基于概率推断的语义SLAM数据关联方法  

A Data Association Method of Semantic SLAM Based on Probabilistic Inference Models

作　　者：陈渊博 袁亮[1,2] 周德勤 于海群 何丽 CHEN Yuanbo;YUAN Liang;ZHOU Deqin;YU Haiqun;HE Li(Xinjiang University,Urumqi 830000 China;Beijing University of Chemical Technology,Beijing 100000 China;Beijing Yupont Power Technology Co.Ltd.,Beijing 100000 China)

机构地区：[1]新疆大学,乌鲁木齐830000 [2]北京化工大学,北京100000 [3]北京煜邦电力技术股份有限公司,北京100000

出　　处：《电光与控制》2023年第2期46-50,共5页Electronics Optics & Control

基　　金：国家自然科学基金(62063033);新疆维吾尔自治区自然科学基金(2019D01C021);新疆维吾尔自治区研究生创新项目(XJ2021G050)。

摘　　要：针对传统视觉SLAM对环境语义信息理解不足的问题,语义视觉SLAM借助语义路标提高机器人的定位精度。语义路标的准确关联是实现机器人深层定位和导航的关键,错误的关联将导致机器人定位丢失。针对动态扰动和观测噪声扰动所产生的高关联模糊性问题,提出利用非参数聚类和随机近似推断结合的方法提高语义路标关联的准确性,通过正确的数据关联实现机器人的准确定位。仿真和KITTI数据集上的实验结果表明,在噪声干扰下该算法能够提高语义路标数据关联的准确性和鲁棒性,融合语义信息和几何信息优化机器人和语义路标的位姿,提高机器人的定位精度。To solve the problem that the traditional vision SLAM is not fully capable of understanding the semantic information,semantic vision SLAM uses semantic landmarks to improve the localization accuracy of the robot.Accurate association of semantic landmarks is the key to deep localization and navigation of the robot,and incorrect association will lead to loss of localization.To address the problem of high association ambiguity caused by dynamic perturbation and observation noise perturbation,a method combining nonparametric clustering with stochastic approximate inference is proposed to improve the accuracy of semantic landmark association,and accurate localization is realized by correct data association.The results of simulations and experiments on KITTI data set show that,the proposed algorithm can improve the accuracy and robustness of data association of semantic landmarks under noise perturbation,fuse the semantic and geometric information to optimize the poses of the robot and semantic landmarks,and improve the localization accuracy of the robot.

关 键 词：语义视觉SLAM 语义路标 数据关联 非参数聚类 随机近似推断 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]