一种基于多规则约束的SLAM概率物体关联方法研究

张建博; 陶庆; 袁亮

doi:10.13568/j.cnki.651094.651316.2021.09.25.0001

您当前的位置：

首页 >

文章列表页 >

一种基于多规则约束的SLAM概率物体关联方法研究

更新时间：2026-01-21

- 一种基于多规则约束的SLAM概率物体关联方法研究
- Journal of Xinjiang University (Natural Science Edition in Chinese and English) Vol. 39, Issue 4, Pages: 492-497(2022)
- 作者机构：
  
  1. 新疆大学机械工程学院
  2. 北京化工大学信息科学与技术学院
- 作者简介：
- 基金信息：
- DOI：10.13568/j.cnki.651094.651316.2021.09.25.0001
  CLC： TP242;TP391.41
- Published：2022
- 稿件说明：
移动端阅览
[1]张建博,陶庆,袁亮.一种基于多规则约束的SLAM概率物体关联方法研究[J].新疆大学学报(自然科学版)(中英文),2022,39(04):492-497.
[1]张建博,陶庆,袁亮.一种基于多规则约束的SLAM概率物体关联方法研究[J].新疆大学学报(自然科学版)(中英文),2022,39(04):492-497. DOI： 10.13568/j.cnki.651094.651316.2021.09.25.0001.

DOI：10.13568/j.cnki.651094.651316.2021.09.25.0001.

摘要

针对单目语义同时定位与地图构建在物体关联上的关联模糊问题，提出一种基于多规则约束的概率物体关联方法．利用物体的类别、尺寸和朝向等语义信息进行物体关联，消除物体关联过程中的模糊性，从而提高SLAM的定位精度，进而可以为地图构建提供准确的位姿．通过室外公共数据集KITTI验证了基于多规则约束的概率物体关联方法能够有效提高SLAM的定位精度．

Abstract

Aiming at the ambiguous problem of simultaneous localization and mapping(SLAM) in object association

a probabilistic object association method based on multi-rule constraints was proposed. The semantic information of objects such as category

size and orientation is used for object association

eliminating the ambiguity in the process of object association

thus improving the localization accuracy of SLAM

and providing accurate pose for mapping. Based on the outdoor public dataset

it is verified that the multi-rule probabilistic object association method can effectively improve the localization accuracy of SLAM.

关键词

Keywords

references

邢志伟,朱晓蕊,何超.基于行人行为学习的机器人同时定位与可通行区域制图[J].机械工程学报,2019,55(11):36-45.

韩涛,黄友锐,周宁亚,等.基于膜计算粒子群优化的Fast SLAM算法改进[J].新疆大学学报(自然科学版)(中英文),2020,37(2):156-162.

MUR-ARTAL R,MONTIEL J M M,TARD′OS J D.ORB-SLAM:a versatile and accurate monocular SLAM system[J].IEEETransactions on Robotics,2015,31(5):1147-1163.

BOWMAN S L,ATANASOV N,DANIILIDIS K,et al.Probabilistic data association for semantic SLAM[C].Piscataway:IEEEInternational Conference on Robotics and Automation(ICRA),IEEE,2017.

DOHERTY K,FOURIE D,LEONARD J.Multimodal semantic SLAM with probabilistic data association[C].Piscataway:IEEEInternational Conference on Robotics and Automation(ICRA),IEEE,2019.

DOHERTY K J,BAXTER D P,SCHNEEWEISS E,et al.Probabilistic data association via mixture models for robust semantic SLAM[C].Piscataway:IEEE International Conference on Robotics and Automation(ICRA),IEEE,2020.

YANG S,SCHERER S.Cube SLAM:monocular 3D object SLAM[J].IEEE Transactions on Robotics,2019,35(4):925-938.

NICHOLSON L,MILFORD M,S¨UNDERHAUF N.Quadric SLAM:dual quadrics from object detections as landmarks in objectoriented SLAM[J].IEEE Robotics and Automation Letters,2019,4(1):1-8.

WU Y,ZHANG Y,ZHU D,et al.EAO-SLAM:monocular semi-dense object SLAM based on ensemble data association[C].Piscataway:IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS),IEEE,2020.

RAN T,YUAN L,ZHANG J B,et al.Not only look but infer:multiple hypothesis clustering of data association inference for semantic SLAM[J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-9.

ZHANG J B,YUAN L,RAN T,et al.Bayesian nonparametric object association for semantic SLAM[J].IEEE Robotics and Automation Letters,2021,6(3):5493-5500.

GEIGER A,LENZ P,URTASUN R.Are we ready for autonomous driving?The KITTI vision benchmark suite[C].Piscataway:IEEE Conference on Computer Vision and Pattern Recognition(CVPR),IEEE,2012.

MUR-ARTAL R,TARD′OS 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.

Views

116

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰