基于TEASER算法的空间非合作目标位姿估计  

Pose Estimation of Space Non-Cooperative Target Based on TEASER Algorithm

作　　者：王世昌 华宝成[1] 周依尔 李小路 WANG Shichang;HUA Baocheng;ZHOU Yier;LI Xiaolu(Space Optoelectronic Measurement and Perception Lab.,Beijing Institute of Control Engineering,Beijing 100094,China;School of Instrumentation and Optoelectronic Engineering,Beihang University,Beijing 100191,China)

机构地区：[1]北京控制工程研究所空间光电测量与感知实验室,北京100094 [2]北京航空航天大学仪器科学与光电工程学院,北京100191

出　　处：《空间控制技术与应用》2024年第1期25-34,共10页Aerospace Control and Application

基　　金：国家重点研发计划(2018YFB0504500);空间智能控制技术实验室开放基金(2021-JCJQ-LB-010-05);光电测量与智能感知中关村开放实验室开放基金(LabSOMP202101)

摘　　要：基于点云的空间非合作目标位姿估计,常受到噪声影响.提出截断最小二乘估计与半定松弛(truncated least squares estimation and semidefinite relaxation,TEASER)与迭代最近点(iterative closest point,ICP)的结合算法,提升空间非合作目标位姿估计精度与鲁棒性.该方法包括粗配准与精配准两个环节:在粗配准环节中,基于局部点云与模型点云的方向直方图特征(signature of histogram of orientation,SHOT)确定匹配对,利用TEASER算法求解初始位姿;在精配准环节中,可结合ICP算法优化位姿估计结果.北斗卫星仿真实验表明:在连续帧位姿估计中,噪声标准差为3倍点云分辨率时,基于TEASER的周期关键帧配准方法的平移误差小于3.33 cm,旋转误差小于2.18°;与传统ICP方法相比,平均平移误差与平均旋转误差均有所降低.这表明所提出的空间非合作目标位姿估计方法具有良好的精度和鲁棒性.The pose estimation of space non-cooperative targets based on point cloud is often affected by noise.In order to improve the accuracy and robustness of pose estimation for space non-cooperative targets,a combination algorithm of truncated least squares estimation and semidefinite relaxation(TEASER)and iterative closest point(ICP)is proposed in this paper.The method includes two parts:coarse registration and fine registration.In coarse registration,the matching pair is found by the signature of histogram of orientation(SHOT)of local point cloud and model point cloud,and then the initial pose is solved by TEASER.In fine registration,ICP is used to optimize the pose estimation results.The Beidou satellite simulation experiment shows that when the noise standard deviation is 3 times the resolution of the point cloud,the translation error of the periodic key frame registration method based on TEASER is less than 3.33cm,and the rotation error is less than 2.18°in the pose estimation of continuous frames.Compared with the traditional ICP method,the average translation error and average rotation error are reduced.The results show that the proposed pose estimation method has good accuracy and robustness.

关 键 词：空间非合作目标 位姿估计 点云配准 截断最小二乘估计与半定松弛算法 迭代最近点算法 

分 类 号：TN958.98[电子电信—信号与信息处理] V11[电子电信—信息与通信工程]