[1]宋燕燕,秦 军,邢艳芳,等.基于多智能体的图优化 SLAM 构建方法[J].计算机技术与发展,2020,30(11):205-209.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 038]
　SONG Yan-yan,QIN Jun,XING Yan-fang,et al.An Optimizing SLAM Construction Method Based on Multi-agent[J].,2020,30(11):205-209.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 038]
点击复制

基于多智能体的图优化 SLAM 构建方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年11期
页码:
205-209
栏目:
应用开发研究
出版日期:
2020-11-10

文章信息/Info

Title:
An Optimizing SLAM Construction Method Based on Multi-agent
文章编号:
1673-629X(2020)11-0205-05
作者:
宋燕燕1; 秦 军1; 2; 邢艳芳1; 汪晨曦1; 周洪萍1
1. 中国传媒大学南广学院,江苏 南京 211172; 2. 南京邮电大学,江苏 南京 210003
Author(s):
SONG Yan-yan1; QIN Jun1; 2; XING Yan-fang1; WANG Chen-xi1; ZHOU Hong-ping1
1. Communication University of China,Nanjing,Nanjing 211172,China; 2. Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
多智能体; 图优化; 同时定位与地图构建; 三维重建; 可视化
Keywords:
multi-agent; graph optimization; simultaneous localization and mapping; three-dimensional reconstruction; visualization
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 11. 038
摘要:
随着人工智能和增强现实技术在社会中的地位稳步上升,这些领域的核心关键技术在逐步实现突破,对于三维环境的动态实时的理解是当前增强现实技术研究方面最活跃的问题之一。 为实现多人同时应用视觉同时定位与地图构建(simultaneous localization and mapping,SLAM)系统,将图优化框架的 SLAM 与多智能体进行结合研究,提出基于多智能体的 SLAM 构建方法。 首先简要介绍了视觉 SLAM 框架,系统地分析了在构建三维场景时,利用相机将信息进行整合和预处理,并估算相邻图像之间的运动以及检测信息来构建整体的框架。 从视觉中提炼出最优化的 3D 模型以及各种参数来达到三维重建,通过相机的运动过程来确定视觉的深度特性以及加强沉浸式的观感体验,最终根据其本身的可视化追踪和环境理解,将非线性优化方案结合多智能体进行 SLAM 构建,实现移动平台真实浏览虚拟样板间的可视化与交互。
Abstract:
With the steady rise of the status of artificial intelligence and augmented reality technology in the society,the key technologies in these fields are gradually breaking through. The dynamic? real-time understanding of 3D environment is one of the most active problems in the research of augmented reality. To realize the multi-person simultaneous application of simultaneous localization and mapping system,SLAM of graph optimization framework and multi-agent is combined and a multi-agent based SLAM construction method is put forward. Firstly,the visual SLAM framework is briefly introduced,and the whole frame is constructed by using the camera to integrate and preprocess the information and estimate the motion between the adjacent images and detect the information. Optimized 3D models and various parameters are extracted from vision to achieve three - dimensional reconstruction. The depth of vision is determined? by the camera爷s motion process and the immersion experience is enhanced. Finally,according to its own visual tracking and environmental understanding,a multi-agent SLAM construction method based on nonlinear optimization is proposed,and visualization and interaction between the real browsing virtual templates on the mobile platform is presented.

相似文献/References:

[1]曹雷 陈希亮.作战智能体分队攻击目标分配模型研究[J].计算机技术与发展,2009,(12):150.
　CAO Lei,CHEN Xi-liang.Research on Dynamic Weapon Target Assignment in Combat Agent Unit[J].,2009,(11):150.
[2]刘丹 谢益武.面向智能体的信息系统开发方法研究[J].计算机技术与发展,2006,(03):101.
　LIU Dan,XIE Yi-wu.Research on Development Methods in Agent-Oriented IS[J].,2006,(11):101.
[3]张礼华 卢道华.基于多Agent的网络课程协作学习平台的构建与研究[J].计算机技术与发展,2006,(09):126.
　ZHANG Li-hua,LU Dao-hua.Construction and Study of Cooperation - Learning Platform for Network Course Based on Multi- Agent[J].,2006,(11):126.
[4]陈 雪,姜玉莲*.分布式事件触发的多单摆系统一致性跟踪控制[J].计算机技术与发展,2020,30(09):177.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 032]
　CHEN Xue,JIANG Yu-lian*.Consensus Tracking Control of Multiple Simple-pendulum Network System Based on Distributed Event Triggering Mechanism[J].,2020,30(11):177.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 032]
[5]李铁维,王牧阳,周 炎.基于点线结合特征的单目视觉里程计[J].计算机技术与发展,2021,31(01):48.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 009]
　LI Tie-wei,WANG Mu-yang,ZHOU Yan.Monocular Visual Odometry Based on Point and Line Features[J].,2021,31(11):48.[doi:10. 3969 / j. issn. 1673-629X. 2021. 01. 009]
[6]王 闯,沈苏彬.一种基于多智能体的分布式深度神经网络算法[J].计算机技术与发展,2021,31(12):45.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 008]
　WANG Chuang,SHEN Su-bin.A Distributed Deep Neural Network Algorithm Based on Multi-agent[J].,2021,31(11):45.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 008]
[7]张 旺,侯海良.含约束和通信时滞的多智能体系统包含控制[J].计算机技术与发展,2022,32(03):34.[doi:10. 3969 / j. issn. 1673-629X. 2022. 03. 006]
　ZHANG Wang,HOU Hai-liang.Containment Control for Sampling Multi-Agent System with Input Constraints and Communication Delays[J].,2022,32(11):34.[doi:10. 3969 / j. issn. 1673-629X. 2022. 03. 006]
[8]朱辰阳,赵春晓.个人快速交通动态任务分配问题的优化研究[J].计算机技术与发展,2022,32(11):127.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 019]
　ZHU Chen-yang,ZHAO Chun-xiao.Research on Optimization of Dynamic Task Allocation in Personal Rapid Transit[J].,2022,32(11):127.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 019]
[9]王 军,曹 雷,陈希亮,等.智能博弈对抗类型及其关键技术[J].计算机技术与发展,2022,32(S2):1.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 001]
　WANG Jun,CAO Lei,CHEN Xi-liang,et al.Types and Key Technologies of Intelligent Game Confrontations[J].,2022,32(11):1.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 001]
[10]郭 鑫,王 微,青 伟,等.基于强化学习的多智能体泛化性研究[J].计算机技术与发展,2023,33(04):114.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 017]
　GUO Xin,WANG Wei,QING Wei,et al.Research on Generalization of Multi-agent Based on Reinforcement Learning[J].,2023,33(11):114.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 017]

更新日期/Last Update: 2020-11-10