIR:机器人系统中多业务并发的消息数据流调度
TSDSIR:multi-service concurrent message data flow scheduling in robotic systems
摘要
Abstract
Aiming at the characteristics of multi-service concurrency and multi-modal message data mixing faced in the robot cloud-edge-end collaboration scenarios,a multi-message dynamic scheduling method oriented to time-sensitive at-tributes was proposed based on the analysis of the message distribution mechanism in the robot operating system 2(ROS2).Firstly,scheduling parameters,including message priority and transmission times,were defined based on multi-topic concurrency and real-time network state in ROS2,enabling real-time queue state characterization.Then,a hybrid time/priority scheduling model was designed with specific switching rules and boundary conditions.Finally,the dynamic scheduling method,considering time sensitivity,was integrated into ROS2's data distribution service layer.Simulation experiments and practical applications verify that the proposed method can improve the efficiency of concurrent trans-mission of multiple message streams in ROS2,and at the same time guarantee the real-time reliable transmission of high-priority message data with time-sensitive attributes.关键词
机器人操作系统2/数据分发服务/时间敏感属性/混杂切换/多消息流调度Key words
ROS2/data distribution service/time-sensitive attribute/hybrid switching/multi-message flow scheduling分类
信息技术与安全科学引用本文复制引用
丁男,冀承慧,胡创业,许力..TSDSIR:机器人系统中多业务并发的消息数据流调度[J].通信学报,2024,45(8):205-220,16.基金项目
国家自然科学基金资助项目(No.62072071,No.62262066) （No.62072071,No.62262066）
"十四五"国家重点研发计划基金资助项目(No.2022YFB4500800) （No.2022YFB4500800）
新疆维吾尔自治区自然科学基金资助项目(No.2021D01E20) The National Natural Science Foundation of China(No.62072071,No.62262066),The National Key Research and Development Program of the"14th Five-Year"Plan(No.2022YFB4500800),The Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2021D01E20) （No.2021D01E20）
