Vision-based primary localization method for SLAM mobile robots


  • Mingcen Gu Graduate School of Advanced Technology and Science, Tokushima University, Tokushima, Japan. School of Information Science and Technology, Nantong University, Nantong, China.
  • Stephen Karungaru Graduate School of Advanced Technology and Science, Tokushima University, Tokushima, Japan.
  • Kenji Terada Graduate School of Advanced Technology and Science, Tokushima University, Tokushima, Japan.
  • Yuehua Li School of Information Science and Technology, Nantong University, Nantong, China.


SLAM, AMCL, ORB feature points, Initial pose, Identifying wall corners


The AMCL (Adaptive Monte Carlo Localization) algorithm with visual provision of initial values is proposed to address the slow localization speed caused by conventional laser SLAM (Simultaneous Localization and Mapping) without initial poses and the global localization failure after a robot abduction event. In the initial map building phase, the ORB (Oriented FAST and Rotated BRIEF) feature values are extracted from the camera and the wall corners are identified, and then the pose information is stored in the database and a feature dictionary is constructed. After restarting, the dictionary is called to perform loopback detection by receiving the images captured by the current camera, and a successful detection results in a rough initial pose. If the detection fails, the initial pose is roughly calculated by identifying the wall corners. Finally, the particle filtering algorithm scatters particles in a small area near the obtained pose and converges to obtain a relatively accurate pose.


Gaur A, Pawar M.AGV Based Material Handling System: A Literature Review [J].International Journal of Research; Scientific Innovation , Ill, 2016.

Zh. Y.C.The innovation path of AGV navigation technology [J]Logistics Technology and Applications,2018,v.23;No.221(7): 16-9

Berman S, Schechtman E, Edan Y. Evaluation Of Automatic Guided Vehicle Systems [J]. Robotics and Computer Integrated Manufacturing, 2009, 25(3): 522-8.

Vis I F A, Survey of research in the design and control of automated guided vehicle systems[J]. European Journal of Operational Research, 2004, 170(3):

Xue-Meng Yang, Min-Ru Yao, Kai Cao. A review of key problems and solutions of SLAM for mobile robots[J]. Computer System Applications,2018,27(7): 1-10

Leonard J J, Durrant-Whyte H F, Cox I J. Dynamic map building for an autonomous mobile robot[J]. International Journal of Robotics Research, 1992, 11(4): 286-298.

Smith R.C, Cheeseman P. On the representation and estimation of spatial uncertainty[J]. International Journal of Robotics Research,1987(5): 56-68.

Weininger D. Smiles I. Introduction and encoding rules[J]. Journal of Chemical Information and Computer Sciences,1988,28:31-36.

Smith R, Self M, Cheeseman P. Estimating uncertain spatial relationships in robotics[M].Autonomous robot vehicles. Springer New York, 1990: 435-461.

Kalman R E. A new approach to linear filtering and prediction problems[J]. Journal of basic Engineering,1960,82(1): 35-45.

Davison A J, Reid I D, Molton N D, et al. Mono SLAM: real-time single camera SLAMU[J].IEEE Trans Pattern Anal Mach Intell,2007,29(6):1052-1067.

Davison A J. Real-Time Simultaneous Localisation and Mapping with a SingleCamera[C]. IEEE International Conference on Computer Vision. IEEE Computer Society.2003:1403.

Doucet A, De Freitas N, Murphy K,et al. Rao-Blackwellised particle filtering for dynamic Bayesian networks[C]. Proceedings of the Sixteenth conference on Uncertainty inartificial intelligence. Morgan Kaufmann Publishers Inc., 2000: 176-183.

Montemerlo M, Thrun S, Koller D, et al. Fast SLAM: a factored solution to thesimultaneous localization and mapping problem[C]. Proc. of Theaaai National Conference on ArtificialIntelligence.2002:593-598

Grisetti G, Stachniss C, Burgard W. Improved techniques for grid mapping withrao-blackwellized particle filters [J]. IEEE Transactions on Robotics,2007,23(1): 34-46

Dong F., Liu Z, Kong D, et al. Adapting the sample size in particle filters through KLD-sampling[J]. International Journal of Robotics Research, 2003, 22(12): 985-1003.

Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C]. Nara, Japan: IEEE Computer Society,2007:1-10.

Mur-Artal R, Montiel J M M, Tardos J D .ORB-SLAM: A Versatile and Accurate Monocular SLAM System[J]. Robotics EEE Transactions on,2015,31(5):1147-1163.

Mur-Artal R, Tardos 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.

EngelJ, Schops T, Cremers D. LSD-SLAM: Large-Scale Direct monocular SLAM[C] Zurich, Switzerland: Springer Verlag, 2014: 834-849.

Engel J, Sturm J, Cremers D. Semi-dense visual odometry for a monocular camera[C]Sydney, NSW, Australia: Institute of Electrical and Electronics Engineers Inc, 2014:1449-1456.

Forster C , Pizzoli M ,Davide Scaramuzza. SVO: Fast Semi-Direct Monocular Visual Odometry[C]. EEE International Conference on Robotics & Automation. IEEE2014:15-22

Hess W, Kohler D, Rapp H, et al. Real-timeloop closure in 2D LIDAR SLAM [C]. EEE International Conference on Robotics and Automation,2016: 1271-1278.

Rosten E, Drummond T. Machine learning for high-speed corner detection[C]. Graz. Austria: Springer Verlag,2006:430-443.

Calonder M, Lepetit V, Strecha C, et al. BRIEF: Binary robust independent elementary features[C]. Springer Verlag,2010: 778-792.

Galvez-Lpez D , Tardos J D . Bags of Binary Words for Fast Place Recognition in Image Sequences[J]. Robotics, IEEE Transactions on,2012,28(5):1188-1197.

Lloyd S P . Least Squares Quantization in PCM's[J]. IEEE Transactions on Information Theory,1982,28(2):129-136.



How to Cite

Mingcen Gu, Stephen Karungaru, Kenji Terada, & Yuehua Li. (2024). Vision-based primary localization method for SLAM mobile robots. JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH, 6(3). Retrieved from