Advertisement

Navigate to Remember: A Declarative Memory Model for Incremental Semantic Mapping

  • Wei Hong ChinEmail author
  • Naoyuki Kubota
  • Zhaojie Ju
  • Honghai Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11743)

Abstract

Biologically inspired computational techniques play a crucial role in robotic cognition. Artificial learning agents and robots that interact in complex environments must constantly acquire and refine knowledge over long periods of time. In this paper, we propose a novel recurrent neural architecture that mimics humans’ declarative memory system for continuously generating a cognitive map during robot navigation. The proposed method termed as Declarative Memory Adaptive Recurrent Model (DM-ARM), and consists of three hierarchical memory courses: (i) Working Memory, (ii) Episodic Memory and (iii) Semantic Memory layer. Each memory layer comprises a self-organizing adaptive recurrent incremental network (SOARIN) with a different learning task respectively. The Working Memory layer quickly clusters sensory information while the Episodic Memory layer learns fine-grained spatiotemporal relationships of clusters (temporal encoding). Both the memory layer learning is in an unsupervised manner. The Semantic Memory layer utilizes task-relevant cues to adjust the level of architectural flexibility and generate a semantic map that contains more compact episodic representations. The effectiveness of the proposed recurrent neural architecture is evaluated through a series of experiments. We implemented and validated our proposed work on the tasks of robot navigation.

Keywords

Cognitive map Navigation Mobile robot Episodic memory 

References

  1. 1.
    Rebai, K., Azouaoui, O. Achour, N.: Bio-inspired visual memory for robot cognitive map building and scene recognition. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, 2012, pp. 2985–2990 (2012).  https://doi.org/10.1109/IROS.2012.6385493
  2. 2.
    Buzsáki, G., Moser, E.I.: Memory, navigation and theta rhythm in the hippocampal-entorhinal system. In: Nature Neuroscience 2013, vol. 16, pp. 130–138. Nature Publishing Group (2013).  https://doi.org/10.1038/nn.3304CrossRefGoogle Scholar
  3. 3.
    O’keefe, J., Nadel, L.: The Hippocampus As a Cognitive Map, vol. 3. Clarendon Press, Oxford (1978)Google Scholar
  4. 4.
    McNaughton, B.L., Battaglia, F.P., Jensen, O., Moser, E.I., Moser, M.-B.: Path integration and the neural basis of the cognitive map. Nat. Rev. Neurosci. 7(8), 663–678 (2006).  https://doi.org/10.1038/nrn1932CrossRefGoogle Scholar
  5. 5.
    Tulving, E.: Episodic and semantic memory1. In: Organization of Memory, pp. 381–402 (1972)Google Scholar
  6. 6.
    Tian, B., Shim, V.A., Yuan, M., Srinivasan, C., Tang, H., Li, H.: RGB-D based cognitive map building and navigation. In: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo, pp. 1562–1567 (2013).  https://doi.org/10.1109/IROS.2013.6696557
  7. 7.
    Yan, W., Weber, C., Wermter, S.: A neural approach for robot navigation based on cognitive map learning. In: 2012 International Joint Conference on Neural Networks (IJCNN), Brisbane, QLD, pp. 1–8 (2012)Google Scholar
  8. 8.
    Chin, W.H., Toda, Y., Kubota, N., Loo, C.K., Seera, M.: Episodic memory multimodal learning for robot sensorimotor map building and navigation. IEEE Trans. Cogn. Dev. Syst.  https://doi.org/10.1109/TCDS.2018.2875309
  9. 9.
    Kumaran, D., Hassabis, D., McClelland, J.L.: What learning systems do intelligent agents need? complementary learning systems theory updated. Trends Cogn. Sci. 20(7), 512–534 (2016)CrossRefGoogle Scholar
  10. 10.
    McClelland, J.L., McNaughton, B.L., O’Reilly, R.C.: Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol. Rev. 102(3), 419–457 (1995).  https://doi.org/10.1037/0033-295X.102.3.419CrossRefGoogle Scholar
  11. 11.
    Parisi, G.I., Tani, J., Weber, C., Wermter, S.: Lifelong learning of humans actions with deep neural network self-organization. Neural Netw. 96, 137–149 (2017).  https://doi.org/10.1016/j.neunet.2017.09.001CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Wei Hong Chin
    • 1
    Email author
  • Naoyuki Kubota
    • 1
  • Zhaojie Ju
    • 2
  • Honghai Liu
    • 2
  1. 1.Faculty of Systems DesignTokyo Metropolitan UniversityHinoJapan
  2. 2.University of PortsmouthPortsmouthUK

Personalised recommendations