[1]曾毓菁,姜勇.一种融入注意力和预测的特征选择SLAM算法[J].智能系统学报,2021,16(6):1039-1044.[doi:10.11992/tis.202010036]
 ZENG Yujing,JIANG Yong.Feature selection simultaneous localization and mapping algorithm incorporating attention and anticipation[J].CAAI Transactions on Intelligent Systems,2021,16(6):1039-1044.[doi:10.11992/tis.202010036]
点击复制

一种融入注意力和预测的特征选择SLAM算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年6期
页码:
1039-1044
栏目:
学术论文—机器感知与模式识别
出版日期:
2021-11-05

文章信息/Info

Title:
Feature selection simultaneous localization and mapping algorithm incorporating attention and anticipation
作者:
曾毓菁1234 姜勇234
1. 东北大学 信息科学与工程学院,辽宁 沈阳 110006;
2. 中国科学院 沈阳自动化研究所,辽宁 沈阳 110016;
3. 中国科学院 网络化控制系统重点实验室,辽宁 沈阳 110016;
4. 中国科学院 机器人与智能制造创新研究院,辽宁 沈阳 110169
Author(s):
ZENG Yujing1234 JIANG Yong234
1. School of Information Science and Engineering, Northeastern University, Shenyang 110006, China;
2. Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China;
3. Key Laboratory of Networked Control Systems, Chinese Acad
关键词:
即时定位与地图创建视觉注意力预测特征选择logdet度量延迟求值贪婪算法信息矩阵
Keywords:
SLAMvisionattentionanticipationfeature selectionlogdet metriclazy evaluationgreedy algorithminformation matrix
分类号:
TP391
DOI:
10.11992/tis.202010036
摘要:
针对SLAM (simultaneous localization and mapping)在急转弯、快速运动场景中定位失败的问题,提出一种融入注意力和预测的特征选择即时定位与地图创建(SLAM)算法,选择随着相机的运动更有可能保持在视野中的特征点,舍去即将消失在视野中的特征点。首先利用logdet度量量化特征选择的可行性,然后计算特征点的信息矩阵,再从检测到的特征中通过贪婪算法选择 k 个特征(近似的)最大化logdet度量,最后结合ORB-SLAM2的实际实验表明,该算法在复杂场景(如急转弯、快速运动)中可以确保定位的准确性。
Abstract:
A simultaneous localization and mapping (SLAM) algorithm incorporating attention and anticipation is proposed to solve the localization failure problem of SLAM in the scene of sharp turning and fast movement. The algorithm can select feature points that are more likely to remain in the field of view as the camera moves and discard features that are about to disappear from the field of view. The logdet metric is used to measure the feasibility of quantifying the feature selection first. The information matrix of the feature points is then calculated. From the detected features, a greedy algorithm is used to select k features (approximately) to maximize the logdet metric. The actual test combined with ORB-SLAM2 shows that the algorithm can ensure positioning accuracy in complex scenarios, such as in the scene of sharp turning and fast movement.

参考文献/References:

[1] CARRASCO M. Visual attention: The past 25 years[J]. Vision research, 2011, 51(13): 1484-1525.
[2] OUERHANI N, BUR A, HüGLI H. Visual attention-based robot self-localization[C]//Proceedings of the European Conference on Mobile Robotics. Ancona, Italy, 2005: 8-13.
[3] NEWMAN P, HO K. SLAM-loop closing with visually salient features[C]//IEEE International Conference on Robotics and Automation. Barcelona, Spain, 2005: 635-642.
[4] SALA P, SIM R, SHOKOUFANDEH A, et al. Landmark selection for vision-based navigation[J]. IEEE transactions on robotics, 2006, 22(2): 334-349.
[5] FRINTROP S, JENSFELT P. Attentional landmarks and active gaze control for visual SLAM[J]. IEEE transactions on robotics, 2008, 24(5): 1054-1065.
[6] HOCHDORFER S, SCHLEGEL C. Landmark rating and selection according to localization coverage: addressing the challenge of lifelong operation of SLAM in service robots[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. St. Louis, USA, 2009: 382-387.
[7] STRASDAT H, STACHNISS C, BURGARD W. Which landmark is useful? Learning selection policies for navigation in unknown environments[C]//2009 IEEE International Conference on Robotics and Automation. Kobe, Japan, 2009: 1410-1415.
[8] SHI Zongying, LIU Zhibin, WU Xianliang, et al. Feature selection for reliable data association in visual SLAM[J]. Machine vision and applications, 2013, 24(4): 667-682.
[9] CVI?I? I, PETROVI? I. Stereo odometry based on careful feature selection and tracking[C]//European Conference on Mobile Robots. Lincoln, UK, 2015: 1-6.
[10] MNIH V, HEESS N, GRAVES A, et al. Recurrent models of visual attention[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada, 2014: 2204-2212.
[11] DAVISON A J. Active search for real-time vision[C]//Tenth IEEE International Conference on Computer Vision. Beijing, China, 2005: 66-73.
[12] SHEN Shaojie, MULGAONKAR Y, MICHAEL N, et al. Vision-based state estimation and trajectory control towards high-speed flight with a quadrotor[C]//Proceedings of Robotics: Science and Systems X. Berlin, Germany, 2013: 865-878.
[13] FALANGA D, MUEGGLER E, FAESSLER M, et al. Aggressive quadrotor flight through narrow gaps with onboard sensing and computing using active vision[C]//IEEE International Conference on Robotics and Automation. Singapore, Singapore, 2017: 5774-5781.
[14] BIAN Fang, KEMPE D, GOVINDAN R. Utility-based sensor selection[C]//5th International Conference on Information Processing in Sensor Networks. Nashville, USA, 2006: 11-18.
[15] SHAMAIAH M, BANERJEE S, VIKALO H. Greedy sensor selection: leveraging submodularity[C]//49th IEEE Conference on Decision and Control. Atlanta, USA, 2010: 2572-2577.
[16] CARLONE L, KARAMAN S. Attention and anticipation in fast visual-inertial navigation[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). Singapore, Singapore, 2017: 3886-3893.
[17] JOHNSSON T. Efficient compilation of lazy evaluation[C]//Proceedings of the 1984 SIGPLAN symposium on Compiler construction. Montreal, Canada, 1984: 58-69.
[18] 常友渠, 肖贵元, 曾敏. 贪婪算法的探讨与研究[J]. 重庆电力高等专科学校学报, 2008, 13(3): 40-42
CHANG Youqu, XIAO Guiyuan, ZENG Ming. Discussion and research on greedy algorithm[J]. Journal of Chongqing Electric Power College, 2008, 13(3): 40-42
[19] 赵军圣, 庄光明, 王增桂. 最大似然估计方法介绍[J]. 长春理工大学学报, 2010(6): 53-54
ZHAO Junsheng, ZHUANG Guangming, WANG Zenggui. Introduction to maximum likelihood estimation method[J]. Journal of Changchun University of Science and Technology, 2010(6): 53-54
[20] LANCASTER T. The covariance matrix of the information matrix test[J]. Econometrica, 1984, 52(4): 1051-1053.
[21] 同济大学. 高等数学. 北京: 高等教育出版社, 2001.8.
[22] BURRI M, NIKOLIC J, GOHL P, et al. The EuRoC micro aerial vehicle datasets[J]. The international journal of robotics research, 2016, 35(10): 1157-1163.
[23] ESSER P, DAWES H, COLLETT J, et al. IMU: inertial sensing of vertical CoM movement[J]. Journal of biomechanics, 2009, 42(10): 1578-1581.
[24] 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.
[25] STURM J, ENGELHARD N, ENDRES F, et al. A benchmark for the evaluation of RGB-D SLAM systems[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vilamoura-Algarve, Portugal, 2012: 573-580.

相似文献/References:

[1]雷丽充,刘华平,孙富春,等.面向灵巧操作的视觉目标识别[J].智能系统学报,2015,10(01):37.[doi:10.3969/j.issn.1673-4785.201311050]
 LEI Lichong,LIU Huaping,SUN Fuchun,et al.Visual object recognition for smart manipulation[J].CAAI Transactions on Intelligent Systems,2015,10(6):37.[doi:10.3969/j.issn.1673-4785.201311050]
[2]林海涛,张华,李永龙,等.基于力传感的系留无人机定位方法研究[J].智能系统学报,2020,15(4):672.[doi:10.11992/tis.201907015]
 LIN Haitao,ZHANG Hua,LI Yonglong,et al.Research on the positioning method of tethered UAV using force sensing[J].CAAI Transactions on Intelligent Systems,2020,15(6):672.[doi:10.11992/tis.201907015]

备注/Memo

备注/Memo:
收稿日期:2020-10-29。
基金项目:国家自然科学基金项目(52075531)
作者简介:曾毓菁,硕士研究生,主要研究方向为三维重建、SLAM、配网带电作业机器人环境感知;姜勇,研究员,博士,主要研究方向为机器人智能控制、多传感器融合、特种机器人控制系统设计与集成。负责及参加完成了国家863重点项目、国家自然科学基金青年及面上项目、中科院知识创新工程重大项目、辽宁省自然科学基金项目、机器人学重点实验室项目、国网及南网重点项目等20余项。获国家发明专利授权3项、实用新型专利4项,登记软件著作权2项,参编专著2部,发表学术论文20余篇
通讯作者:姜勇.E-mail:jiangyong@sia.com
更新日期/Last Update: 2021-12-25