UAV Navigation Algorithm Based on Improved Algorithm of Simultaneous Localization and Mapping with Adaptive Local Range of Observations

Authors: Geng Ke Ke, Chulin A.N. Published: 28.05.2017
Published in issue: #3(114)/2017  
DOI: 10.18698/0236-3933-2017-3-76-94

Category: Informatics, Computer Engineering and Control | Chapter: System Analysis, Control, and Information Processing  
Keywords: UAV, improved algorithm for EKF-SLAM, data fusion, characteristic points

The paper proposes an improved algorithm for the extended Kalman filter for simultaneous localization and mapping (EKF-SLAM), allowing the essential reduction of the amount of computation required by adapting the range of observation in real time in different threedimensional environments for unmanned aerial vehicles (UAVs). We built cloudy-point environment map and calculated coordinates of the characteristic points using 8-point normalized algorithm based on computer vision monocular. The improvement is achieved by adaptive dynamic restriction of the current dimensions of the environmental observable part and the number of observable targets for UAV positioning correction. The simulation results show that the proposed method significantly reduces the volume of calculations, while maintaining the accuracy of localization, and can be applied to the UAV navigation.


[1] Cheeseman P., Smith R., Self M. A stochastic map for uncertain spatial relationships. 4th Int. Symp. on Robotic Research, 1987, pp. 467-474.

[2] Biswas J., Veloso M. Depth camera based indoor mobile robot localization and navigation. IEEE Int. Conf. on Robotics and Automation, 2012, pp. 1697-1702. DOI: 10.1109/ICRA.2012.6224766 Available at: http://ieeexplore.ieee.org/document/6224766

[3] Tu Y., Huang Z., Zhang X., et al. The mobile robot SLAM based on depth and visual sensing in structured environment. Robot Intelligence Technology and Applications 3, 2015, pp. 343-357. DOI: 10.1007/978-3-319-16841-8_32 Available at: https://link.springer.com/chapter/10.1007/978-3-319-16841-8_32

[4] Choi Y.W., Kim K.D., Choi J.W., Lee S.G. Laser image SLAM based on image matching for navigation of a mobile robot. Journal of the Korean Society for Precision Engineering, 2013, vol. 30, no. 2, pp. 177-184. DOI: 10.7736/KSPE.2013.30.2.177 Available at: http://koreascience.or.kr/article/ArticleFullRecord.jsp?cn=JMGHBV_2013_v30n2_177

[5] Fabresse F.R., Caballero F., Maza I., Ollero A. Localization and mapping for aerial manipulation based on range-only measurements and visual markers. IEEE Int. Conf. on Robotics and Automation (ICRA), 2014, pp. 2100-2106. DOI: 10.1109/ICRA.2014.6907147 Available at: http://ieeexplore.ieee.org/document/6907147

[6] Roh H.C., Sung C.H., Kang M.T., Chung M.J. Fast SLAM using polar scan matching and particle weight based occupancy grid map for mobile robot. 8th Int. Conf. on Ubiquitous Robots and Ambient Intelligence (URAI), 2011, pp. 756-757. DOI: 10.1109/URAI.2011.6146004 Available at: http://ieeexplore.ieee.org/document/6146004

[7] Qu L., He S., Qu Y. An SLAM algorithm based on improved UKF. 24th Chinese Control and Decision Conf. (CCDC), 2012, pp. 4154-4157. DOI: 10.1109/CCDC.2012.6243112 Available at: http://ieeexplore.ieee.org/document/6243112

[8] Chatterjee A., Ray O., Chatterjee A., Rakshit A. Development of a real-life EKF based SLAM system for mobile robots employing vision sensing. Expert Systems with Applications, 2011, vol. 38, no. 7, pp. 8266-8274. DOI: 10.1016/j.eswa.2011.01.007 Available at: http://www.sciencedirect.com/science/article/pii/S0957417411000273

[9] Sola J., Vidal-Calleja T., Civera J., Montiel J.M.M. Impact of landmark parametrization on monocular EKF-SLAM with points and lines. Int. Journal of Computer Vision, 2012, vol. 97, no. 3, pp. 339-368. DOI: 10.1007/s11263-011-0492-5 Available at: https://link.springer.com/article/10.1007/s11263-011-0492-5

[10] Bailey T., Nieto J., Guivant J., Stevens M., Nebot E. Consistency of the EKF-SLAM algorithm. IEEE/RSJInt. Conf. on Intelligent Robots and Systems, 2006, pp. 3562-3568. DOI: 10.1109/IROS.2006.281644 Available at: http://ieeexplore.ieee.org/document/4058955

[11] Ke Ke Geng. An improved EKF-SLAM algorithm for mobile robot. Internauka, 2016, no. 2, pp. 74-78.

[12] Krig S. Computer vision metrics: Survey, taxonomy, and analysis. Apress, 2014.

[13] Smith S.M., Brady J.M. SUSAN - a new approach to lowlevel image processing. Int. Journal of Computer Vision, 1997, vol. 23, no. 1, pp. 45-78. DOI: 10.1023/A:1007963824710 Available at: https://link.springer.com/article/10.1023%2FA%3A1007963824710

[14] Geng Ke Ke, Chulin N.A. Environment reconstruction method with cloudy-point maps based on real-time monocular computer vision. Mezhdunarodnyy zhurnal eksperimental’nogo obrazovaniya [International Journal of Experimental Education], 2015, no. 12-3, pp. 437-442. Available at: https://expeducation.ru/ru/article/view?id=9163

[15] Di Stefano L., Mattoccia S., Mola M. An efficient algorithm for exhaustive template matching based on normalized cross correlation. Proc. 12th Int. Conf. on Image Analysis and Processing, 2003, pp. 322-327. DOI: 10.1109/ICIAP.2003.1234070 Available at: http://ieeexplore.ieee.org/document/1234070

[16] Armangue X., Salvi J. Overall view regarding fundamental matrix estimation. Image and Vision Computing, 2003, vol. 21, no. 2, pp. 205-220. DOI: 10.1016/S0262-8856(02)00154-3 Available at: http://www.sciencedirect.com/science/article/pii/S0262885602001543

[17] Camera calibration toolbox for Matlab. vision.caltech: website Available at: http://www.vision.caltech.edu/bouguetj/calib_doc (accessed 19.10.2016).

[18] Hartley R.I. Estimation of relative camera positions for uncalibrated cameras. European Conf. on Computer Vision, 1992, pp. 579-587. DOI: 10.1007/3-540-55426-2_62 Available at: https://link.springer.com/chapter/10.1007/3-540-55426-2_62?no-access=true

[19] Hartley R., Zisserman A. Multiple view geometry in computer vision. Cambridge University Press, 2003.

[20] Bunschoten R., Krose B. Visual odometry from an omnidirectional vision system. IEEE Int. Conf. on Robotics and Automation, 2003, vol. 1, pp. 577-583. DOI: 10.1109/ROBOT.2003.1241656 Available at: http://ieeexplore.ieee.org/document/1241656

[21] Nister D., Naroditsky O., Bergen J. Visual odometry. Proc. 2004 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2004, no. 1, pp. 652-659. DOI: 10.1109/CVPR.2004.1315094 Available at: http://ieeexplore.ieee.org/document/1315094

[22] Dissanayake M.G., Newman P., Clark S., Durrant-Whyte H.F., Csorba M. A solution to the simultaneous localization and map building (SLAM) problem. IEEE Transactions on Robotics and Automation, 2001, vol. 17, no. 3, pp. 229-241. DOI: 10.1109/70.938381 Available at: http://ieeexplore.ieee.org/document/938381

[23] Bailey T. Mobile robot localization and mapping in extensive outdoor environments. The University of Sydney, 2002.

[24] Gen Ke Ke, Chulin N.A. Algorithm of particle data association for SLAM based on improved ant algorithm. Nauka i obrazovanie: nauchnoe izdanie MGTU im. N.E. Baumana [Science and Education: Scientific Publication of BMSTU], 2015, pp. 340-355. DOI: 10.7463/1015.0818707 Available at: http://technomag.edu.ru/jour/article/view/165