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.
Similar content being viewed by others
References
Lavalle S (2006) Planning algorithms. Cambridge University Press, Cambridge
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):1251–1270
Marble JD, Bekris KE (2013) Asymptotically near-optimal planning with probabilistic roadmap spanners. IEEE Trans Robot 29(2):432–444
LaValle Steven M, Kuffner James J Jr (2001) Randomized kinodynamic planning. Int J Robot Res 20(5):378–400
Karaman S, Frazzoli E (2011) Sampling-based algorithms for optimal motion planning. Int J Robot Res 30(7):846–894
Zhang Haijun, Wang Shuang, Zhao Mingbo, Xiaofei Xu, Ye Yunming (2018) Locality reconstruction models for book representation. IEEE Trans Knowl Data Eng 30(10):1873–1886
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):5304–5318
Furao S, Ogura T, Hasegawa O (2007) An enhanced self-organizing incremental neural network for online unsupervised learning. Neural Netw 20(8):893–903
Zhang H, Xiao X, Hasegawa O (2014) A load-balancing self-organizing incremental neural network. IEEE Trans Neural Netw Learn Syst 25(6):1096–1105
Hsu D, Latombe JC, Kurniawati H (2006) On the probabilistic foundations of probabilistic roadmap planning. Int J Robot Res 25(7):627–643
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 3067–3074
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):1055–1071
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 4405–4410
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 3671–3678
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 900–905
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 4196–4201
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 2646–2652
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 63–69
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 3740–3747
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 629–636
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 7087–7094
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):2402–2415
Xing Y, Shi X, Shen F et al (2016) A self-organizing incremental neural network based on local distribution learning. Neural Netw 84:143–160
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):964–972
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 Park
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):451–462
Song S, Miller KD, Abbott LF (2000) Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nat Neurosci 3(9):919
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):1363–1374
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):883–921
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).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
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.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xia, C., Zhang, Y. & Chen, IM. Learning sampling distribution for motion planning with local reconstruction-based self-organizing incremental neural network. Neural Comput & Applic 31, 9185–9205 (2019). https://doi.org/10.1007/s00521-019-04370-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04370-y