Robust semantic SLAM with variable structure

ZHANG Zheng; LI Decai; HE Yuqing

doi:10.19304/J.ISSN1000-7180.2021.0892

Chinese

您当前的位置：

首页 >

文章列表页 >

Robust semantic SLAM with variable structure

更新时间：2026-09-04

- Robust semantic SLAM with variable structure
- Vol. 39, Issue 3, Pages: 9-16(2022)
- 作者机构：
  
  1. 中国科学院沈阳自动化研究所机器人学国家重点实验室,辽宁,沈阳,110000
  2. 中国科学院机构机器人与智能制造创新研究院,辽宁,沈阳,110000
  3. 中国科学院大学机构,北京,101408
- 作者简介：
- 基金信息：
- DOI：10.19304/J.ISSN1000-7180.2021.0892
  CLC：
- Published：2022
- 稿件说明：
移动端阅览
张铮, 李德才, 何玉庆. 变结构的鲁棒语义SLAM算法[J]. 微电子学与计算机, 2022, 39(3): 9-16.

ZHANG Zheng, LI Decai, HE Yuqing. Robust semantic SLAM with variable structure[J]. 2022, 39(3): 9-16.
张铮, 李德才, 何玉庆. 变结构的鲁棒语义SLAM算法[J]. 微电子学与计算机, 2022, 39(3): 9-16. DOI： 10.19304/J.ISSN1000-7180.2021.0892.

ZHANG Zheng, LI Decai, HE Yuqing. Robust semantic SLAM with variable structure[J]. 2022, 39(3): 9-16. DOI： 10.19304/J.ISSN1000-7180.2021.0892.

摘要

基于深度学习的飞速发展，语义信息逐渐成为SLAM(Simultaneous Location and Mapping)领域的研究热点.由于环境以及传感器本身带来的噪声问题，现有大多数语义SLAM算法所构建的语义地图中存在一些异常点，导致构建的语义地图缺乏一致性，并且影响算法精度.损失函数可以调整对异常点分配的权重，从而抑制异常点的存在.但是大多数语义SLAM算法使用的损失函数本身模型固定，不能很好地适应周围环境噪声的变化.为了解决此问题，提出了一种变结构的鲁棒语义SLAM算法，称为VS-SLAM.采用高斯混合相关熵权重函数作为损失函数，利用其可以通过调整参数，随周围环境噪声变化来改变其模型结构的特点，最大程度地拟合噪声的分布，更有利于降低算法对异常点的权重分配，提高对异常点的鲁棒性.在公开KITTI数据集上的实验表明，本文算法在建图的时间几乎相等的情况下，平均相对平移误差和旋转误差分别降低了5.36%和8.82%，并且构建的语义地图更加具有一致性.

Abstract

Based on the rapid development of deep learning

semantic information has gradually become a research hotspot in the field of SLAM (Simultaneous Location and Mapping). Due to the noise problem caused by the environment and the sensor

there are some abnormal points in the semantic map constructed by most existing semantic SLAM algorithms

which results in the lack of consistency of the constructed semantic maps and affect the accuracy of the algorithms. The loss function can adjust the weights assigned to the outliers

thereby suppressing the existence of the outliers. However

the model of loss function used by most semantic SLAM algorithms is fixed and cannot adapt well to changes in ambient noise. To solve this problem

a robust lidar semantic SLAM algorithm with variable structure is proposed

which uses Gaussian mixture correntropy weight function as the loss function

called VS-SLAM. It uses the characteristics of the model structure that can be adjusted by adjusting the parameters and changed with the surrounding environmental noise to fit the noise distribution to the greatest extent

which is more conducive to reducing the weight of the algorithm for outliers and improving robustness to the outliers. Experiments on the open KITTI dataset show that the average relative translation error and rotation error are reduced by 5.36% and 8.82% respectively

while the mapping time is almost equal

and the constructed semantic maps are more consistent.

关键词

Keywords

references

焦志鹏. 无人驾驶中SLAM定位算法研究与实现[D]. 南京: 南京邮电大学, 2020. DOI: 10.27251/d.cnki.gnjdc.2020.001394. JIAO Z P. Research and implementation of SLAM positioning algorithm in unmanned driving[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2020. DOI: 10.27251/d.cnki.gnjdc.2020.001394.

CHEN B D, WANG X, LU N, et al. Mixture correntropy for robust learning[J]. Pattern Recognition, 2018, 79: 318-327. DOI: 10.1016/j.patcog.2018.02.010.

BOWMAN S L, ATANASOV N, DANⅡLIDIS K, et al. Probabilistic data association for semantic SLAM[C]//Proceedings of 2017 IEEE International Conference on Robotics and Automation. Singapore: IEEE, 2017: 1722-1729. DOI: 10.1109/ICRA.2017.7989203.

BEHLEY J, STACHNISS C. Efficient surfel-Based SLAM using 3D laser range data in urban environments[C]//Proceedings of the 14th Robotics: Science and Systems XIV. Pittsburgh, [S. l. ]. 2018.

姜昊辰, 刘衍青, 彭镜铨, 等. 基于语义先验和深度约束的室内动态场景RGB-D SLAM算法[J]. 信息与控制, 2021, 50(3): 275-286. DOI: 10.13976/j.cnki.xk.2021.0167. JIANG H C, LIU Y Q, PENG J Q, et al. RGB-D SLAM algorithm based on semantic priors and depth constraints for dynamic indoor environment[J]. Information and Control, 2021, 50(3): 275-286. DOI: 10.13976/j.cnki.xk.2021.0167.

ROGERS J G, TREVOR A J B, NIETO-GRANDA C, et al. Simultaneous localization and mapping with learned object recognition and semantic data association[C]//Proceedings of 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. San Francisco: IEEE, 2011: 1264-1270. DOI: 10.1109/IROS.2011.6095152.

姚二亮, 张合新, 宋海涛, 等. 基于语义信息和边缘一致性的鲁棒SLAM算法[J]. 机器人, 2019, 41(6): 751-760. DOI: 10.13973/j.cnki.robot.180697. YAO E L, ZHANG H X, SONG H T, et al. Robust SLAM algorithm based on semantic information and edge consistency[J]. Robot, 2019, 41(6): 751-760. DOI: 10.13973/j.cnki.robot.180697.

BRASCH N, BOZIC A, LALLEMAND J, et al. Semantic monocular SLAM for highly dynamic environments[C]//Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems. Madrid, Spain: IEEE, 2018: 393-400. DOI: 10.1109/IROS.2018.8593828.

陈世明, 郑丽楠, 吴龙龙, 等. 面向3维空间的移动机器人快速自适应SLAM算法[J]. 信息与控制, 2012, 41(4): 419-424. DOI: 10.3724/SP.J.1219.2012.00 419. CHEN S M, ZHENG L N, WU L L, et al. A fast and adaptive SLAM algorithm for mobile robots in three-dimensional space[J]. Information and Control, 2012, 41(4): 419-424. DOI: 10.3724/SP.J.1219.2012.00 419.

杜振龙, 马芸, 李晓丽. 基于视觉SLAM的任意路径场景重建的优化[J]. 信息与控制, 2020, 49(6): 667-672. DOI: 10.13976/j.cnki.xk.2020.9475. DU Z L, MA Y, LI X L. Scene reconstruction optimization along the free trajectory based on the vision SLAM[J]. Information and Control, 2020, 49(6): 667-672. DOI: 10.13976/j.cnki.xk.2020.9475.

LI P L, QIN T, SHEN S J. Stereo vision-based semantic 3D object and ego-motion tracking for autonomous driving[C]//Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018: 664-679. DOI: 10.1007/978-3-030-01216-8_40.

TATENO K, TOMBARI F, LAINA I, et al. CNN-SLAM: real-time dense monocular SLAM with learned depth prediction[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6565-6574. DOI: 10.1109/CVPR.2017.695.

刘震. 基于语义地图视觉SLAM系统设计[D]. 北京: 北京交通大学, 2018. LIU Z. Visual SLAM system design based on semantic map[D]. Beijing: Beijing Jiaotong University, 2018.

YANG S C, HUANG Y L, SCHERER S. Semantic 3D occupancy mapping through efficient high order CRFs[C]//Proceedings of 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vancouver: IEEE, 2017: 590-597. DOI: 10.1109/IROS.2017.8202212.

CHEN X Y L, MILIOTO A, PALAZZOLO E, et al. SuMa++: efficient LiDAR-based semantic SLAM[C]//Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems. Macau, China: IEEE, 2019: 4530-4537. DOI: 10.1109/IROS40897.2019.8967704.

GEIGER A, LENZ P, URTASUN R. Are we ready for autonomous driving? The KITTI vision benchmark suite[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2012: 3354-3361. DOI: 10.1109/CVPR.2012.6248074.

MILIOTO A, VIZZO I, BEHLEY J, et al. RangeNet ++: fast and Accurate LiDAR semantic segmentation[C]//Proceedings of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems. Macau, China: IEEE, 2019: 4213-4220. DOI: 10.1109/IROS40897.2019.8967762.

LIANOS K N, SCHÖNBERGER J L, POLLEFEYS M, et al. VSO: visual semantic odometry[C]//Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018: 246-263. DOI: 10.1007/978-3-030-01225-0_15.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on the design of blockchain-based AI-generated content traceability framework

Aerial small object detection algorithm based on improved RT-DETR

Microservices anomaly detection based on the correlation of monitoring metrics

Monte carlo analysis of V-layout trench SiC neutron detector

Implementation and verification of a dual-chain power gating strategy for low power design

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰