Advertisement

Neural Computing and Applications

, Volume 31, Issue 12, pp 9185–9205 | Cite as

Learning sampling distribution for motion planning with local reconstruction-based self-organizing incremental neural network

  • Chongkun Xia
  • Yunzhou ZhangEmail author
  • I-Ming Chen
Original Article
  • 70 Downloads

Abstract

For sampling-based motion planners (e.g., PRM and RRT*), collision detection dominates the asymptotic running time and reduces the execution efficiency. The reason of this problem is that obtaining a high-dimensional implicit representation (i.e., configuration space distribution) of the state space is not easy, especially in the complicated environment with various obstacles. Though sampling-based planning algorithms and their variants perform well, most of these algorithms have strict restrictions and narrow applications. A possible ideal solution is to design a non-uniform sampling strategy to ensure the sampling process only occurs in collision-free region \(\chi _{free}\) but not in collision region \(\chi _{col}\). Therefore, we propose a new methodology to learn the sampling distribution for non-uniform sampling. The sampling distribution is learned through a local reconstruction-based self-organizing incremental neural network and allows to generate samples from the learned latent distribution. Besides, our method can adapt well to environmental non-vigorous changes and adjust the learned distribution quickly. The method can effectively exploit the underlying structure of the planning problem and be spread for general use in combination with any sampling-based planning algorithms. Specifically, we use two typical planning problems to show that the proposed method can effectively learn and update the sampling distribution from the high-dimensional configuration space in the changed environment, resulting in a dominant performance in terms of the cost, running time and success rate.

Keywords

Motion planning Sampling distribution Local reconstruction Self-organizing incremental neural network Non-uniform sampling 

Notes

Acknowledgements

We would like to thank other members from Robotics Research Centre (RRC) of Nanyang Technological University (Singapore) for helping us to improve this work. We benefited a lot from the academic discussion and exchanges in RRC. Additionally, the authors would like to thank experienced anonymous reviewers for their constructive and valuable suggestions for improving the overall quality of this paper.

Funding

This work was supported by Fundamental Research Funds for the Central Universities, China (N172608005, N182608004), the Distinguished Creative Talent Program of Shenyang (RC170490) and National Natural Science Foundation of China (No. 61471110, 61733003), China Scholarship Council (CSC) scholarships (No. 201806080120).

Compliance with ethical standards

Conflict of interest

No conflict of interest exits in the submission of this manuscript, and the manuscript is approved by all authors for publication. We would like to declare that the work described was original research that has not been published previously, and not under consideration for publication elsewhere, in whole or in part. All authors listed have approved the manuscript that is enclosed.

References

  1. 1.
    Lavalle S (2006) Planning algorithms. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  2. 2.
    Schulman J, Duan Y, Ho J et al (2014) Motion planning with sequential convex optimization and convex collision checking. Int J Robot Res 33(9):1251–1270CrossRefGoogle Scholar
  3. 3.
    Marble JD, Bekris KE (2013) Asymptotically near-optimal planning with probabilistic roadmap spanners. IEEE Trans Robot 29(2):432–444CrossRefGoogle Scholar
  4. 4.
    LaValle Steven M, Kuffner James J Jr (2001) Randomized kinodynamic planning. Int J Robot Res 20(5):378–400CrossRefGoogle Scholar
  5. 5.
    Karaman S, Frazzoli E (2011) Sampling-based algorithms for optimal motion planning. Int J Robot Res 30(7):846–894CrossRefGoogle Scholar
  6. 6.
    Zhang Haijun, Wang Shuang, Zhao Mingbo, Xiaofei Xu, Ye Yunming (2018) Locality reconstruction models for book representation. IEEE Trans Knowl Data Eng 30(10):1873–1886CrossRefGoogle Scholar
  7. 7.
    Zhang H, Wang S, Xu X, Chow TWS, Wu QMJ (2018) Tree2Vector: learning a vectorial representation for tree-structured data. IEEE Trans Neural Netw Learn Syst 29(11):5304–5318MathSciNetCrossRefGoogle Scholar
  8. 8.
    Furao S, Ogura T, Hasegawa O (2007) An enhanced self-organizing incremental neural network for online unsupervised learning. Neural Netw 20(8):893–903CrossRefGoogle Scholar
  9. 9.
    Zhang H, Xiao X, Hasegawa O (2014) A load-balancing self-organizing incremental neural network. IEEE Trans Neural Netw Learn Syst 25(6):1096–1105CrossRefGoogle Scholar
  10. 10.
    Hsu D, Latombe JC, Kurniawati H (2006) On the probabilistic foundations of probabilistic roadmap planning. Int J Robot Res 25(7):627–643CrossRefGoogle Scholar
  11. 11.
    Gammell JD, Srinivasa SS, Barfoot TD (2015) Batch informed trees (BIT*): sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs. In: 2015 IEEE international conference on robotics and automation (ICRA). IEEE, pp 3067–3074Google Scholar
  12. 12.
    Van den Berg JP, Overmars MH (2005) Using workspace information as a guide to non-uniform sampling in probabilistic roadmap planners. Int J Robot Res 24(12):1055–1071CrossRefGoogle Scholar
  13. 13.
    Yang Y, Brock O (2004) Adapting the sampling distribution in PRM planners based on an approximated medial axis. In: 2004 IEEE international conference on robotics and automation. Proceedings ICRA’04, vol 5. IEEE, pp 4405–4410Google Scholar
  14. 14.
    Berenson D, Abbeel P, Goldberg K (2012) A robot path planning framework that learns from experience. In: IEEE international conference on robotics and automation. IEEE, pp 3671–3678Google Scholar
  15. 15.
    Coleman D, Şucan IA, Moll M, et al (2015) Experience-based planning with sparse roadmap spanners. In: IEEE international conference on robotics and automation. IEEE, pp 900–905Google Scholar
  16. 16.
    Li Y, Bekris KE (2011) Learning approximate cost-to-go metrics to improve sampling-based motion planning. In: IEEE international conference on robotics and automation. IEEE, pp 4196–4201Google Scholar
  17. 17.
    Arslan O, Tsiotras P (2015) Machine learning guided exploration for sampling-based motion planning algorithms. In: 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 2646–2652Google Scholar
  18. 18.
    Huh J, Lee DD (2016) Learning high-dimensional mixture models for fast collision detection in rapidly-exploring random trees. In: 2016 IEEE international conference on robotics and automation (ICRA). IEEE, pp 63–69Google Scholar
  19. 19.
    Huh J, Lee B, Lee DD (2017) Adaptive motion planning with high-dimensional mixture models. In: 2017 IEEE international conference on robotics and automation (ICRA). IEEE, pp 3740–3747Google Scholar
  20. 20.
    Chen N, Karl M, van der Smagt P (2016) Dynamic movement primitives in latent space of time-dependent variational autoencoders. In: 2016 IEEE-RAS 16th international conference on humanoid robots (humanoids). IEEE, pp 629–636Google Scholar
  21. 21.
    Ichter B, Harrison J, Pavone M (2018) Learning sampling distributions for robot motion planning. In: 2018 IEEE international conference on robotics and automation (ICRA). IEEE, pp 7087–7094Google Scholar
  22. 22.
    Gebru ID, Alameda-Pineda X, Forbes F et al (2016) EM algorithms for weighted-data clustering with application to audio-visual scene analysis. IEEE Trans Pattern Anal Mach Intell 38(12):2402–2415CrossRefGoogle Scholar
  23. 23.
    Xing Y, Shi X, Shen F et al (2016) A self-organizing incremental neural network based on local distribution learning. Neural Netw 84:143–160CrossRefGoogle Scholar
  24. 24.
    Sudo A, Sato A, Hasegawa O (2009) Associative memory for online learning in noisy environments using self-organizing incremental neural network. IEEE Trans Neural Netw 20(6):964–972CrossRefGoogle Scholar
  25. 25.
    Kawewong A, Pimpup R, Hasegawa O (2013) Incremental learning framework for indoor scene recognition. In: Twenty-seventh AAAI conference on artificial intelligence. AAAI Press, Menlo ParkGoogle Scholar
  26. 26.
    He X, Kojima R, Hasegawa O (2007) Developmental word grounding through a growing neural network with a humanoid robot. IEEE Trans Syst Man Cybern Part B (Cybern) 37(2):451–462CrossRefGoogle Scholar
  27. 27.
    Song S, Miller KD, Abbott LF (2000) Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nat Neurosci 3(9):919CrossRefGoogle Scholar
  28. 28.
    Mei J, Liu M, Wang YF et al (2016) Learning a Mahalanobis distance-based dynamic time warping measure for multivariate time series classification. IEEE Trans Cybern 46(6):1363–1374CrossRefGoogle Scholar
  29. 29.
    Janson L, Schmerling E, Clark A et al (2015) Fast marching tree: a fast marching sampling-based method for optimal motion planning in many dimensions. Int J Robot Res 34(7):883–921CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Information Science and EngineeringNortheastern UniversityShenyangChina
  2. 2.School of Mechanical and Aerospace EngineeringNanyang Technological University (NTU)SingaporeSingapore

Personalised recommendations