Map Building Method Based on Hierarchical Temporal Memory
ZHANG Xin-Zheng1, MAI Xiao-Chun2, ZHANG Jian-Fen1
1.Electrical and Information College, Jinan University, Zhuhai 519070 2.Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 999077
Abstract A map building method based on hierarchical temporal memory (HTM)is proposed. The mapping problem is treated as scene recognition. The map is composed of a series of scenes being the outputs of HTM network. Firstly, the position invariant robust feature (PIRF) is extracted from the obtained images and then the PIRFs are applied to build the visual vocabulary. Secondly, according to the visual vocabulary PIRF descriptors of an image are projected to the vector of visual word occurrences. Multiple visual word occurrences vectors are formed as a sequence of visual word occurrences. This sequence is inputted to HTM to implement the environment map learning and building and closed loop scenes recognition. The performance of the proposed mapping method is evaluated by two experiments. The results show that the proposed strategy based on HTM is effective for map building and closed loop detection.
[1] Milford M, Schulz R, Prasser D, et al. Learning Spatial Concepts from RatSLAM Representations. Robotics and Autonomous Systems, 2007, 55(5): 403-410 [2] Bacca B, Salvi J, Cufí X. Appearance-Based SLAM for Mobile Robots // Proc of the 12th International Conference of the Catalan Association for Artificial Intelligence. Cardona, Spain, 2009: 55-64 [3] Cummins M, Newman P. FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance. The International Journal of Robotics Research, 2008, 27(6): 647-665 [4] Cummins M, Newman P. Appearance-Only SLAM at Large Scale with FAB-MAP 2.0. The International Journal of Robotics Research, 2011, 30(9): 1100-1123 [5] Beeson P, Modayil J, Kuipers B. Factoring the Mapping Problem: Mobile Robot Map-Building in the Hybrid Spatial Semantic Hierarchy. The International Journal of Robotics Research, 2010, 29(4): 428-459 [6] Wu P L, Kong L F, Gao S N. Holography Map for Home Robot: An Object-Oriented Approach. Intelligent Service Robotics, 2012, 5(3): 147-157 [7] Barrera A, Weitzenfeld A. Biologically-Inspired Robot Spatial Cognition Based on Rat Neurophysiological Studies. Autonomous Robots, 2008, 25(1/2): 147-169 [8] Milford M J, Wyeth G F. Mapping a Suburb with a Single Camera Using a Biologically Inspired SLAM System.Trans on Robotics, 2008, 24(5): 1038-1053 [9] Wyeth G, Milford M. Spatial Cognition for Robots.Robotics & Automation Magazine, 2009, 16(3): 24-32 [10] Rebai K, Azouaoui O, Achour N. Fuzzy ART-Based Place Recognition for Visual Loop Closure Detection. Biological Cybernetics, 2013, 107(2): 247-259 [11] Li Y M, Li S, Ge Y J. A Biologically Inspired Solution to Simultaneous Localization and Consistent Mapping in Dynamic Environments. Neurocomputing, 2013, 104: 170-179 [12] Hawkins J, Blakeslee S. On Intelligence. New York, USA: Henry Holt and Company, 2004 [13] Zhang X Z, Zhang J F, Rad A B, et al. A Novel Mapping Strategy Based on Neocortex Model: Pre-liminary Results by Hierarchical Temporal Memory // Proc of theInternational Conference on Robotics and Biomimetics. Guangzhou, China, 2012: 476-481 [14] Hawkins J, Ahmad S, Dubinsky D. Hierarchical Temporal Memory Including HTM Cortical Learning Algorithms [EB/OL]. [2013-12-20]. http:// numenta.com/assets/pdf/whitepapers/hierarchical-temporal-memory-cortical-learning-algorithm-0.2.1-en.pdf [15] Kawewong A, Tongprasit N, Tangruamsub S, et al. Online and Incremental Appearance-Based SLAM in Highly Dynamic Environments. The International Journal of Robotics Research, 2011, 30(1): 33-55 [16] Kawewong A, Tongprasit N, Hasegawa O. PIRF-Nav 2.0: Fast and Online Incremental Appearance-Based Loop-Closure Detection in an Indoor Environment. Robotics and Autonomous Systems, 2011, 59(10): 727-739 [17] George D. How the Brain Might Work: A Hierarchical and Temporal Model for Learning and Recognition. Ph.D Dissertation. Stanford, USA: Stanford University, 2008 [18] Bundzel M, Hashimoto S. Object Identification in Dynamic Images Based on the Memory-Prediction Theory of Brain Function. Journal of Intelligent Learning Systems and Applications, 2010, 2(4): 212-220 [19] Yang J, Jiang Y G, Hauptmann A G, et al. Evaluating Bag-of-Visual-Words Representations in Scene Classification // Proc of the International Workshop on Multimedia Information Retrieval. Augsburg, Germany, 2007: 197-206 [20] Grauman K, Leibe B. Visual Object Recognition. San Rafael, USA: Morgan & Claypool Publisher, 2011
2015, Vol. 28 
