《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (8): 2536-2543.DOI: 10.11772/j.issn.1001-9081.2023081184

• 计算机软件技术 • 上一篇    下一篇

无人系统数据融合流水线架构设计

刘艺, 杨国利, 郑奇斌(), 李翔, 周杨森, 陈德鹏   

  1. 北京大数据先进技术研究院,北京 100195
  • 收稿日期:2023-09-03 修回日期:2023-10-08 接受日期:2023-10-17 发布日期:2024-08-22 出版日期:2024-08-10
  • 通讯作者: 郑奇斌
  • 作者简介:刘艺(1990—),男(回族),安徽蚌埠人,助理研究员,博士,主要研究方向:智能数据工程、演化算法
    杨国利(1987—),男,河北石家庄人,副研究员,博士,主要研究方向:知识计算
    郑奇斌(1990—),男,甘肃兰州人,助理研究员,博士,主要研究方向:数据工程、机器学习 zhengqb@aibd.ac.cn
    李翔(1988—),男,四川资中人,助理研究员,博士,主要研究方向:大数据
    周杨森(1991—),男,河北保定人,工程师,硕士,主要研究方向:机器人
    陈德鹏(1995—),男,天津人,工程师,硕士,主要研究方向:机器人。
  • 基金资助:
    国家自然科学青年基金资助项目(72201275);第八届中国科协青年人才托举工程项目(2022QNRC001)

Architecture design of data fusion pipeline for unmanned systems

Yi LIU, Guoli YANG, Qibin ZHENG(), Xiang LI, Yangsen ZHOU, Depeng CHEN   

  1. Advanced Institute of Big Data (Beijing),Beijing 100195,China
  • Received:2023-09-03 Revised:2023-10-08 Accepted:2023-10-17 Online:2024-08-22 Published:2024-08-10
  • Contact: Qibin ZHENG
  • About author:LIU Yi, born in 1990, Ph. D., assistant research fellow. His research interests include intelligent data engineering, evolutionary algorithm.
    YANG Guoli, born in 1987, Ph. D., associate research fellow. His research interest include knowledge computing.
    LI Xiang, born in 1988, Ph. D., assistant research fellow. His research interest include big data.
    ZHOU Yangsen, born in 1991, M. S., engineer. His research interest include robot.
    First author contact:CHEN Depen, born in 1995, M. S., engineer. His research interest include robot.
  • Supported by:
    National Science Foundation for Young Scientists of China(72201275);Young Elite Scientists Sponsorship Program by CAST(2022QNRC001)

摘要:

传感器是无人系统智能化行动的基础,而通过融合多传感器的数据能增强无人系统的智能感知和自主决策能力,提升无人系统的可靠性和鲁棒性。无人系统的数据融合面临传感器类型多样、数据格式异构、数据融合分析的实时性强,以及算法模型种类复杂、更新演化快等挑战,传统定制化开发前端融合模型和基于后端融合平台的方法难以适用。因此,提出一种面向数据融合的流水线平台,以支持数据自动转换、算法灵活组合、模型高可配置、功能快速迭代,且能面向任务,动态、快速构建数据融合模型并提供信息服务。在剖析无人系统数据融合流程和技术体系的基础上,设计流水线框架及其关键功能构件,分析亟待突破的关键技术,给出框架的运行方式和实际案例,探讨未来的发展方向。

关键词: 数据融合, 无人系统, 流水线, 感知数据, 算法服务

Abstract:

Sensors are the basis for unmanned systems to perform intelligent actions. The fusion of multi-sensor data can enhance intelligent perception and autonomous decision-making capabilities of unmanned systems, and improve the reliability and robustness of these systems. Data fusion of unmanned systems encounters many challenges such as diverse sensor types, heterogeneous data formats, real-time needs of data fusion and analysis, as well as complex types and fast evolution of algorithm models. Traditional methods of developing fusion models through customization on front end and approaches based on fusion platform running on back end are difficult to apply in these cases. Therefore, a pipeline platform for data fusion was proposed. This platform has capabilities to support automatic data transformation, flexible algorithm combination, dynamic model configuration, and rapid iteration of functions to achieve dynamic and quick data fusion model construction and provide information service for different tasks. Based on the analysis of data fusion process and techniques, the pipeline framework and its key functions and components were characterized, the key technologies that urgently need breakthroughs were analyzed, the running way and actual case of the framework were given, and research directions for future development were pointed out.

Key words: data fusion, unmanned system, pipeline, sensing data, algorithm service

中图分类号: