Hostname: page-component-cd9895bd7-8ctnn Total loading time: 0 Render date: 2024-12-18T16:08:08.454Z Has data issue: false hasContentIssue false
  • English
  • Français

A study of visual and tactile terrain classification and classifier fusion for planetary exploration rovers

Published online by Cambridge University Press:  01 November 2008

Ibrahim Halatci ,
Christopher A. Brooks  and
Karl Iagnemma
Ibrahim Halatci*
Affiliation:
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139.
Christopher A. Brooks
Affiliation:
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139.
Karl Iagnemma
Affiliation:
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139.
*
*Corresponding author: E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Summary

Knowledge of the physical properties of terrain surrounding a planetary exploration rover can be used to allow a rover system to fully exploit its mobility capabilities. Terrain classification methods provide semantic descriptions of the physical nature of a given terrain region. These descriptions can be associated with nominal numerical physical parameters, and/or nominal traversability estimates, to improve mobility prediction accuracy. Here we study the performance of multisensor classification methods in the context of Mars surface exploration. The performance of two classification algorithms for color, texture, and range features are presented based on maximum likelihood estimation and support vector machines. In addition, a classification method based on vibration features derived from rover wheel–terrain interaction is briefly described. Two techniques for merging the results of these “low-level” classifiers are presented that rely on Bayesian fusion and meta-classifier fusion. The performance of these algorithms is studied using images from NASA's Mars Exploration Rover mission and through experiments on a four-wheeled test-bed rover operating in Mars-analog terrain. Also a novel approach to terrain sensing based on fused tactile and visual features is presented. It is shown that accurate terrain classification can be achieved via classifier fusion from visual and tactile features.

Keywords

Mobile robotsrobot vision systemsrobot sensing systemsextraterrestrial exploration
Type
Article
Information
Robotica , Volume 26 , Issue 6 , November 2008 , pp. 767 - 779
Copyright
Copyright © Cambridge University Press 2008

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

1.Angelova, A., Matthies, L., Helmick, D., Sibley, G. and Perona, P., “Learning to Predict Slip for Ground Robots,” In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Orlando, FL (May 2006a).Google Scholar
2.Angelova, A., Matthies, L., Helmick, D. and Perona, P., “Slip Prediction Using Visual Information,” In: Proceedings of the Robotics: Science and Systems (RSS), Philadelphia, PA (Aug. 2006b).Google Scholar
3.Ansar, A., Castano, A. and Matthies, L., “Enhanced Real-Time Stereo Using Bilateral Filtering,” In: 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, Thesaloniki, Greece (Sep. 2004) pp. 455–462.Google Scholar
4.Avedisyan, A., Wettergreen, D., Fong, T. and Baur, C., “Far-Field Terrain Evaluation Using Geometric and Toposemantic Vision,” In: 8th ESA Workshop on Advanced Space Technologies for Robotics and Automation, Noordwijk, Netherlands (2004).Google Scholar
5.Bellutta, P., Manduchi, R., Matthies, L., Owens, K. and Rankin, K., “Terrain Perception for Demo III,” In: Proceedings of the Intelligent Vehicles Symposium, Dearbon, Michigan (Oct. 2000) pp. 326–331.Google Scholar
6.Bilmes, J., “A Gentle Tutorial on the EM Algorithm and Its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models,” Technical Report, University of Berkeley (1997).Google Scholar
7.Bishop, C. M., Neural Networks for Pattern Recognition (Oxford University Press, New York, 1995).Google Scholar
8.Bouman, C. and Liu, B., “Multiple Resolution Segmentation of Textured Images.” IEEE Trans. Pattern Anal. Machine Intell. 13 (2), pp. 99–113 (1991).CrossRefGoogle Scholar
9.Brooks, C. and Iagnemma, K., “Vibration-Based Terrain Classification for Planetary Rovers,” IEEE Trans Robotics 21 (6), 1185–1191 (2005).Google Scholar
10.Castano, R., Judd, M., Estlin, T., Anderson, R. C., Gaines, D., Castano, A., Bornstein, B., Stough, T. and Wagstaff, K., “Current Results From a Rover Science Data Analysis System,” In: Proceedings of 2005 IEEE Aerospace Conference, Big Sky (2005) pp. 356–365.CrossRefGoogle Scholar
11.Chih-Chung, C. and Chih-Jen, L., “LIBSVM: A Library for Support Vector Machines” (2001). Software retrieved January 2006. Available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.Google Scholar
12.Coltry, D., “Mars Exploration Rover Multispectral Color Imagery” (2006). Retrieved May 21, 2006, from http://www.lyle.org/~markoff/.Google Scholar
13.Dima, C. S., Vandapel, N. and Hebert, M., “Sensor and Classifier Fusion for Outdoor Obstacle Detection: An Application of Data Fusion to Autonomous Road Detection,” Appl. Imagery Pattern Recognition Workshop, Vol. 1, 255–262 (2003).Google Scholar
14.Dima, C. S., Vandapel, N. and Hebert, M., “Classifier Fusion for Outdoor Obstacle Detection,” In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 1, (ICRA, 2004), New Orleans, Lousiana, pp. 665–671.Google Scholar
15.Espinal, F., Huntsberger, T. L., Jawerth, B. and Kubota, T., “Wavelet-Based Fractal Signature Analysis for Automatic Target Recognition,” Opt. Eng. (Special Section on Advances in Pattern Recognition) 37 (1), 166–174 (1998).Google Scholar
16.Goldberg, S., Maimone, M. and Matthies, L., “Stereo Vision and Rover Navigation Software for Planetary Exploration,” In: IEEE Aerospace Conference, Big Sky, 5 (2002) pp. 2025–2036.Google Scholar
17.Gor, V., Castaño, R., Manduchi, R., Anderson, R. and Mjolsness, E., “Autonomous Rock Detection for Mars Terrain,” Space 2001 (AIAA, Albuquerque, New Mexico, 2001), pp. 1–14.Google Scholar
18.Iagnemma, K. and Dubowsky, S., “Terrain Estimation for High Speed Rough Terrain Autonomous Vehicle Navigation,” In: Proceedings of the SPIE Conference on Unmanned Ground Vehicle Technology IV, Orlando, Florida (Mar. 2002).Google Scholar
19.Kelly, A., Stentz, A., Amidi, O., Bode, M., Bradley, D., Calderon, A. D., Happold, M., Herman, H., Mandelbaum, R., Pilarski, T., Rander, P., Thayer, S., Vallidis, N. and Warner, R. “Toward Reliable Off Road Autonomous Vehicles Operating in Challenging Environments,” Int. J. Robotics Res. 25 (5/6) (June 2006), pp. 449–483.CrossRefGoogle Scholar
20.Mandelbaum, R., McDowell, L., Bogoni, L., Reich, B. and Hansen, M., “Real-Time Stereo Processing, Obstacle Detection and Terrain Estimation Form Vehicle-Mounted Stereo Cameras,” In: Proceedings of the 4th IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 288 (1998).Google Scholar
21.Manduchi, R., “Bayesian Fusion of Color and Texture Segmentations,” In: Proceedings of International Conference on Computer Vision (ICCV), (ICCV, 1999) Kerkyra 2 (1999) pp. 956–962.Google Scholar
22.Manduchi, R., “Learning Outdoor Color Classification From Just One Training Image,” In: Proceedings of European Conference on Computer Vision (ECCV), (ECCV, 2004), Prague, Czech Republic, 28 (11) (2004) pp. 1713–1723.Google Scholar
23.Manduchi, R., Castano, A., Thalukder, A. and Matthies, L., “Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation,” Autonomous Robots 18, 81–102 (May 2005).Google Scholar
24.Mars Analyst's Notebook (2006). Retrieved May 24, 2006, from http://anserver1.eprsl.wustl.edu/.Google Scholar
25.McGuire, P. C., Martinez, E. D., Ormö, J. O., Elvira, J. G., Rodriguez Manfredi, J. A., Martinez, E. Sebastian, Ritter, H., Haschke, R., Oesker, M., Ontrup, J., “The Cyborg Astrobiologist: Scouting Red Beds for Uncommon Features With Geological Significance,” Int. J. Astrobiol. 4, 101–113 (2005).Google Scholar
26.Ojeda, L., Borenstein, J., Witus, G. and Karlsen, R., (2006). “Terrain Characterization and Classification With A Mobile Robot,” Journal of Field Robotics 23 (2), pp. 103–122 (2006).Google Scholar
27.Rajpoot, K. M. and Rajpoot, N. M., “Wavelets and Support Vector Machines for Texture Classification,” In: Proceedings of 8th IEEE International Multitopic Conference, Lahore, Pakistan (2004) pp. 328–333.Google Scholar
28.Rasmussen, C., “Laser Range-, Color-, and Texture-based Classifiers for Segmenting Marginal Roads,” In: Proceedings of Conference on Computer Vision & Pattern Recognition Technical Sketches, Kauai, HI (Dec. 2001).Google Scholar
29.Reed, T. and Hans du Buf, J.. “A review of recent texture segmentations nad feature extraction techniques,” CVGIP: Image Understanding Vol. 57(3), May 1993, pp. 359–372.Google Scholar
30.Sadhukhan, D., Moore, C. and Collins, E., “Terrain Estimation Using Internal Sensors,” In: Proceedings of International Conference on Robotics and Applications (IASTED) Honolulu, Hawaii 84 (11) (2004) pp. 1684–1704.Google Scholar
31.Shi, X. and Manduchi, R., “A Study on Bayes Feature Fusion for Image Classification,” In: Proceedings of the IEEE Workshop on Statistical Algorithms for Computer Vision, Madison, Wisconsin (2003).Google Scholar
32.Squyres, S. W. et al. , “Athena Mars Rover Science Investigation,” J. Geophys. Res., 108 (E12), 8062 (2003).Google Scholar
33.Thompson, D. R., Niekum, S., Smith, T. and Wettergreen, D., “Automatic Detection and Classification of Features of Geologic Interest,” In: Proceedings of IEEE Aerospace Conference, Big Sky, Montana (2005) pp. 366–377.Google Scholar
34.Urquhart, M. and Gulick, V., “Lander Detection and Identification of Hydrothermal Deposits,” abstract presented at First Landing Site Workshop for MER, Mountain View, California (2003).Google Scholar
35.Vandapel, N., Huber, D. F., Kapuria, A. and Hebert, M., “Natural Terrain Classification Using 3-D Ladar Data,” In: Proceedings of the International Conference on Robotics and Automation (ICRA), New Orleans, Lousiana 5 (2004) pp. 5117–5122.Google Scholar
36.Vapnik, V. N., The Nature of Statistical Learning Theory (Springer, New York, 1995).CrossRefGoogle Scholar
37.Videre Design (2006). Retrieved on May 25, 2006 at http://www.videredesign.com/index.htm.Google Scholar
38.Wolpert, D. H. (1992), Stacked Generalization, Neural Networks, Vol. 5, pp. 241–259, Pergamon Press.Google Scholar