A survey of simultaneous localization and mapping on unstructured lunar complex environment

Simultaneous localization and mapping (SLAM) technology is the key to realizing lunar rover’s intelligent perception and autonomous navigation. It embodies the autonomous ability of mobile robot, and has attracted plenty of concerns of researchers in the past thirty years. Visual sensors are meaningful to SLAM research because they can provide a wealth of information. Visual SLAM uses merely images as external information to estimate the location of the robot and construct the environment map. Nowadays, SLAM technology still has problems when applied in large-scale, unstructured and complex environment. Based on the latest technology in the field of visual SLAM, this paper investigates and summarizes the SLAM technology using in the unstructured complex environment of lunar surface. In particular, we focus on summarizing and comparing the detection and matching of features of SIFT, SURF and ORB, in the meanwhile discussing their advantages and disadvantages. We have analyzed the three main methods: SLAM Based on Extended Kalman Filter, SLAM Based on Particle Filter and SLAM Based on Graph Optimization (EKF-SLAM, PF-SLAM and Graph-based SLAM). Finally, this article summarizes and discusses the key scientific and technical difficulties in the lunar context that Visual SLAM faces. At the same time, we have explored the frontier issues such as multi-sensor fusion SLAM and multi-robot cooperative SLAM technology. We also predict and prospect the development trend of lunar rover SLAM technology, and put forward some ideas of further research.Simultaneous localization and mapping (SLAM) technology is the key to realizing lunar rover’s intelligent perception and autonomous navigation. It embodies the autonomous ability of mobile robot, and has attracted plenty of concerns of researchers in the past thirty years. Visual sensors are meaningful to SLAM research because they can provide a wealth of information. Visual SLAM uses merely images as external information to estimate the location of the robot and construct the environment map. Nowadays, SLAM technology still has problems when applied in large-scale, unstructured and complex environment. Based on the latest technology in the field of visual SLAM, this paper investigates and summarizes the SLAM technology using in the unstructured complex environment of lunar surface. In particular, we focus on summarizing and comparing the detection and matching of features of SIFT, SURF and ORB, in the meanwhile discussing their advantages and disadvantages. We have analyzed the three main methods: SLAM B...

[1]  John J. Leonard,et al.  Directed Sonar Sensing for Mobile Robot Navigation , 1992 .

[2]  Ronald Azuma,et al.  Improving static and dynamic registration in an optical see-through HMD , 1994, SIGGRAPH.

[3]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[4]  Eduardo Mario Nebot,et al.  Optimization of the simultaneous localization and map-building algorithm for real-time implementation , 2001, IEEE Trans. Robotics Autom..

[5]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[6]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[7]  Sebastian Thrun,et al.  FastSLAM 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges , 2003, IJCAI.

[8]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[9]  Hassan Hajjdiab,et al.  Vision-based multi-robot simultaneous localization and mapping , 2004, First Canadian Conference on Computer and Robot Vision, 2004. Proceedings..

[10]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[11]  Tom Drummond,et al.  Edge landmarks in monocular SLAM , 2009, Image Vis. Comput..

[12]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[13]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[14]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[16]  Luis Miguel Bergasa,et al.  Real-time wide-angle stereo visual SLAM on large environments using SIFT features correction , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  W. Sardha Wijesoma,et al.  Extended rao-blackwellised genetic algorithmic filter SLAM in dynamic environment with raw sensor measurement , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Zhou Di.  Analysis of the Consistency of EKF-based SLAM , 2008 .

[19]  Kurt Konolige,et al.  CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching , 2008, ECCV.

[20]  Chandana Paul,et al.  Hybrid laser and vision based object search and localization , 2008, 2008 IEEE International Conference on Robotics and Automation.

[21]  Jaime Valls Miró,et al.  Information-Efficient 3-D Visual SLAM for Unstructured Domains , 2008, IEEE Transactions on Robotics.

[22]  Jin Ye,et al.  The Realizing of Autonomous Navigation in Lunar Rover Virtual Simulation System , 2009 .

[23]  Eryong Wu,et al.  Monocular vision SLAM based on key feature points selection , 2010, The 2010 IEEE International Conference on Information and Automation.

[24]  Dai-xian Zhu.  Binocular Vision-SLAM Using Improved SIFT Algorithm , 2010, 2010 2nd International Workshop on Intelligent Systems and Applications.

[25]  Md Jan Nordin,et al.  SIFT based monocular SLAM with multi-clouds features for indoor navigation , 2010, TENCON 2010 - 2010 IEEE Region 10 Conference.

[26]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[27]  Zhang Lianxiu.  A Three-dimensional Localization Algorithm of Lunar Rover Based on Binocular Vision , 2012 .

[28]  Vincent Lepetit,et al.  BRIEF: Computing a Local Binary Descriptor Very Fast , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Huaqing Min,et al.  Graph-based SLAM: A Survey , 2013 .

[30]  Ye You.  The Research of SLAM Monocular Vision Based on The Improved SURF Feather , 2014, 2014 International Conference on Computational Intelligence and Communication Networks.

[31]  Wolfram Burgard,et al.  3-D Mapping With an RGB-D Camera , 2014, IEEE Transactions on Robotics.

[32]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

[33]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[34]  Paolo Valigi,et al.  Exploring Representation Learning With CNNs for Frame-to-Frame Ego-Motion Estimation , 2016, IEEE Robotics and Automation Letters.