Skip to main content
SpringerLink
Log in

Gradual learning for behavior acquisition by evolving artificial neural network

  • Special Feature: Original Article
  • Published:
Artificial Life and Robotics Aims and scope Submit manuscript

Abstract

This paper describes a behavior acquisition of virtual robots by evolving artificial neural network (EANN) with a gradual learning. The gradual learning is a method in which initial states of simulation for evaluation is changing as optimization progresses. Motion of virtual robot is calculated by the physical engine PhysX, and it is controlled by an ANN. Parameters of an ANN are optimized by particle swarm optimization (PSO) so that a virtual robot follows the given target. Experimental results show that the gradual learning is better than a common learning method, realizing the standing behaviors which are not acquired by a common learning at all. It is also shown that random initialization of solutions in the middle of optimization leads to better behaviors.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447

    Article  Google Scholar 

  2. Allen B, Faloutsos P (2009) Complex networks of simple neurons for bipedal locomotion. In: Intelligent robots and systems, pp 4457–4462

  3. Sareni B, Krahenbuhl L (1998) Fitness sharing and niching methods revisited. IEEE Trans Evol Comput 2(3):97–106

    Article  Google Scholar 

  4. Gomez F (2009) Sustaining diversity using behavioral information distance. In: Proceedings of the 11th annual conference on genetic and evolutionary computation, pp 113–120

  5. Yoneda K, Suzuki I, Yamamoto M, Furukawa M (2011) Behavioral acquisition for elastic circular robot by using composite behavior (in Japanese). J Jpn Soc Precis Eng 77(5):476–482

    Article  Google Scholar 

  6. Ooe R, Suzuki I, Yamamoto M, Furukawa M (2013) Composite artificial neural network—selection-type neural network ensembles in dynamic system control by unsupervised learning—(in Japanese). J Jpn Soc Precis Eng 79(6):552–558

    Article  Google Scholar 

  7. Cully A, Mouret JB (2013), Behavioral repertoire learning in robotics. In: Proceedings of the 15th annual conference on genetic and evolutionary computation, pp 175–182

  8. Kennedy J, Eberhart R (1995) Particle swarm optimization. IEEE Int Conf Neural Netw 4:1942–1948

    Google Scholar 

  9. Eberhart R, Hu X (1999) Human tremor analysis using particle swarm optimization. In: Proceedings of the 1999 congress on evolutionary computation, vol 3, pp 1927–1930

  10. Eberhart R, Shi Y (2001) Particle swarm optimization: developments, applications and resources. In: Proceedings of the 2001 congress on evolutionary computation, vol 1, pp 81–86

Download references

Author information

Authors and Affiliations

  1. Department of Information and Computer Science, Hokkaido University of Science, Sapporo, Japan

    Ryosuke Ooe & Takashi Kawakami

Authors
  1. Ryosuke Ooe
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Takashi Kawakami
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ryosuke Ooe.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ooe, R., Kawakami, T. Gradual learning for behavior acquisition by evolving artificial neural network. Artif Life Robotics 21, 399–404 (2016). https://doi.org/10.1007/s10015-016-0316-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10015-016-0316-3

Keywords

Search

Navigation