Abstract
This paper presents a new neural network for online topological map building inspired by beta oscillations and hippocampal place cell learning. The memory layer represents the hippocampus, the input layer represents the entorhinal, and the \(\rho\) is the orientation system. In this model, multiple-scale entorhinal grid cell activations form the input layer feature patterns, which are categorized by hippocampal place cells (nodes) and act as spatial categories in the memory layer. Top-down attentive matching and mismatch-mediated reset (beta oscillations), which are triggered by the orientation system, overcome the stability-plasticity dilemma and prevent the catastrophic forgetting of place cell maps. In our proposed method, nodes in the topological map represent place cells (robot location), while edges connect nodes and store robot action (i.e., orientation, direction). Our method is based upon a multi-channel Adaptive Resonance Associative Memory (ARAM) network architecture to obtain multiple sensory sources for topological map building. It comprises two layers: input and memory. The input layer collects sensory data and incrementally clusters the obtained information into a set of topological nodes. In the memory layer, the clustered information is used as a topological map where nodes are associated with actions. The advantages of the proposed method are: (1) it does not require high-level cognitive processes and prior knowledge to make it work in a natural environment; and (2) it can process multiple sensory sources simultaneously in continuous space, which is crucial for real-world robot navigation. Thus, we combine our Topological Gaussian ARAM method (TGARAM) with incremental principle component analysis to constitute a basis for topological map building. Lastly, the proposed method was validated using several standardized benchmark datasets.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ball D, Heath S, Wiles J, Wyeth G, Corke P, Milford M (2013) OpenRatSLAM: an open source brain-based slam system. Autonom Robots 3:149–176. doi:10.1007/s10514-012-9317-9
Barrera A, Weitzenfeld A (2008) Biologically-inspired robot spatial cognition based on rat neurophysiological studies. Autonom Robots 25(1–2):147–169. doi:10.1007/s10514-007-9074-3
Benjamin K, Yung-Tai B (1991) A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations. J Robot Autonom Syst 8:47–63
Berke J, Hetrick V, Breck J, Greene R (2008) Transient 23–30 hz oscillations in mouse hippocampus during exploration of novel environments. Hippocampus 18(5):519–29. doi:10.1002/hipo.20435
Carpenter GA (2003) Default artmap. In: Proceedings of the international joint conference on neural networks (IJCNN03), pp 1396–1401
Carpenter GA, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comput Vis Graph Image Process. doi:10.1016/S0734-189X(87)80014-2
Ceriani S, Fontana G, Giusti A (2009) Rawseeds ground truth collection systems for indoor self-localization and mapping. In: Autonomous robots. Kluwer, Hingham, MA, USA, vol 27, pp 353–371. doi:10.1007/s10514-009-9156-5
Chandrasekaran S, Manjunath BS, Wang YF, Winkeler J, Zhang H (1996) An eigenspace update algorithm for image analysis. Technical report, Santa Barbara, CA, USA
Chang H, Lee CSG, Hu Y, Lu YH (2007) Multi-robot slam with topological/metric maps. In: IEEE/RSJ international conference on intelligent robots and systems, 2007, IROS 2007, pp 1467–1472. doi:10.1109/IROS.2007.4399142
Chang-Hyuk C, Jae-Bok S, Woojin C (2002) Topological map building based on thinning and its application to localization. In: IEEE/RSJ international conference on intelligent robots and systems, 2002, vol 1, pp 552–557. doi:10.1109/IRDS.2002.1041448
Chatila R, Laumond J (1985) Position referencing and consistent world modeling for mobile robots. In: Proceedings 1985 IEEE international conference on robotics and automation, vol 2, pp 138–145. doi:10.1109/ROBOT.1985.1087373
David Filliat JA (2003) Map-based navigation in mobile robots: I. A review of localization strategies. Cogn Syst Res 4(4):243–282. doi:10.1016/S1389-0417(03)00008-1
Fontana G, Matteucci M, Sorrenti D (2014) Rawseeds: building a benchmarking toolkit for autonomous robotics. In: Amigoni F, Schiaffonati V (eds) Methods and experimental techniques in computer engineering. Springer International Publishing, SpringerBriefs in Applied Sciences and Technology, Berlin, pp 55–68
Ghahramani Z, Hinton GE (2000) Variational learning for switching state-space models. Neural Comput 12(4):831–864. doi:10.1162/089976600300015619
Giovannangeli C, Gaussier P (2008) Autonomous vision-based navigation: goal-oriented action planning by transient states prediction, cognitive map building, and sensory-motor learning. In: IEEE/RSJ international conference on intelligent robots and systems, 2008, IROS 2008, pp 676–683. doi:10.1109/IROS.2008.4650872
Grossberg S (2009) Beta oscillations and hippocampal place cell learning during exploration of novel environments. Hippocampus 19(9):881–885. doi:10.1002/hipo.20602
Grossberg S, Versace M (2008) Spikes, synchrony, and attentive learning by laminar thalamocortical circuits. Brain Res. doi:10.1016/j.brainres.2008.04.024
Hall P, Marshall D, Martin R (1998a) Merging and splitting eigenspace models. IEEE Trans Pattern Anal Mach Intell 22:2000
Hall PM, Marshall D, Martin RR (1998b) Incremental eigenanalysis for classification. In: British machine vision conference, pp 286–295
Jean-Arcady M, Agns G, Benot G, Mehdi K, Patrick P, Alain B (2005) The Psikharpax project: towards building an artificial rat. Robot Autonom Syst 50(4):211–223. doi:10.1016/j.robot.2004.09.018
Jockusch J, Ritter H (1999) An instantaneous topological mapping model for correlated stimuli. In: International joint conference on neural networks, 1999, IJCNN’99, vol 1, pp 529–534. doi:10.1109/IJCNN.1999.831553
Kwon TB, Song JB (2008) Thinning-based topological exploration using position possibility of topological nodes. Adv Robot 22(2–3):339–359. doi:10.1163/156855308X292619
Leivas G, Botelho S, Drews P, Figueiredo M, Haffele C (2010) Sensor fusion based on multi-self-organizing maps for slam. In: 2010 IEEE conference on multisensor fusion and integration for intelligent systems (MFI). doi:10.1109/MFI.2010.5604482
Levey A, Lindenbaum M (2000) Sequential Karhunen–Loeve basis extraction and its application to images. IEEE Trans Image Process 9(8):1371–1374. doi:10.1109/83.855432
McGlinchey S, Peña M, Fyfe C (2006) Quantization errors in the harmonic topographic mapping. In: Proceedings of the 5th WSEAS international conference on signal processing, world scientific and engineering academy and society (WSEAS), Stevens Point, Wisconsin, USA, SIP’06, pp 105–110. http://dl.acm.org/citation.cfm?id=1983937.1983961
Milford M, Wyeth G, Prasser D (2004) RatSLAM: a hippocampal model for simultaneous localization and mapping. In: Proceedings of the international robotics and automation (ICRA’04), vol 1, pp 403–408. doi:10.1109/ROBOT.2004.1307183
O’Keefe J, Dostrovsky J (1971) The hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving rat. Brain Res 34(1):171–175
Shi C, Wang Y, Yang J (2010) Online topological map building and qualitative localization in large-scale environment. Robot Auton Syst 58(5):488–496. doi:10.1016/j.robot.2010.01.009
Tan AH (1995) Adaptive resonance associative map. Neural Netw 8(3):437–446. doi:10.1016/0893-6080(94)00092-Z
Tarutoko Y, Kobayashi K, Watanabe K (2006) Topological map generation based on Delaunay triangulation for mobile robot. In: International joint conference on SICE-ICASE, 2006, pp 492–496. doi:10.1109/SICE.2006.315477
Thrun S (1998) Learning metric-topological maps for indoor mobile robot navigation. Artif Intell 99(1):21–71. doi:10.1016/S0004-3702(97)00078-7
Tomatis N, Nourbakhsh IR, Siegwart R (2003) Hybrid simultaneous localization and map building: a natural integration of topological and metric. Robot Autonom Syst 44(1):3–14. doi:10.1016/S0921-8890(03)00006-X
Van Zwynsvoorde D, Simeon T, Alami R (2000) Incremental topological modeling using local voronoi-like graphs. In: Proceedings 2000 IEEE/RSJ international conference on intelligent robots and systems, 2000 (IROS 2000), vol 2, pp 897–902. doi:10.1109/IROS.2000.893133
Williamson JR (1996) Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps. Neural Netw 9:881–897. doi:10.1016/0893-6080(95)00115-8
Winkeler J, Manjunath B, Chandrasekaran S (1999) Subset selection for active object recognition. In: IEEE computer society conference on computer vision and pattern recognition, 1999, vol 2, pp –516. doi:10.1109/CVPR.1999.784729
Acknowledgments
The authors would like to acknowledge a scholarship provided by the University of Malaya (Fellowship Scheme). This research is supported in part by HIR grant UM.C/625/1/HIR/MOHE/FCSIT/10 from the University of Malaya.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chin, W.H., Loo, C.K. Topological Gaussian ARAM for biologically inspired topological map building. Neural Comput & Applic 29, 1055–1072 (2018). https://doi.org/10.1007/s00521-016-2505-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2505-3