室内环境下立体视觉惯导融合定位

doi:10.13474/j.cnki.11-2246.2019.0377

测绘通报 ›› 2019, Vol. 0 ›› Issue (12): 12-17.doi: 10.13474/j.cnki.11-2246.2019.0377

• 人工智能与高精度地图 • 上一篇下一篇

室内环境下立体视觉惯导融合定位

敖龙辉, 郭杭

南昌大学, 江西南昌 330031

收稿日期:2019-03-14 发布日期:2020-01-03
通讯作者: 郭杭。E-mail:guo1_2002@hotmail.com E-mail:guo1_2002@hotmail.com
作者简介:敖龙辉(1993-),男,硕士生,主要从事机器视觉导航定位方面的研究。E-mail:787155843@qq.com
基金资助:
科技部重点研发项目（2016YFB0502002）；国家自然科学基金（41764002；41374039）；南昌大学研究生创新专项资金项目（CX2018156）

Fusion location method of stereo vision inertial navigation system in indoor environment

AO Longhui, GUO Hang

Nanchang University, Nanchang 330031, China

Received:2019-03-14 Published:2020-01-03

摘要/Abstract

摘要： 针对室内服务机器人在居家环境下导航定位问题，本文研究了紧耦合非线性优化的立体视觉惯性融合导航方法。本文采用预积分、边缘化、滑动窗口优化等关键技术，提出了一种稳健的视觉惯性导航系统初始化方法。运用于室内家庭服务机器人中，设计并实现了对应的视觉惯性融合导航系统。在搭建的模拟居家环境下，验证了本文系统的初始化方法能够提供稳健、准确的系统初值；最后通过试验验证了本文定位系统的准确性与稳定性，定位误差可控制在0.1 m以内。

关键词: IMU预积分, 滑动窗口优化, 室内机器人, 立体视觉惯导融合, 导航定位

Abstract: Aiming at the navigation and positioning problem of indoor service robots in the home environment, this paper studies the stereo-integrated inertial fusion navigation method based on tightly coupled nonlinear optimization. The method adopts key technologies such as pre-integration, edge-based and sliding window optimization, and proposes a robust initialization method of visual inertial navigation system. Used in indoor home service robots, the corresponding visual inertial fusion navigation system is designed and implemented. In the simulated home environment, the initialization method of the system can provide robust and accurate initial values. Finally, the accuracy and stability of the positioning system are verified by experiments. The positioning error can be controlled within 0.1 m.

Key words: IMU pre-integration, sliding window optimization, indoor robot, stereoscopic visual inertial navigation fusion, navigating positioning

中图分类号:

P228

敖龙辉, 郭杭. 室内环境下立体视觉惯导融合定位[J]. 测绘通报, 2019, 0(12): 12-17.

AO Longhui, GUO Hang. Fusion location method of stereo vision inertial navigation system in indoor environment[J]. Bulletin of Surveying and Mapping, 2019, 0(12): 12-17.

参考文献

[1] FORSTER C, PIZZOLI M, SCARAMUZZA D. SVO:fast semi-direct monocular visual-odometry[C]//Proceedings of the IEEE Interhational Conference on Robotics and Automation. Hong Kong, China:IEEE 2014.
[2] ENGEL J, SCHOPS T, CREMERS D. Lsd-slam:large-scale direct monocular slam[C]//European Conference on Computer Vision.[S.l.]:Springer International Publishing, 2014.
[3] ENGEL J, KOLTUN V, CREMERS D. DSO:direct sparse odometry[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.[S.l.]:IEEE,2017.
[4] MUR-ARTAL R, MONTIEL J, TARDOS J D. Orb-slam:a versatile and accurate monocular slam system[J]. IEEE Transactions on Robotics, 2015,31(5):1147-1163.
[5] BRITTING K R. Inertial navigation systems analysis[M].[S.l.]:Artech House Publishers, 1971.
[6] PAUL M K, WU K, HESCH J A, et al. Acomparative analysis of tightly-coupled monocular, binocular, and stereo VINS[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2017:165-172.
[7] LEUTENEGGER S, LYNEN S, BOSSE M, et al. Keyframe-based visual-inertial odometry using nonlinear optimization[J].International Journal of Robotics Research, 2015, 34(3):314-334.
[8] USENKO V, ENGEL J, STVCKLER J, et al. Direct visual-inertial odometry with stereo cameras[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2016:1885-1892.
[9] HUAI J Z, TOTH C K, GREJNER-BRZEZINSKA D A. Stereo-inertial odometry using nonlinear optimization[C]//28th International Technical Meeting of the Satellite Division of the Institute of Navigation. Tampa, USA:Institute of Navigation, 2015:2087-2097.
[10] LUPTON T,SUKKARIEH S. Visual-inertial-aided navigation for high-dynamic motion in built environments without initial conditions[J]. IEEE Transactions on Robotics, 2012, 28(1):61-76.
[11] GUI J,GU D,WANG S. A review of visua-inertial odometry from filtering and optimization perspectives[J].Advanced Robotics, 2015, 29(20):1289-1301.
[12] FORSTER C, CARLONE L, DELLAERT F, et al. On-manifold preinte-gration for real-time visual-inertial odometry[J]. IEEE Transactions on Robotics, 2017, 33(1):1-21.
[13] HARRIS C, STEPHENS M. A combined corner and edge detector[C]//Proceedings of the 4th Alvey vision conference.[S.l.]:Citeseer, 1988.
[14] LUCAS B D, KANADE T. An iterative image registration technique with an application to stereo vision[C]//Proceedings of the 1981 DARPA Image Understanding Workshop.[S.l.]:Workshop, 1981.
[15] 王辰, 郑顺义, 朱锋博, 等.一种基于多目视觉的无人机实时定位方法[J]. 测绘通报,2018(4):32-35,82.

室内环境下立体视觉惯导融合定位

Fusion location method of stereo vision inertial navigation system in indoor environment

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李林阳, 柴洪洲, 李姗姗, 乔书波, 邝英才, 吕志平. 海洋立体观测网建设与发展综述[J]. 测绘通报, 2021, 0(5): 30-37,95.
[2]	肖业伟, 谢小刚. 强跟踪抗差自适应滤波算法及其在无人机导航定位中的应用[J]. 测绘通报, 2021, 0(4): 64-67.
[3]	窦超, 安向东, 赵利江, 张生鹏, 毕泰武. 格尔木市高精度数字高程基准模型研究[J]. 测绘通报, 2020, 0(8): 108-111.
[4]	张熙, 陈现春, 包海. 星座异构基准站网虚拟参考站数据生成方法[J]. 测绘通报, 2020, 0(2): 66-71.
[5]	王一文, 钱闯, 唐健, 温景仁, 牛小骥. 预建高精度地图的封闭区域UGV自动驾驶导航定位[J]. 测绘通报, 2020, 0(1): 21-25.
[6]	董明旭, 楚彬, 刘紫平, 郝建明, 匡翠林. 一种基于CORS的GNSS事后精密定位服务平台建设方法[J]. 测绘通报, 2018, 0(8): 18-25.
[7]	陈明, 张鹏, 武军郦, 张秋义. 卫星导航定位基准站标准体系构建分析[J]. 测绘通报, 2018, 0(10): 84-87,112.
[8]	连达军, 陈国栋, 袁铭, 张序. “卫星导航定位原理”课程研究性教学法探讨[J]. 测绘通报, 2018, 0(1): 161-164.
[9]	刘成, 郭树人, 李芳. 卫星导航定位卡尔曼滤波时延平滑方法研究[J]. 测绘通报, 2017, 0(11): 6-10,26.
[10]	薛卫星, 邱卫宁, 花向红, 张晓章, 蒋胜华. WiFi信号强度空间分辨率的研究分析[J]. 测绘通报, 2016, 0(9): 43-46.
[11]	刘艳国, 秘金钟, 李得海, 张晶晶, 王霞迎. BDS基线解算不同时段精度差异分析[J]. 测绘通报, 2016, 0(6): 1-5.
[12]	章迪, 许才军, 陈巍, 张煜. GNSS三维仿真测量实践教学系统的实现[J]. 测绘通报, 2016, 0(5): 120-122,134.
[13]	辛洁, 任晖, 王冬霞, 赵金贤, 胡彩波. GPS信号改正参数研究[J]. 测绘通报, 2016, 0(3): 22-24,28.
[14]	周立, 赵新生, 蒋廷臣, 汤均博, 王继刚, 白珏莹. 港口航道陆域形变监测动态空间基准框架构建[J]. 测绘通报, 2015, 0(4): 22-24.
[15]	张超, 李得海, 章传银, 秘金钟, 宋志英. 一种新型激光测距定位系统交会角适用条件研究[J]. 测绘通报, 2015, 0(3): 16-18,57.