Robot localization algorithm based on tight coupling of vision  inertial and radar information

Liu Jiange; Xu Chang; Dai Xin; Xu Xiaomin; Li Qingwu

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Robot localization algorithm based on tight coupling of vision inertial and radar information

更新时间：2025-09-25

- Robot localization algorithm based on tight coupling of vision inertial and radar information
- Issue 5, (2025)
- 作者机构：
  
  1. 国网江苏省电力有限公司淮安供电分公司
  2. 河海大学
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
Liu Jiange, Xu Chang, Dai Xin, et al. Robot localization algorithm based on tight coupling of vision inertial and radar information[J]. 2025, (5).
DOI：

Liu Jiange, Xu Chang, Dai Xin, et al. Robot localization algorithm based on tight coupling of vision inertial and radar information[J]. 2025, (5). DOI：

摘要

为解决在复杂的变电站环境中，巡检机器人定位性能差、精度低的问题，本文提出了一种基于视觉、惯性和雷达信息紧耦合的机器人定位算法。首先对多传感器的外参进行联合标定，引入基于位姿图的传感器外参优化策略对标定的外参进行进一步优化；然后对激光雷达获取的点云和相机获取的可见光图像进行预处理，通过预积分方式对IMU信息进行状态传播，估计机器人初始位姿；最后结合激光雷达、相机和IMU的信息进行残差构建，联合优化全局位姿，实现对巡检机器人的高精度定位。实验结果表明，本文提出的定位算法优于现有的定位算法，能够实现复杂环境下的变电站巡检机器人高精度定位。

Abstract

In order to solve the problem of poor positioning performance and low accuracy of inspection robot in complex substation environment

this paper proposes a robot positioning algorithm based on the tight coupling of vision

inertia and radar information. Firstly

the external parameters of multi-sensors are calibrated jointly

and the sensor external parameter optimization strategy based on pose map is introduced to further optimize the calibrated external parameters. Then

the point cloud obtained by lidar and the visible light image obtained by camera are preprocessed

and the IMU information is propagated by pre-integration to estimate the initial pose of the robot. Finally

the residual is constructed by combining the information of lidar

camera and IMU

and the global pose is jointly optimized to achieve high-precision positioning of the inspection robot. The experimental results show that the positioning algorithm proposed in this paper is superior to the existing positioning algorithm

and can realize high-precision positioning of substation inspection robot in complex environment.

关键词

Keywords

references

钱宇骋, 朱太云, 甄超, 等. 基于多源数据分析的变电站状态维护策略优化方法[J]. 科学技术与工程, 2021, 21(13): 5387-5393.

Kang S, Lee H. Optical Flow-Based Pose Correction for Robust Robot Localization in Corridor Environments[C]. IEEE 14th Annual Ubiquitous Computing, Electronics Mobile Communication Conference (UEMCON), 2023: 0571-0576.

Sarlin P E, Unagar A, Larsson M, et al. Back to the feature: Learning robust camera localization from pixels to pose[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021: 3247-3257.

J. Engel, T. Sch?ps, D. Cremers. Lsd-slam: Large-scale direct monocular slam[C]. European Conference on Computer Vision (ECCV), 2014: 834–849.

栾添添, 吕奉坤, 班喜程, 等. 高动态环境下的傅里叶梅林变换视觉 SLAM 算法[J]. 仪器仪表学报, 2023, 44(7): 242-251.

冯洲, 续欣莹, 郑宇轩, 等. 动态场景下基于实例分割和三维重建的多物体单目 SLAM[J]. 仪器仪表学报, 2023, 44(8): 51-62.

D. Schlegel, M. Colosi, G. Grisetti. Proslam: Graph slam from a programmer’s perspective[C]. IEEE International Conference on Robotics and Automation (ICRA), 2018: 3833–3840.

Mur-Artal R, Tardós J D. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE transactions on robotics, 2017, 33(5): 1255-1262.

Eckenhoff K, Geneva P, Huang G. MIMC-VINS: A versatile and resilient multi-IMU multi-camera visual-inertial navigation system[J]. IEEE Transactions on Robotics, 2021, 37(5): 1360-1380.

Wang Y, Li X. An improved robust EKF algorithm based on sigma points for UWB and foot-mounted IMU fusion positioning[J]. Journal of Spatial Science, 2021, 66(2): 329-350.

郭文卓, 李林阳, 程振豪, 等. 先验地图/IMU/LiDAR 的图优化和 ESKF 位姿估计方法对比[J].测绘科学, 2023, 48(4): 88-97.

Oishi S, Koide K, Yokozuka M, et al. LC*: Visual-inertial Loose Coupling for Resilient and Lightweight Direct Visual Localization[C]. 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023: 4033-4039.

iang J, Yuan J, Zhang X, et al. DVIO: An optimization-based tightly coupled direct visual-inertial odometry[J]. IEEE Transactions on Industrial Electronics, 2020, 68(11): 11212-11222.

Zhang J, Singh S. Laser–visual–inertial odometry and mapping with high robustness and low drift[J]. Journal of field robotics, 2018, 35(8): 1242-1264.

Reinke A, Palieri M, Morrell B, et al. Locus 2.0: Robust and computationally efficient lidar odometry for real-time 3d mapping[J]. IEEE Robotics and Automation Letters, 2022, 7(4): 9043-9050.

Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM: a versatile and accurate monocular SLAM system[J]. IEEE transactions on robotics, 2015, 31(5): 1147-1163.

Qin T, Li P, Shen S. Vins-mono: A robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018, 34(4): 1004-1020.

Xu W, Zhang F. Fast-lio: A fast, robust lidar-inertial odometry package by tightly-coupled iterated kalman filter[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 3317-3324.