Abstract
This paper reports on the deployment of self-organizing maps in unsupervised learning of the traversal cost for a hexapod walking robot. The problem is motivated by traversability assessment of terrains not yet visited by the robot, but for which shape and appearance features are available. The perception system of the robot is used to extract terrain features that are accompanied by traversal cost characterization captured from the real experience of the robot with the terrain, which is characterized by proprioceptive features. The learned model is employed to predict the traversal cost of new terrains based only on the shape and appearance features. Based on the experimental deployment of the robot in various terrains, a dataset of the traversal cost has been collected that is utilized in the presented evaluation of the traversal cost modeling using self-organizing map approach. In comparison with the Gaussian process, the self-organizing map provides competitive results and the found paths using the predicted traversal costs are close to the optimal path based on reference traversal cost of the particular terrain types. Besides, the self-organizing map can also be utilized for unsupervised identification of the terrain types, and it further supports incremental learning, which is more suitable for practical deployments of the robot in a priory unknown environments where reference traversal costs are not available.
This work was supported by the Czech Science Foundation under research project No.18-18858S. The authors acknowledge the support of the OP VVV MEYS funded project CZ.02.1.01/0.0/0.0/16_019/0000765 “Research Center for Informatics”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arthur, D., Vassilvitskii, S.: K-means++: the advantages of careful seeding. In: Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 1027–1035 (2007)
Bartoszyk, S., Kasprzak, P., Belter, D.: Terrain-aware motion planning for a walking robot. In: International Workshop on Robot Motion and Control (RoMoCo), pp. 29–34 (2017). https://doi.org/10.1109/RoMoCo.2017.8003889
Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 1(2), 224–227 (1979). https://doi.org/10.1109/TPAMI.1979.4766909
Faigl, J., Prágr, M.: Incremental traversability assessment learning using growing neural gas algorithm. In: Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization, pp. 166–176 (2020). https://doi.org/10.1007/978-3-030-19642-4_17
Faigl, J., Čížek, P.: Adaptive locomotion control of hexapod walking robot for traversing rough terrains with position feedback only. Robot. Auton. Syst. 116, 136–147 (2019). https://doi.org/10.1016/j.robot.2019.03.008
GPy: a Gaussian process framework in python (2012). http://github.com/SheffieldML/GPy. Accessed 28 Mar 2019
Hartigan, J.A., Wong, M.A.: A k-means clustering algorithm. JSTOR Appl. Stat. 28(1), 100–108 (1979). https://doi.org/10.2307/2346830
Kohonen, T.: Self-organizing Maps, 3rd edn. Springer, Heidelberg (2001). https://doi.org/10.1007/978-3-642-56927-2
Kragh, M., Jørgensen, R.N., Pedersen, H.: Object detection and terrain classification in agricultural fields using 3D lidar data. In: International Conference on Computer Vision Systems (ICVS), vol. 9163, pp. 188–197 (2015). https://doi.org/10.1007/978-3-319-20904-3_18
Prágr, M., Čížek, P., Faigl, J.: Cost of transport estimation for legged robot based on terrain features inference from aerial scan. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1745–1750 (2018). https://doi.org/10.1109/IROS.2018.8593374
Prágr, M., Čížek, P., Faigl, J.: Incremental learning of traversability cost for aerial reconnaissance support to ground units. In: Modelling and Simulation for Autonomous Systems (MESAS), pp. 412–421 (2019). https://doi.org/10.1007/978-3-030-14984-0_30
Prágr, M., Čížek, P., Faigl, J.: Online incremental learning of the terrain traversal cost in autonomous exploration. In: Robotics: Science and Systems (RSS) (2019). https://doi.org/10.15607/RSS.2019.XV.040
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Rougier, N., Boniface, Y.: Dynamic self-organising map. Neurocomputing 74(11), 1840–1847 (2011). https://doi.org/10.1016/j.neucom.2010.06.034
Ultsch, A., Siemon, H.P.: Kohonen’s self organizing feature maps for exploratory data analysis. In: International Neural Network Conference (INNC), pp. 305–308 (1990)
Vasudevan, S., Ramos, F., Nettleton, E., Durrant-Whyte, H., Blair, A.: Gaussian process modeling of large scale terrain. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 1047–1053 (2009). https://doi.org/10.1002/rob.20309
Vesanto, J., Alhoniemi, E.: Clustering of the self-organizing map. IEEE Trans. Neural Networks 11(3), 586–600 (2000). https://doi.org/10.1109/72.846731
Čížek, P., Faigl, J.: On localization and mapping with RGB-D sensor and hexapod walking robot in rough terrains. In: IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2273–2278 (2016). https://doi.org/10.1109/SMC.2016.7844577
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Faigl, J., Prágr, M. (2019). On Unsupervised Learning of Traversal Cost and Terrain Types Identification Using Self-organizing Maps. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation. ICANN 2019. Lecture Notes in Computer Science(), vol 11727. Springer, Cham. https://doi.org/10.1007/978-3-030-30487-4_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-30487-4_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30486-7
Online ISBN: 978-3-030-30487-4
eBook Packages: Computer ScienceComputer Science (R0)