基于声纳的水下机器人同时定位与地图构建技术研究
摘要
智能水下机器人(Autonomous Underwater Vehicle ,AUV)要实现自治,即不依赖于人的自主识别和分辨能力,首先要具备独立的视觉系统和自定位系统。通过视觉系统,机器人才能获取水下的环境信息,为其运动和水下作业提供引导。智能水下机器人的视觉系统主要依靠“声视觉”,与传统的声纳系统不同,声视觉系统不仅要有声图像和声信息的获取能力,而且应该具备对图像和信息的处理、特征提取以及分类和识别的功能。同时定位与地图创建(Simultaneous Localization and Mapping,SLAM)是机器人技术领域的研究热点,也是实现机器人真正自主的关键。智能水下机器人基于声视觉系统和SLAM的研究具有重要的理论意义和应用价值。
在海底未知复杂环境中,绝大多数陆路环境下常用的传感器无法使用,比如光学的、无线的,在水中衰减得太快。脱离了外部导航支持的情形下,AUV唯一可依赖的是自身机载的惯性传感器和主动声纳。前视声纳及其处理系统作为水下机器人的主要传感设备,担负着发现机器人前方目标,并对目标进行定位和识别的任务。前视声纳提供障碍物目标的距离和角度,可在二维空间上(XY平面)分辨目标的轮廓和位置。在AUV的前端装备声纳设备,通过声纳探测,可以提供连续重叠的图像帧,经进一步处理可用于SLAM算法的实现。通过对声纳图像进行特征提取,将环境特征不断更新添加到特征地图中,使用SLAM算法实现AUV的自主航行。
本文使用Super Seaking DST前视声纳扫描水下环境得到仿真程序所需要的声纳图像,并将数字图像处理的方法应用于声纳图像,对声纳图像经过滤波、平滑、分割等处理后,提取出目标点特征和线特征,得到水下环境的特征地图,构建了基于环境特征的特征地图仿真平台,使用EKF SLAM算法实现了AUV的自主定位和导航的仿真,并对不同的环境特征下AUV的运行轨迹及其误差产生的原因进行了分析。
In order to achieve capability of autonomous navigation for an AUV in an unknown environment,AUV should be equipped independent visual system and the positioning system. By visual system,AUV could get around environmental information and guide its autonomous navigation. Visual system rely mainly on the "Sound Vision",it is different from the traditional sonar system,Visual system not only have the ability to obtain acoustic image and information,but also have the ability of information processing,feature extraction and classification. Simultaneous Localization and Mapping is the key point of robots autonomous navigation, the study of the sound vision and SLAM is of great theoretical significance and the value of application.
In the unknown complex undersea environment,the majority of sensors which are used in the air are unable to use in the undersea environment,such as optical and wireless,which attenuate too soon in the water. In the circumstances of lacking external navigation support,AUV can now only rely on the self contained inertial sensors and sonar. Forward looking sonar and its system as the main sensory (sensing equipment),charged with target location,identification and imaging tasks. It can provide the distance and angle data of the obstacles and distinguish the outline and location of target in the two dimensional space (XY plane).The advantage of using forward looking sonar is that the sonar can be equipped in the front end of the AUV,sonar detection provides the overlapping images frame,this will also help to achieve SLAM algorithm. Through the sonar image feature extraction,environmental features will be added to the constantly updated feature map,using SLAM algorithm implement autonomous navigation of the AUV.
This paper using forward looking sonar—Super Seaking DST sonar to scan underwater environment,using the digital image processing to extract features from sonar images,and the nearest neighbor filter algorithm to associate data. The EKF SLAM is applied to estimate underwater robot pose and build environment feature maps. The simulation results show that,the active imaging sonar can be successfully applied to AUV navigation in unknown environment; In addition,the AUV trajectories generated in the cases of using lines features and points features and the error curve also be analyzed.
在海底未知复杂环境中,绝大多数陆路环境下常用的传感器无法使用,比如光学的、无线的,在水中衰减得太快。脱离了外部导航支持的情形下,AUV唯一可依赖的是自身机载的惯性传感器和主动声纳。前视声纳及其处理系统作为水下机器人的主要传感设备,担负着发现机器人前方目标,并对目标进行定位和识别的任务。前视声纳提供障碍物目标的距离和角度,可在二维空间上(XY平面)分辨目标的轮廓和位置。在AUV的前端装备声纳设备,通过声纳探测,可以提供连续重叠的图像帧,经进一步处理可用于SLAM算法的实现。通过对声纳图像进行特征提取,将环境特征不断更新添加到特征地图中,使用SLAM算法实现AUV的自主航行。
本文使用Super Seaking DST前视声纳扫描水下环境得到仿真程序所需要的声纳图像,并将数字图像处理的方法应用于声纳图像,对声纳图像经过滤波、平滑、分割等处理后,提取出目标点特征和线特征,得到水下环境的特征地图,构建了基于环境特征的特征地图仿真平台,使用EKF SLAM算法实现了AUV的自主定位和导航的仿真,并对不同的环境特征下AUV的运行轨迹及其误差产生的原因进行了分析。
In order to achieve capability of autonomous navigation for an AUV in an unknown environment,AUV should be equipped independent visual system and the positioning system. By visual system,AUV could get around environmental information and guide its autonomous navigation. Visual system rely mainly on the "Sound Vision",it is different from the traditional sonar system,Visual system not only have the ability to obtain acoustic image and information,but also have the ability of information processing,feature extraction and classification. Simultaneous Localization and Mapping is the key point of robots autonomous navigation, the study of the sound vision and SLAM is of great theoretical significance and the value of application.
In the unknown complex undersea environment,the majority of sensors which are used in the air are unable to use in the undersea environment,such as optical and wireless,which attenuate too soon in the water. In the circumstances of lacking external navigation support,AUV can now only rely on the self contained inertial sensors and sonar. Forward looking sonar and its system as the main sensory (sensing equipment),charged with target location,identification and imaging tasks. It can provide the distance and angle data of the obstacles and distinguish the outline and location of target in the two dimensional space (XY plane).The advantage of using forward looking sonar is that the sonar can be equipped in the front end of the AUV,sonar detection provides the overlapping images frame,this will also help to achieve SLAM algorithm. Through the sonar image feature extraction,environmental features will be added to the constantly updated feature map,using SLAM algorithm implement autonomous navigation of the AUV.
This paper using forward looking sonar—Super Seaking DST sonar to scan underwater environment,using the digital image processing to extract features from sonar images,and the nearest neighbor filter algorithm to associate data. The EKF SLAM is applied to estimate underwater robot pose and build environment feature maps. The simulation results show that,the active imaging sonar can be successfully applied to AUV navigation in unknown environment; In addition,the AUV trajectories generated in the cases of using lines features and points features and the error curve also be analyzed.
引文
[1]蒋新松,封锡盛,王棣棠编著.水下机器人.沈阳:辽宁科学技术出版社,2000. 244 252
[2] [英] A.D.Waite著,王德石等译,徐韬,张明敏审.实用声纳工程.北京:电子工业出版社,2004.XI XX
[3]丁凯.基于前视声纳的水下目标跟踪技术研究:[硕士学位论文].哈尔滨:哈尔滨工程大学船舶与海洋结构物设计制造,2006
[4] Jerry L. Sutton,Underwater Acoustic Imaging,Proceedings of the IEEE,Vol.69,No.4,1979
[5] M. W. M. Gamini Dissanayake,A Solution to the Simultaneous Localization and Map Building (SLAM) Problem,IEEE Transactions on Robotics and Automation, Vol 17,No 3, June 2001.
[6] Stefan B. Williams, Paul Newman, Gamini Dissanayake and Hugh Durrant Whyte, Autonomous Underwater Simultaneous Localization and Map Building , Pro.Of ICRA'00.IEEE International Conference on Robotics and Automation vol.2,San Francisco,CA,USA.2000.1793 1798
[7] John J. Leonard1,Robert N. Carpenter2, and Hans Jacob S. Feder1,Stochastic Mapping Using Forward Look Sonar, Cambridge University Press .2001.467 480
[8] David Ribas and Pere Ridao, SLAM using an Imaging Sonar for Partially Structured Underwater Environments,Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China (2006)
[9] Durrant Wh qe H F. Where am I. A tutorial on mobile vehicle localization. Industrial Robot,1994. 11 16.
[10] M. Betke and L. Gurvits. Mobile robot localization using landmarks. IEEE Transactions on Robotics and Automation,1997.251 263.
[11] J. Castellanos,J. Neira,O. Strauss,and J. Tardos. Detecting high level features for mobile robot localization. In Proc. IEEE Int. Conference on Multi sensor Fusion and Integration for Intelligent Systems,1996.611 618
[12] J.J. Leonard and H.F. Durrant Whyte. Mobile robot localization by tracking geometric beacons. IEEE Transactions on Robotics and Automation,1991 7(3).376 382,
[13]李启虎著.声呐信号处理引论(第二版).北京:海洋出版社,2000.20 36
[14]田坦,刘国枝,孙大军编著.声纳技术.哈尔滨:哈尔滨工程大学出版社,2000.6 29
[15]刘晨晨.高分辨率成像声纳图像处理:[博士学位论文].哈尔滨:哈尔滨工程大学信号与信息处理,2006
[16] R. Simmons and S. Koenig. Probabilistic robot navigation in partially observableenvironments. In Proc. Int. Joint Conference on Artificial Intelligence,1995.1080 1087.
[17] S. Thrun,D. Fox,W. Burgard,and F. Dellaert. Robust monte carlo localization for mobile robots. Artificial Intelligence.2000.
[18] P. Jensfelt,Approaches to Mobile Robot Localization in Indoor Environments,PhD Thesis,Royal Institute of Technology (KTH).Sweden,2001.
[19] Burgard W Fox D, Henning. D, and Schmidt T. Estimating the absolute position of a mobile robot using position probability grids. In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAf96). 1996.896 901.90
[20]王文晶. EKF SLAM算法在水下航行器定位中的应用研究:[硕士学位论文].哈尔滨:哈尔滨工程大学自动化学院,2007
[21]厉茂海,洪炳熔.移动机器人的概率定位方法研究进展.机器人,2005. 27(4).380 384.
[22] Jensfelt P. Approaches to mobile robot localization in indoor environments. Sweden Royal Institute of Technology. 2001.
[23] Burgard W Derr A,Fox D. Integrating global position estimation and position tracking for mobile robots:the nainic Markov localization approach. In Proc. IEEE/RSJ Int. Con# On Intelligent Robots and Systems. 1998.730 735.
[24] Qingxiang Wu.. Bell DA, et al. Rough computational methods on reducing cost of computation in Markov localization for mobile robots. In Proc. the 4th World Congress on Intelligent Control and Automation. 2002.1226 1230.
[25] Gustafsson F. Gunnarsson F. Bergman N, et al. Particle filters for positioning, navigation,and tracking. IEEE Transactions on Signal Processing. 2002.425 435
[26]史忠科.最优估计的计算方法.北京:科学出版社,2001
[27] M. Wada,K.S. Yoon and H. Hashimoto,High Accuracy Road Vehicle State Estimation Using Extended Kalman Filter,Proceedings of 3rd.IEEE International Conference on Intelligent Transportation Systems, 2000. 282 287
[28] http://www.cs.unc.edu/ welch/kalman/kalman_ filter/kalman.html,
[29] Moravec H, Elfes A. High resoulution maps from `vide angle sonar. In Proceedings of the IEEE International Conference on Robotics and Automation(ICRA'85). 1985.116 121
[30] Amir, A. Efrat, P. Indyk, and H. Samet. Efficient Regular Data Structures and Algorithms for Location and Proximity Problems. In IEEE Symposium on Foundations of Computer Science,1999. 160 170
[31] Chong K. and Kleeman L. Mobile robot map building from an advanced sonar array and accurate odome:International Journal of Robotics Research. 1999,18(1).20 36.
[32] Cassandra A R, Kaelbling L P. Kuiren J A. Acting under uncertainty:Discrete Bayesian models for mobile robot navigation. In Proc. IEEE/RSJ International Conference on Roboticsand Systems. 1996,963 972.
[33] Kortenkamp D,and Weymouth T. Topological mapping for mobile robots using a combination of sonar and vision sensing. In Proceedings of the Twelth National Conference on Artifcial Intelligence (AAAI'94),1994.979 984.
[34] Thrun S. Learning metric topological maps for indoor mobile robot navigation. Artificial Intelligence, 1998,21 71.
[35]王璐,蔡自兴.未知环境中移动机器人并发建图与定位((CML)研究进展.机器人,2004.26(4):380 384.92
[36] Smith R, Self. M Chesseman P. Estimating uncertain spatial relationships in robotics. Uncertainty in Artificial Intelligence. 1988.435 461.
[37] Tim Bailey, Mobile Robot Localization and Mapping in Extensive Outdoor Environments, PhD thesis,The University of Sydney. August 2002
[38] J.M.Bell. A model for the simulation of sidescan sonar. PhD thesis,Heriot Watt University,Edinburgh,Scotland,September 1995.
[39] Ioseba Joaquin Tena Ruiz, Enhanced Concurrent Mapping and Localisation Using Forward looking Sonar,PhD thesis,HeriotWatt University,September 2001.
[40] R.K.Hansen and P.A.Andersen. The application of real 3D acoustical imaging. In OCEANS’98 IEEE,pages 738 741,Nice,France,September 1998.
[41] Decoding Sonar Scanline Data,Super Seaking DST sonar datasheet
[42] Software Notes for controlling and operating RS 232 Sonar* Heads, Super Seaking DST sonar datasheet
[43]周新伦,柳健,刘华志编.数字图像处理.北京:国防工业出版社,1986
[44]胡学龙,许开宇编著,章毓晋主审.数字图像处理.北京:电子工业出版社,2006.56 68,134 149
[45]陈书海,傅录祥编著.实用数字图像处理.北京:科学技术出版社,2005,139 150,360 370
[46]阮秋琦编著.数字图像处理学(第二版).电子工业出版社,2007.334 336
[47] http://www.ece.eps.hw.ac.uk/~ceeyrp/www/Teaching/B39SD2/B39SD2.html
[48]王家文,李仰军编著.MATLAB 7.0图像图像处理.北京:国防工业出版社,2006.252 266
[49] [美] R.西格沃特,I.R.诺巴克什著,李人厚译.自主移动机器人导论.西安:西安交通大学出版社,2006,1 20
[50]袁连喜.水下智能机器人声视觉成像可视化技术研究:[硕士学位论文].哈尔滨:哈尔滨工程大学水声工程,2002
[51] A.C. Schultz and W. Adams. Continuous localization using evidence grids. In IEEE International Conference on Robotics and Automation, pages 2833–2839, 1998.
[52] Thrun S. Particle filters in robotics[A].Proceedings of Uncertainty in AI(UAI 2002) [C].SanFrancisco
[53] Y. Bar Shalom and E. Tse. Tracking in a cluttered environment with probabilistic data association. Automatica,1975.451–460.
[54] J.A. Castellanos, J.M.M Montiel, J. Neira, and J.D. Tard′os. The SP map: A probabilistic framework for simultaneous localization and map building. IEEE Transactions on Robotics and Automation,1999 .15(5):948–952
[55]殷波.移动机器人同时定位与地图创建.[博士学位论文].青岛:中国海洋大学,2006
[56]刘保龙.基于声纳的移动机器人未知环境地图构建仿真平台[J].系统仿真学报,2007,19(13)
[57]王永清.同时定位与地图创建中的数据关联技术研究.[硕士学位论文].青岛:中国海洋大学电子系,2007
[58] JoséNeira and Juan D. Tardós, Data Association in Stochastic Mapping Using the Joint Compatibility Test, IEEE Transactions on Robotics and Automation,Vol,17,No 6,December 2001
[59]许枫,丛鸿文.侧扫声纳声图判别.海洋测绘.2001年第1期,58 59
[60] M. Dissanayake, P. Newman, S. Clark, H. Durrant Whyte, and M. Csorba. A solution to the simultaneous localization and mapping (slam) problem. IEEE Transactions on Robotics and Automation, 2001.
[2] [英] A.D.Waite著,王德石等译,徐韬,张明敏审.实用声纳工程.北京:电子工业出版社,2004.XI XX
[3]丁凯.基于前视声纳的水下目标跟踪技术研究:[硕士学位论文].哈尔滨:哈尔滨工程大学船舶与海洋结构物设计制造,2006
[4] Jerry L. Sutton,Underwater Acoustic Imaging,Proceedings of the IEEE,Vol.69,No.4,1979
[5] M. W. M. Gamini Dissanayake,A Solution to the Simultaneous Localization and Map Building (SLAM) Problem,IEEE Transactions on Robotics and Automation, Vol 17,No 3, June 2001.
[6] Stefan B. Williams, Paul Newman, Gamini Dissanayake and Hugh Durrant Whyte, Autonomous Underwater Simultaneous Localization and Map Building , Pro.Of ICRA'00.IEEE International Conference on Robotics and Automation vol.2,San Francisco,CA,USA.2000.1793 1798
[7] John J. Leonard1,Robert N. Carpenter2, and Hans Jacob S. Feder1,Stochastic Mapping Using Forward Look Sonar, Cambridge University Press .2001.467 480
[8] David Ribas and Pere Ridao, SLAM using an Imaging Sonar for Partially Structured Underwater Environments,Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China (2006)
[9] Durrant Wh qe H F. Where am I. A tutorial on mobile vehicle localization. Industrial Robot,1994. 11 16.
[10] M. Betke and L. Gurvits. Mobile robot localization using landmarks. IEEE Transactions on Robotics and Automation,1997.251 263.
[11] J. Castellanos,J. Neira,O. Strauss,and J. Tardos. Detecting high level features for mobile robot localization. In Proc. IEEE Int. Conference on Multi sensor Fusion and Integration for Intelligent Systems,1996.611 618
[12] J.J. Leonard and H.F. Durrant Whyte. Mobile robot localization by tracking geometric beacons. IEEE Transactions on Robotics and Automation,1991 7(3).376 382,
[13]李启虎著.声呐信号处理引论(第二版).北京:海洋出版社,2000.20 36
[14]田坦,刘国枝,孙大军编著.声纳技术.哈尔滨:哈尔滨工程大学出版社,2000.6 29
[15]刘晨晨.高分辨率成像声纳图像处理:[博士学位论文].哈尔滨:哈尔滨工程大学信号与信息处理,2006
[16] R. Simmons and S. Koenig. Probabilistic robot navigation in partially observableenvironments. In Proc. Int. Joint Conference on Artificial Intelligence,1995.1080 1087.
[17] S. Thrun,D. Fox,W. Burgard,and F. Dellaert. Robust monte carlo localization for mobile robots. Artificial Intelligence.2000.
[18] P. Jensfelt,Approaches to Mobile Robot Localization in Indoor Environments,PhD Thesis,Royal Institute of Technology (KTH).Sweden,2001.
[19] Burgard W Fox D, Henning. D, and Schmidt T. Estimating the absolute position of a mobile robot using position probability grids. In Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAf96). 1996.896 901.90
[20]王文晶. EKF SLAM算法在水下航行器定位中的应用研究:[硕士学位论文].哈尔滨:哈尔滨工程大学自动化学院,2007
[21]厉茂海,洪炳熔.移动机器人的概率定位方法研究进展.机器人,2005. 27(4).380 384.
[22] Jensfelt P. Approaches to mobile robot localization in indoor environments. Sweden Royal Institute of Technology. 2001.
[23] Burgard W Derr A,Fox D. Integrating global position estimation and position tracking for mobile robots:the nainic Markov localization approach. In Proc. IEEE/RSJ Int. Con# On Intelligent Robots and Systems. 1998.730 735.
[24] Qingxiang Wu.. Bell DA, et al. Rough computational methods on reducing cost of computation in Markov localization for mobile robots. In Proc. the 4th World Congress on Intelligent Control and Automation. 2002.1226 1230.
[25] Gustafsson F. Gunnarsson F. Bergman N, et al. Particle filters for positioning, navigation,and tracking. IEEE Transactions on Signal Processing. 2002.425 435
[26]史忠科.最优估计的计算方法.北京:科学出版社,2001
[27] M. Wada,K.S. Yoon and H. Hashimoto,High Accuracy Road Vehicle State Estimation Using Extended Kalman Filter,Proceedings of 3rd.IEEE International Conference on Intelligent Transportation Systems, 2000. 282 287
[28] http://www.cs.unc.edu/ welch/kalman/kalman_ filter/kalman.html,
[29] Moravec H, Elfes A. High resoulution maps from `vide angle sonar. In Proceedings of the IEEE International Conference on Robotics and Automation(ICRA'85). 1985.116 121
[30] Amir, A. Efrat, P. Indyk, and H. Samet. Efficient Regular Data Structures and Algorithms for Location and Proximity Problems. In IEEE Symposium on Foundations of Computer Science,1999. 160 170
[31] Chong K. and Kleeman L. Mobile robot map building from an advanced sonar array and accurate odome:International Journal of Robotics Research. 1999,18(1).20 36.
[32] Cassandra A R, Kaelbling L P. Kuiren J A. Acting under uncertainty:Discrete Bayesian models for mobile robot navigation. In Proc. IEEE/RSJ International Conference on Roboticsand Systems. 1996,963 972.
[33] Kortenkamp D,and Weymouth T. Topological mapping for mobile robots using a combination of sonar and vision sensing. In Proceedings of the Twelth National Conference on Artifcial Intelligence (AAAI'94),1994.979 984.
[34] Thrun S. Learning metric topological maps for indoor mobile robot navigation. Artificial Intelligence, 1998,21 71.
[35]王璐,蔡自兴.未知环境中移动机器人并发建图与定位((CML)研究进展.机器人,2004.26(4):380 384.92
[36] Smith R, Self. M Chesseman P. Estimating uncertain spatial relationships in robotics. Uncertainty in Artificial Intelligence. 1988.435 461.
[37] Tim Bailey, Mobile Robot Localization and Mapping in Extensive Outdoor Environments, PhD thesis,The University of Sydney. August 2002
[38] J.M.Bell. A model for the simulation of sidescan sonar. PhD thesis,Heriot Watt University,Edinburgh,Scotland,September 1995.
[39] Ioseba Joaquin Tena Ruiz, Enhanced Concurrent Mapping and Localisation Using Forward looking Sonar,PhD thesis,HeriotWatt University,September 2001.
[40] R.K.Hansen and P.A.Andersen. The application of real 3D acoustical imaging. In OCEANS’98 IEEE,pages 738 741,Nice,France,September 1998.
[41] Decoding Sonar Scanline Data,Super Seaking DST sonar datasheet
[42] Software Notes for controlling and operating RS 232 Sonar* Heads, Super Seaking DST sonar datasheet
[43]周新伦,柳健,刘华志编.数字图像处理.北京:国防工业出版社,1986
[44]胡学龙,许开宇编著,章毓晋主审.数字图像处理.北京:电子工业出版社,2006.56 68,134 149
[45]陈书海,傅录祥编著.实用数字图像处理.北京:科学技术出版社,2005,139 150,360 370
[46]阮秋琦编著.数字图像处理学(第二版).电子工业出版社,2007.334 336
[47] http://www.ece.eps.hw.ac.uk/~ceeyrp/www/Teaching/B39SD2/B39SD2.html
[48]王家文,李仰军编著.MATLAB 7.0图像图像处理.北京:国防工业出版社,2006.252 266
[49] [美] R.西格沃特,I.R.诺巴克什著,李人厚译.自主移动机器人导论.西安:西安交通大学出版社,2006,1 20
[50]袁连喜.水下智能机器人声视觉成像可视化技术研究:[硕士学位论文].哈尔滨:哈尔滨工程大学水声工程,2002
[51] A.C. Schultz and W. Adams. Continuous localization using evidence grids. In IEEE International Conference on Robotics and Automation, pages 2833–2839, 1998.
[52] Thrun S. Particle filters in robotics[A].Proceedings of Uncertainty in AI(UAI 2002) [C].SanFrancisco
[53] Y. Bar Shalom and E. Tse. Tracking in a cluttered environment with probabilistic data association. Automatica,1975.451–460.
[54] J.A. Castellanos, J.M.M Montiel, J. Neira, and J.D. Tard′os. The SP map: A probabilistic framework for simultaneous localization and map building. IEEE Transactions on Robotics and Automation,1999 .15(5):948–952
[55]殷波.移动机器人同时定位与地图创建.[博士学位论文].青岛:中国海洋大学,2006
[56]刘保龙.基于声纳的移动机器人未知环境地图构建仿真平台[J].系统仿真学报,2007,19(13)
[57]王永清.同时定位与地图创建中的数据关联技术研究.[硕士学位论文].青岛:中国海洋大学电子系,2007
[58] JoséNeira and Juan D. Tardós, Data Association in Stochastic Mapping Using the Joint Compatibility Test, IEEE Transactions on Robotics and Automation,Vol,17,No 6,December 2001
[59]许枫,丛鸿文.侧扫声纳声图判别.海洋测绘.2001年第1期,58 59
[60] M. Dissanayake, P. Newman, S. Clark, H. Durrant Whyte, and M. Csorba. A solution to the simultaneous localization and mapping (slam) problem. IEEE Transactions on Robotics and Automation, 2001.