Skip to main content
Springer Nature Link
Log in

Novelty Detection as an Intrinsic Motivation for Cumulative Learning Robots

  • Chapter
  • First Online:
Intrinsically Motivated Learning in Natural and Artificial Systems

  • 3640 Accesses

Abstract

Novelty detection is an inherent part of intrinsic motivations and constitutes an important research issue for the effective and long-term operation of intelligent robots designed to learn, act and make decisions based on their cumulative knowledge and experience. Our approach to novelty detection is from the perspective that the robot ignores perceptions that are already known, but is able to identify anything different. This is achieved by developing biologically inspired novelty detectors based on habituation. Habituation is a type of non-associative learning used to describe the behavioural phenomenon of decreased responsiveness of a cognitive organism to a recently and frequently presented stimulus, and it has been observed in a number of biological organisms. This chapter first considers the relationship between intrinsic motivations and novelty detection and outlines some works on intrinsic motivations. It then presents a critical review of the methods of novelty detection published by the authors. A brief summary of some key recent surveys in the field is then provided. Finally, key open challenges that need to be considered in the design of novelty detection filters for cumulative learning tasks are discussed.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Agyemang, M., Barker, K., Alhajj, R.: A comprehensive survey of numeric and symbolic outlier mining techniques. Intell. Data Anal. 10(6), 521–538 (2006)

    Google Scholar 

  2. Artac, M., Jogan, M., Leonardis, A.: Incremental pca for on-line visual learning and recognition. In: Proceedings of the of the 16th International Conference on Pattern Recognition (ICPR’02), vol. 3, pp. 781–784. IEEE Computer Society, Quebec City, QC, Canada. (2002)

    Google Scholar 

  3. Bakar, Z., Mohemad, R., Ahmad, A., Deris, M.: A comparative study for outlier detection techniques in data mining. In: 2006 IEEE Conference on Cybernetics and Intelligent Systems, pp. 1–6. IEEE (2006)

    Google Scholar 

  4. Baldassare, G.: What are intrinsic motivations? a biological perspective. In: Proceedings of the International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob-2011), pp. E1–E8 (2011)

    Google Scholar 

  5. Baranes, A., Oudeyer, P.-Y.: R-iac: Robust intrinsically motivated exploration and active learning. IEEE Trans. Auton. Mental Dev. 1, 155–169 (2009)

    Google Scholar 

  6. Barto, A., Singh, S., Chentanez, N.: Intrinsically motivated learning of hierarchical collections of skills. In: Proceedings of the of the 3rd International Conference on Developmental Learning (ICDL’04), pp. 112–119 (2004)

    Google Scholar 

  7. Berlyne, D.: Conflict, Arousal and Curiosity, 1st edn. McGraw-Hill, New York (1960)

    Google Scholar 

  8. Bogacz, R., Brown, M.W., Giraud-Carrier, C.: High capacity neural networks for familiarity discrimination. Proceedings of the International Conference on Artificial Neural Networks (ICANN”99), pp. 773–778 (1999)

    Google Scholar 

  9. Chandola, V., Banerjee, A., Kumar, V.: Outlier detection: A survey. Technical report, University of Minnesota (2007)

    Google Scholar 

  10. Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: A survey. ACM Comput. Surv. 41(3), 1–58 (2009)

    Google Scholar 

  11. Colombo, J., Mitchell, D.: Infant visual habituation. Neurobiol. Learn. Mem. 92, 225–234 (2009)

    Google Scholar 

  12. Crook, P.A., Marsland, S., Hayes, G., Nehmzow, U.: A tale of two filters—on-line novelty detection. In: Proceedings of the of the 2002 IEEE International Conference on Robotics and Automation, ICRA 2002, pp. 3894–3899. IEEE, Washington (2002)

    Google Scholar 

  13. De Charms, R.: Personal Causation: The Internal Affective Determinants of Behaviour. Academic, New York (1968)

    Google Scholar 

  14. Deci, E., Ryan, R.: Intrinsic Motivation and Self-Determination in Human Behavior. Plenum, New York (1985)

    Google Scholar 

  15. Festinger, L.: A Theory of Cognitive Dissonance. Stanford University Press, Stanford (1957)

    Google Scholar 

  16. Fritzke, B.: Growing cell structures a self-organizing network for unsupervised and supervised learning. Neural Netw. 7(9), 1441–1460 (1994)

    Google Scholar 

  17. Fritzke, B.: A growing neural gas network learns topologies. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems 7, pp. 625–632. MIT, Cambridge (1995)

    Google Scholar 

  18. Grubbs, F.E.: Procedures for detecting outlying observations in samples. Technometrics 11, 1–21 (1969)

    Google Scholar 

  19. Gurney, K., Prescott, T., Redgrave, P.: A computational model of action selection in the basal ganglia i: A new functional anatomy. Biol. Cybern. 84, 411–423 (2001a)

    MATH  Google Scholar 

  20. Gurney, K., Prescott, T., Redgrave, P.: A computational model of action selection in the basal ganglia ii: Analysis and simulation of behaviour. Biol. Cybern. 84, 401–410 (2001b)

    MATH  Google Scholar 

  21. Harlow, H.: Learning and satiation of response in intrinsically motivated complex puzzle performance by monkeys. J. Comp. Physiol. Psychol. 43, 289–294 (1950)

    Google Scholar 

  22. Hart, S., Grupen, R.: Learning generalizable control programs. IEEE Trans. Auton. Mental Dev. 3, 216–231 (2011)

    Google Scholar 

  23. Helali, R.G.M.: Data mining based network intrusion detection system: A survey. In: Sobh, T., Elleithy, K., Mahmood, A. (eds.) Novel Algorithms and Techniques in Telecommunications and Networking, pp. 501–505. Springer, Dordrecht (2010) (Chapter 86)

    Google Scholar 

  24. Hodge, V., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85–126 (2004)

    MATH  Google Scholar 

  25. Hunt, J.: Intrinsic motivation and its role in psychological development. Nebraska Symp. Motiv. 13, 189–282 (1965)

    Google Scholar 

  26. Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)

    Google Scholar 

  27. Kaplan, F., Oudeyer, P.-Y.: Intrinsically motivated machines. In: Lungarella, M., Iida, F., Bongard, J., Pfeifer, R., (Eds.) 50 Years of Artificial Intelligence, pp. 303–314. Springer, Dordrecht (2007)

    Google Scholar 

  28. Lee, R., Walker, R., Meeden, L., Marshall, J.: Category-based intrinsic motivation. In: Proceedings of the of the Ninth International Conference on Epigenetic Robotics, pp. 81–88 (2009)

    Google Scholar 

  29. Lindeberg, T.: Feature detection with automatic scale selection. Int. J. Comput. Vis. 30(2), 79–116 (1998)

    Google Scholar 

  30. Lisman, J., Grace, A.: The hippocampal-vta loop: Controlling the entry of information into long-term memory. Neuron 5, 703–713 (2005)

    Google Scholar 

  31. Markou, M., Singh, S.: Novelty detection: A review. Part 1: Statistical approaches. Signal Process. 83(12), 2481–2497 (2003a)

    Google Scholar 

  32. Markou, M., Singh, S.: Novelty detection: A review. Part 2: Neural network based approaches. Signal Process. 83(12), 2499–2521 (2003b)

    Google Scholar 

  33. Marshall, J., Blank, D., Meeden, L.: An emergent framework for self-motivation in developmental robotics. In: Proceedings of the of the Third Int. Conference on Development and Learning (ICDL2004), pp. 104–111 (2004)

    Google Scholar 

  34. Marsland, S.: Novelty detection in learning systems. Neural Comput. Surv. 3, 157–195 (2003)

    Google Scholar 

  35. Marsland, S., Nehmzow, U., Shapiro, J.: A real-time novelty detector for a mobile robot. In: Proceedings of the of the EUREL Conference on Advanced Robotics Systems, vol. 2, pp. 8–15 (2000)

    Google Scholar 

  36. Marsland, S., Nehmzow, U., Shapiro, J.: Vision-based environmental novelty detection on a mobile robot. In: Proceedings of the of the International Conference on Neural Information Processing (ICONIP’01), vol. 1, pp. 69–76 (2001)

    Google Scholar 

  37. Marsland, S., Nehmzow, U., Shapiro, J.: Environment-specific novelty detection. In: ICSAB: Proceedings of the Seventh International Conference on Simulation of Adaptive Behavior on From Animals to Animats, pp. 36–45. MIT, Cambridge (2002a)

    Google Scholar 

  38. Marsland, S., Nehmzow, U., Shapiro, J.: On-line novelty detection for autonomous mobile robots. Robot. Auton. Syst. 51(2–3), 191–206 (2005)

    Google Scholar 

  39. Marsland, S., Shapiro, J., Nehmzow, U.: A self-organising network that grows when required. Neural Netw. 15(8–9), 1041–1058 (2002b)

    Google Scholar 

  40. Martinetz, T.M., Schulten, K.J.: A neural-gas network learns topologies. In: Kohonen, T., Makisara, K., Simula, O., Kangas, J. (eds.) Artificial Neural Networks, pp. 397–402. Elsevier, Amsterdam (1991)

    Google Scholar 

  41. Merrick, K.: Self-motivated agents: Towards combined motivation models and integrated learning architectures. In: Mirolli, M., Baldassare, G. (eds.) Intrinsically Motivated Learning Systems, pp. 257–276. Springer, Berlin (2011)

    Google Scholar 

  42. Merrick, K., Maher, M.: Motivated learning from interesting events: Adaptive, multitask learning agents for complex environments. Adap. Behav. 17(1), 7–27 (2009)

    Google Scholar 

  43. Mirolli, M., Baldassare, G.: Functions and mechanisms of intrinsic motivations. In: Mirolli, M., Baldassare, G. (eds.) Intrinsically Motivated Learning Systems, pp. 42–66. Springer, Berlin (2011)

    Google Scholar 

  44. Nehmzow, U., Neto, H.V.: Novelty-based visual inspection using mobile robots. In: Proceedings of the Towards Autonomous Robotic Systems (TAROS’04) (2004)

    Google Scholar 

  45. Nehmzow, U., Neto, H.V.: Visual attention and novelty detection: Experiments with automatic scale selection. In: Proceedings of the Towards Autonomous Robotic Systems (TAROS’06), pp. 139–146 (2006)

    Google Scholar 

  46. Neto, H.V., Nehmzow, U.: Visual novelty detection for inspection tasks using mobile robots. In: Proceedings of the of the 8th Brazilian Symposium on Neural Networks (SBRN’04) (2004)

    Google Scholar 

  47. Neto, H.V., Nehmzow, U.: Automated exploration and inspection: Comparing two visual novelty detectors. Int. J. Adv. Robot. Syst. 2(4), 355–362 (2005a)

    Google Scholar 

  48. Neto, H.V., Nehmzow, U.: Incremental PCA: An alternative approach for novelty detection. In: Proceedings of the Towards Autonomous Robotic Systems (TAROS’05), pp. 227–233 (2005b)

    Google Scholar 

  49. Neto, H.V., Nehmzow, U.: Real-time automated visual inspection using mobile robots. J. Intell. Robot. Syst. 49(3), 293–307 (2007a)

    Google Scholar 

  50. Neto, H.V., Nehmzow, U.: Visual novelty detection with automatic scale selection. Robot. Auton. Syst. 55(9), 693–701 (2007b)

    Google Scholar 

  51. Otmakhova, N., Duzel, E., Deutch, A., Lisman, J.: The hippocampal-vta loop: The role of novelty and motivation in controlling the entry of information in long-term memory. In: Mirolli, M., Baldassare, G. (eds.) Intrinsically Motivated Learning Systems, pp. 277–293. Springer, Berlin (2011)

    Google Scholar 

  52. Oudeyer, P.-Y., Kaplan, F.: What is intrinsic motivation? A typology of computational approaches. Front. Neurobot. 1(6), 1–14 (1999)

    Google Scholar 

  53. Oudeyer, P.-Y., Kaplan, F., Hafner, V.: Intrinsic motivation systems for autonomous mental development. IEEE Trans. Evol. Comput. 11(2), 265–286 (1999)

    Google Scholar 

  54. Patcha, A., Park, J.: An overview of anomaly detection techniques: Existing solutions and latest technological trends. Comput. Netw. 51(12), 3448–3470 (2007)

    Google Scholar 

  55. Rankin, C.: Introduction to special issue of neurobiology of learning and memory on habituation. Neurobiol. Learn. Mem. 92, 125–126 (2009a)

    Google Scholar 

  56. Rankin, C.: Habituation revisited: An updated and revised description of the behavioral characteristics of habituation. Neurobiol. Learn. Mem. 92, 135–138 (2009b)

    Google Scholar 

  57. Redgrave, P., Gurney, K.: The short-latency dopamine signal: A role in discovering novel actions? Nat. Rev. Neurosci. 7, 967–975 (2006)

    Google Scholar 

  58. Ryan, R., Deci, E.: Intrinsic and extrinsic motivations: Classic definitions and new directions. Contemp. Educ. Psychol. 25, 54–67 (2000)

    Google Scholar 

  59. Saunders, R., Gero, J.: Curious agents and situated design evaluations. In: Gero, J., Brazier, F. (eds.) Agents in Design 2002, pp. 133–149. University of Sydney, Sydney (2002)

    Google Scholar 

  60. Saunders, R., Gero, J.S.: The importance of being emergent. In: Proceedings of the of the Conference on Artificial Intelligence in Design (2000)

    Google Scholar 

  61. Schembri, M., Mirolli, M., Baldassare, G.: Evolving internal reinforcers for an intrinsically motivated reinforcement-learning robot. In: Proceedings of the of the 6th International Conference on Development and Learning (ICDL’2007), pp. 282–287 (2007)

    Google Scholar 

  62. Schmidhuber, J.: Curious model-building control systems. In: Proceedings of the of the International Joint Conference on Neural Networks, vol. 2, pp. 1458–1463, Singapore (1991a)

    Google Scholar 

  63. Schmidhuber, J.: A possibility for implementing curiosity and boredom in model-building neural controllers. In: Proceedings of the of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, pp. 222–227 (1991b)

    Google Scholar 

  64. Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation. IEEE Trans. Auton. Mental Dev. 2, 230–247 (2010)

    Google Scholar 

  65. Schmidhuber, J.: Formal theory of creativity & intrinsic motivation (1990–2010): In: Mirolli, M., Baldassare, G. (eds.) Intrinsically Motivated Learning Systems, pp. 149–190. Springer, Berlin (2011)

    Google Scholar 

  66. Shahar, Y.: Dynamic temporal interpretation contexts for temporal abstraction. Ann. Math. Artif. Intell. 22(1–2), 159–192 (1996)

    MATH  Google Scholar 

  67. Shahar, Y., Cheng, C.: Model-based visualization of temporal abstractions. Comput. Intell. 16(2), 279–306 (2000)

    Google Scholar 

  68. Storck, J., Hochreiter, S., Schmidhuber, J.: Reinforcement-driven information acquisition in non-deterministic environments. In: Proceedings of the of the International Conference on Artificial Neural Networks (ICANN’95), vol. 2, pp. 159–164, Paris (1995)

    Google Scholar 

  69. Thompson, D.R.: Domain-guided novelty detection for autonomous exploration. In: IJCAI”09: Proceedings of the 21st International Jont Conference on Artifical Intelligence, pp. 1864–1869. Morgan Kaufmann, San Francisco (2009a)

    Google Scholar 

  70. Thompson, R.: Habituation: A history. Neurobiol. Learn. Mem. 92, 127–134 (2009b)

    Google Scholar 

  71. Thompson, R.F., Spencer, W.A.: Habituation: A model phenomenon for the study of neuronal substrates of behaviour. Psychol. Rev. 73(1), 16–43 (1966)

    Google Scholar 

  72. Wehmeier, S. (ed.): Oxford Advanced Learner’s Dictionary, 7th edn. Oxford University Press, Oxford (2005)

    Google Scholar 

  73. White, R.: Motivation reconsidered: The concept of competence. Psychol. Rev. 66, 297–333 (1959)

    Google Scholar 

  74. Zhang, Y., Meratnia, N., Havinga, P.J.M.: Outlier detection techniques for wireless sensor networks: A survey. IEEE Commun. Surv Tutorials, pp. 159–170 (2010)

    Google Scholar 

Download references

Acknowledgements

Professor Ulrich Nehmzow passed away in April 2010 during the IM-CLeVeR project implementation. While he did initiate the book chapter, he was unable due to illness to contribute to its completion. However, as this book chapter is mainly based on his pioneering ideas and works on novelty detection, we, his colleague researchers, dedicate it to his memory. This research has received funds from the European Commission 7th Framework Programme (FP7/2007-2013), “Challenge 2—Cognitive Systems, Interaction, Robotics”, Grant Agreement No. ICT-IP-231722 and Project “IM-CLeVeR—Intrinsically Motivated Cumulative Learning Versatile Robots”.

Author information

Authors and Affiliations

  1. Intelligent Systems Research Centre, University of Ulster, Derry/Londonderry, BT48 7JL, UK

    Ulrich Nehmzow, Yiannis Gatsoulis, Emmett Kerr, Joan Condell, Nazmul Siddique & T. Martin McGuinnity

Authors
  1. Ulrich Nehmzow
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yiannis Gatsoulis
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Emmett Kerr
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joan Condell
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nazmul Siddique
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. T. Martin McGuinnity
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ulrich Nehmzow .

Editor information

Editors and Affiliations

  1. Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche, Rome, Italy

    Gianluca Baldassarre  & Marco Mirolli  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Nehmzow, U., Gatsoulis, Y., Kerr, E., Condell, J., Siddique, N., McGuinnity, T.M. (2013). Novelty Detection as an Intrinsic Motivation for Cumulative Learning Robots. In: Baldassarre, G., Mirolli, M. (eds) Intrinsically Motivated Learning in Natural and Artificial Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32375-1_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-32375-1_8

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-32374-4

  • Online ISBN: 978-3-642-32375-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics