Hostname: page-component-cd9895bd7-8ctnn Total loading time: 0 Render date: 2024-12-24T02:04:46.206Z Has data issue: false hasContentIssue false
  • English
  • Français

Terrain-Dependent Slip Risk Prediction for Planetary Exploration Rovers

Published online by Cambridge University Press:  23 February 2021

Masafumi Endo Open the ORCID record for Masafumi Endo [Opens in a new window] ,
Shogo Endo ,
Kenji Nagaoka  and
Kazuya Yoshida
Masafumi Endo*
Affiliation:
Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan E-mails: [email protected], [email protected]
Shogo Endo
Affiliation:
Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan E-mails: [email protected], [email protected]
Kenji Nagaoka
Affiliation:
Department of Mechanical and Control Engineering, Graduate School of Engineering, Kyushu Institute of Technology, Kitakyushu, Japan E-mail: [email protected]
Kazuya Yoshida
Affiliation:
Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan E-mails: [email protected], [email protected]
*
*Corresponding author. E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Summary

Wheel slip prediction on rough terrain is crucial for secure, long-term operations of planetary exploration rovers. Although rough, unstructured terrain hampers mobility, prediction by modeling wheel–terrain interactions remains difficult owing to unclear terrain conditions and complexities of terramechanics models. This study proposes a vision-based approach with machine learning for predicting wheel slip risk by estimating the slope from 3D information and classifying terrain types from image information. It considers the slope estimation accuracy for risk prediction under sharp increases in wheel slip due to inclined ground. Experimental results obtained with a rover testbed on several terrain types validate this method.

Keywords

Planetary exploration roversMachine learningWheel slip predictionExteroceptive sensingSlope estimation
Type
Article
Information
Robotica , Volume 39 , Issue 10 , October 2021 , pp. 1883 - 1896
Copyright
© The Author(s), 2021. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Goldberg, S. B., Maimone, M. W. and Matthies, L., “Stereo Vision and Rover Navigation Software for Planetary Exploration,” Proceedings of the IEEE Aerospace Conference, Big Sky, MT, USA (2002) pp. 2025–2036.Google Scholar
Arvidson, R. E., Iagnemma, K. D., Maimone, M., Fraeman, A. A., Zhou, F., Heverly, M. C., Bellutta, P., Rubin, D., Stein, N. T., Grotzinger, J. P. and Vasavada, A. R., “Mars Science Laboratory Curiosity rover megaripple crossings up to sol 710 in gale crater,” J. Field Robot. 34(3), 495–518 (2017).CrossRefGoogle Scholar
Bekker, M. G., Introduction to Terrain-Vehicle Systems (University of Michigan Press, Ann Arbor, USA, 1969).Google Scholar
Ishigami, G., Nagatani, K. and Yoshida, K., “Slope traversal controls for planetary rover on sandy terrain,” J. Field Robot. 26(3), 264–286 (2009).CrossRefGoogle Scholar
Wong, J. Y., Theory of Ground Vehicles (John Wiley & Sons, USA, 1978).Google Scholar
Halatci, I., C. A. Brooks and K. Iagnemma “A study of visual and tactile terrain classification and classifier fusion for planetary exploration rovers,” Robotica 26(6), 767–779 (2008).CrossRefGoogle Scholar
Brooks, C. A. and Iagnemma, K., “Self-supervised terrain classification for planetary surface exploration rovers,” J. Field Robot. 29(3), 445–468 (2012).CrossRefGoogle Scholar
Otsu, K., Ono, M., Fuchs, T. J., I. Baldwin and T. Kubota “Autonomous terrain classification with co- and self-training approach,” IEEE Robot. Autom. Lett. 1(2), 814–819 (2016).CrossRefGoogle Scholar
Berczi, L.-P., Posner, I. and Barfoot, T. D., “Learning to Assess Terrain from Human Demonstration Using an Introspective Gaussian-Process Classifier,” Proceedings of the IEEE International Conference on Robotics and Automation, Seattle, WA, USA (2015) pp. 3178–3185.Google Scholar
Schilling, F., Chen, X., Folkesson, J. and Jensfelt, P., “Geometric and Visual Terrain Classfication for Autonomous Mobile Navigation,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Vancouver, BC, Canada (2017) pp. 2678–2684.Google Scholar
Higa, S., Iwashita, Y., Otsu, K., Ono, M., Lamarre, O., Didier, A. and Hoffman, M., “Vision-based estimation of driving energy for planetary rovers using deep learning and terramechanics,” IEEE Robot. Autom. Lett. 4(4), 3876–3883 (2019).CrossRefGoogle Scholar
Angelova, A., Matthies, L., D. Heilmick and P. Perona “Learning and prediction of slip from visual information,” J. Field Robot. 24(3), 205–231 (2007).CrossRefGoogle Scholar
Cunningham, C., Ono, M., Nesnas, I., Yen, J. and Whittaker, W. L., “Locally-Adaptive Slip Prediction for Planetary Rovers Using Gaussian Processes,” Proceedings of the IEEE International Conference on Robotics and Automation, Singapore, Singapore (2017) pp. 5487–5494.Google Scholar
Skonieczny, K., Shukla, D. K., Faragalli, M., Cole, M. and Iagnemma, K. D., “Data-driven mobility risk prediction for planetary rovers,” J. Field Robot. 36(2), 475–491 (2019).CrossRefGoogle Scholar
Yang, M. Y. and Forstner, W., “Plane Detection in Point Cloud Data,” Proceedings of the 2nd International Conference on Machine Control Guidance, Bonn, Germany (2010) pp. 95–104.Google Scholar
Tanaka, S., Yamada, K., Ito, T. and Ohkawa, T., “Vehicle detection based on perspective transformation using rear-view camera,” Int. J. Vehicular Tech. 2011 (2011).CrossRefGoogle Scholar
Kim, D., Oh, S. M. and Rehg, J. M., “Traversability Classification for UGV Navigation: A Comparison of Patch and Superpixel Representations,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, CA, USA (2007) pp. 3166–3173.Google Scholar
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P. and Susstrunk, S., “SLIC superpixel compared to state-of-the-art superpixel methods,” IEEE Trans. Anal, Pattern. Mach. Intell. 34(11), 2274–2281 (2012).Google ScholarPubMed
Friedman, J. H. “Stochastic gradient boosting,” Comput. Stat. Data Anal. 38(4), 367–378 (2002).CrossRefGoogle Scholar
Loh, W. Y., “Classification and regression trees,” Wiley Interdiscip. Rev. Data Mining Knowl. Discovery 1(1), 14–23 (2011).CrossRefGoogle Scholar
Gonzalez, R., Fiacchini, M. and Iagnemma, K., “Slippage prediction for off-road mobile robots via machine learning regression and proprioceptive sensing,” Robot. Auto. Syst. 105, 85–93 (2018).CrossRefGoogle Scholar
Gonzalez, R., Apostolopoulos, D. and Iagnemma, K., “Slippage and immobilization detection for planetary exploration rovers via machine learning and proprioceptive sensing,” J. Field Robot. 35(2), 231–247 (2018).CrossRefGoogle Scholar
Freitag, D. R., Green, A. J. and Melzer, K. J., “Performance evaluation of wheels for lunar vehicles,” US Army Waterways Experiment Station Technical Report M-70-2 (Vicksburg, MS, 1970).CrossRefGoogle Scholar
Bishop, C. M., Pattern Recognition and Machine Learning (Springer, USA, 2006).Google Scholar
Yamauchi, G., Noyori, T., Nagatani, K. and Yoshida, K., “Improvement of Slope Traversability for a Multi-DOF Tracked Vehicle with Active Reconfiguration of its Joint Forms,” Proceedings of the IEEE International Symposium on Safety, Security, and Rescue Robotics, Hokkaido, Japan (2014) pp. 1–6.Google Scholar