Building of cognizing semantic map in large-scale semi-unknown environment

Abstract

The quick response code based artificial labels are applied to provide semantic concepts and relations of surroundings that permit the understanding of complexity and limitations of semantic recognition and scene only with robot’s vision. By imitating spatial cognizing mechanism of human, the robot constantly received the information of artificial labels at cognitive-guide points in a wide range of structured environment to achieve the perception of the environment and robot navigation. The immune network algorithm was used to form the environmental awareness mechanism with “distributed representation”. The color recognition and SIFT feature matching algorithm were fused to achieve the memory and cognition of scenario tag. Then the cognition-guide-action based cognizing semantic map was built. Along with the continuously abundant map, the robot did no longer need to rely on the artificial label, and it could plan path and navigate freely. Experimental results show that the artificial label designed in this work can improve the cognitive ability of the robot, navigate the robot in the case of semi-unknown environment, and build the cognizing semantic map favorably.

Keywords

artificial label / distributed information representation / cognizing semantic map / service robot

References

[1] DissanayakeG, NewmanP, ClarkS, DurrantF, CsprbaM. A solution to the simultaneous localization and map building (SLAM) problem [J]. IEEE Transactions on Robotics and Automation, 2001, 17(3): 229-241

[2] ChatterjeeA, RayO, ChatterjeeA, RakshitA. Development of a real-life EKF based SLAM system for mobile robots employing vision sensing [J]. Expert Systems with Applications, 2011, 38(7): 8266-8274

[3] WangK, WangW, ZhuangY, SunC-yu. Omnidirectional vision-based self-localization by using large-scale metric-topological 3D map [J]. Automation, 2008, 34(11): 1369-1378

[4] MorenoL, GarridoS, BlancoD, LuisaM. Differential evolution solution to the SLAM problem [J]. Robotics and Autonomous Systems, 2009, 57(4): 441-450

[5] DaveyS. Simultaneous localization and map building using the probabilistic multi-hypothesis tracker [J]. IEEE Transactions on Robotics, 2007, 23(2): 271-280

[6] SchleicherD, BergasaL, ManuelO, BareaR. Real-time hierarchical stereo visual SLAM in large-scale environments [J]. Robotics and Autonomous Systems, 2010, 58(8): 991-1002

[7] ZhengH, WangJ-c, ChenW-dong. Map-based self-localization and navigation system for mobile robots [J]. Robot, 2007, 29(4): 397-402

[8] BooijO, ZivkovicZ, KroseB. Efficient data association for view based SLAM using connected dominating sets [J]. Robotics and Autonomous Systems, 2009, 57(12): 1225-1234

[9] LiuJ, CaiZ-x, TuC-ming. A connectionist approach for cognitive map learning and Navigation based on spatio-temporal experiences [J]. Control Theory and Applications, 2003, 20(2): 161-167

[10] VasudevanS, SiegwartR. A bayesian conceptualization of space for mobile robots[C]. Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007, San Diego, Institute of Electrical and Electronics Engineers Inc: 715-720

[11] EadeE, DrummondT. Edge landmarks in monocular SLAM [J]. Image and Vision Computing, 2009, 27(5): 588-596

[12] VasudevanS, NguyenV, SiegwartR. Towards a cognitive probabilistic representation of space for mobile robots [C]. 2006 IEEE International Conference on Information Acquisition, 2006, Weihai, Inst of Elec and Elec Eng Computer Society: 7-12

[13] YiC-h, SuhI-h, LimG-hyun. CHOI Byung-uk. Bayesian robot localization using spatial object contexts [C]. The 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009, St. Louis, IEEE Computer Society: 3467-3474

[14] SiB-yuResearch on the problem concerning visual artificial landmark based navigation of autonomous mobile robot [D], 2003, Shenyang, Northeastern University

[15] LoevskyI, ShimshoniI. Reliable and efficient landmark-based localization for mobile robots [J]. Robotics and Autonomous Systems, 2010, 58(5): 520-528

[16] ScharsteinD, BriggsA. Real-time recognition of self-similar landmarks [J]. Image and Vision Computing, 2001, 19(11): 763-772

[17] ZhaoS-p, TianG-h, LiX-lei. Robot autonomous localization based on a single artificial landmark [J]. Journal of Shandong University, 2007, 37(4): 39-45

[18] TianG-H, JiangH-T, XueY-H, LiR-Kuan. The design, recognition, localization and application of a new artificial landmark [J]. Journal of Shandong University, 2011, 41(2): 107-113

[19] VarelaF, CoutinhoA, DupireE. Cognitive networks: Immune, neural and otherwise [J]. Theoretical Immunology, 1988359-375

[20] GaoX-l, TianC-y, LaoL-y, ChenY-h, ChenY-yu. Improved direct power injection model of 16-bit microcontroller for electromagnetic immunity prediction [J]. Journal of Central South University of Technology, 2011, 18(6): 2031-2035

[21] CoelhoG, ZubenV. A concentration-based artificial immune network for continuous optimization [C]. 2010 IEEE Congress on Evolutionary Computation, 2010, Barcelona, IEEE Computer Society: 1-8