Abstract
Mobile ground robots operating on uneven terrain must predict which areas of the environment they are able to pass in order to plan feasible paths. We cast traversability estimation as an image classification problem: we build a convolutional neural network that, given a square \(60 \times 60\) px image representing the heightmap of a small \(1.2 \times 1.2\) m patch of terrain, predicts whether the robot will be able to traverse such patch from bottom to top. The classifier is trained for a specific robot model, which may implement any locomotion type (wheeled, tracked, legged, snake-like), using simulation data on a variety of training terrains; once trained, the classifier can be quickly applied to patches extracted from unseen large heightmaps, in multiple orientations, thus building oriented traversability maps. We quantitatively validate the approach on real-elevation datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
data and code to reproduce our results are available online: https://github.com/romarcg/traversability_estimation.
References
Hadsell, R., Scoffier, M., Muller, U., LeCun, Y., Sermanet, P.: Mapping and planning under uncertainty in mobile robots with long-range perception. In. In Proceedings of the International Conference on Intelligent Robots and Systems (IROS), pp. 1–6 (2008)
Uğur, E., Şahin, E.: Traversability: a case study for learning and perceiving affordances in robots. Adapt. Behav. 18, 258–284 (2010)
Molino, V., Madhavan, R., Messina, E., Downs, A., Balakirsky, S., Jacoff, A.: Traversability metrics for rough terrain applied to repeatable test methods. In: 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1787–1794, October 2007
Brooks, C.A., Iagnemma, K.D.: Self-supervised classification for planetary rover terrain sensing. In: 2007 IEEE Aerospace Conference. pp. 1–9 March 2007
Bekhti, M.A., Kobayashi, Y., Matsumura, K.: Terrain traversability analysis using multi-sensor data correlation by a mobile robot. In: 2014 IEEE/SICE International Symposium on System Integration. pp. 615–620, December 2014
Silver, D., Bagnell, J.A., Stentz, A.: Learning from demonstration for autonomous navigation in complex unstructured terrain. Int. J. Rob. Res. 29(12), 1565–1592 (2010)
Chilian, A., Hirschmuller, H.: Stereo camera based navigation of mobile robots on rough terrain, pp. 4571–4576 (2009)
Cunningham, C., Wong, U., Peterson, K.M., Whittaker, W.L.R.: Predicting terrain traversability from thermal diffusivity. In: Mejias, L., Corke, P., Roberts, J. (eds.) Field and Service Robotics. STAR, vol. 105, pp. 61–74. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-07488-7_5
Herbert, M., Caillas, C., Krotkov, E., Kweon, I.S., Kanade, T.: Terrain mapping for a roving planetary explorer. In: Proceedings of 1989 International Conference on Robotics and Automation, vol. 2, pp. 997–1002, May 1989
Balta, H., Cubber, G.D., Doroftei, D., Baudoin, Y., Sahli, H.: Terrain traversability analysis for off-road robots using time-of-flight 3D sensing. In: Proceedings of the International Workshop on Robotics for Risky Environment - Extreme Robotics (2013)
Lacroix, S., Mallet, A., Bonnafous, D., Bauzil, G., Fleury, S., Herrb, M., Chatila, R.: Autonomous rover navigation on unknown terrains functions and integration. In: Rus, D., Singh, S. (eds.) ISER 2000, vol. 271, pp. 501–510. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-45118-8_50
Schwarz, M., Behnke, S.: Local navigation in rough terrain using omnidirectional height. In: ISR/Robotik 2014, 41st International Symposium on Robotics, pp. 1–6, June 2014
Hudjakov, R., Tamre, M.: Aerial imagery terrain classification for long-range autonomous navigation. In: 2009 International Symposium on Optomechatronic Technologies, pp. 88–91, September 2009
Längkvist, M., Kiselev, A., Alirezaie, M., Loutfi, A.: Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks. Remote Sens. 8(4), 329 (2016)
Jackel, L.D., Krotkov, E., Perschbacher, M., Pippine, J., Sullivan, C.: The DARPA LAGR program: goals, challenges, methodology, and phase i results. J. Field Robot. 23(11–12), 945–973 (2006)
Shneier, M., Chang, T., Hong, T., Shackleford, W., Bostelman, R., Albus, J.S.: Learning traversability models for autonomous mobile vehicles. Auton. Robots 24(1), 69–86 (2008)
Hadsell, R., Sermanet, P., Ben, J., Erkan, A., Han, J., Muller, U., LeCun, Y.: Online learning for offroad robots: spatial label propagation to learn long-range traversability. In: Proceedings of Robotics: Science and Systems, Atlanta, GA, USA, June 2007
Rohmer, E., Singh, S.P.N., Freese, M.: V-REP: a versatile and scalable robot simulation framework. In: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1321–1326 November 2013
SenseFly: elevation datasets, (2016). https://www.sensefly.com/drones/example-datasets.html
Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, New York (2006)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Breiman, L.: Random Forests. Mach. Learn. 45(1), 5–32 (2001)
Chollet, F., et al.: Keras, (2015). https://github.com/fchollet/keras
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-scale machine learning on heterogeneous systems, (2015). Software available from tensorflow.org
Acknowledgment
This research was supported by the Swiss National Science Foundation through the National Centre of Competence in Research Robotics.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Chavez-Garcia, R.O., Guzzi, J., Gambardella, L.M., Giusti, A. (2017). Image Classification for Ground Traversability Estimation in Robotics. In: Blanc-Talon, J., Penne, R., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2017. Lecture Notes in Computer Science(), vol 10617. Springer, Cham. https://doi.org/10.1007/978-3-319-70353-4_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-70353-4_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70352-7
Online ISBN: 978-3-319-70353-4
eBook Packages: Computer ScienceComputer Science (R0)