Hostname: page-component-cd9895bd7-fscjk Total loading time: 0 Render date: 2024-12-27T06:34:32.251Z Has data issue: false hasContentIssue false
  • English
  • Français

The Cyborg Astrobiologist: testing a novelty detection algorithm on two mobile exploration systems at Rivas Vaciamadrid in Spain and at the Mars Desert Research Station in Utah

Published online by Cambridge University Press:  30 November 2009

P.C. McGuire ,
C. Gross ,
L. Wendt ,
A. Bonnici ,
V. Souza-Egipsy ,
J. Ormö ,
E. Díaz-Martínez ,
B.H. Foing ,
R. Bose  and
S. Walter
...Show all authors
P.C. McGuire
Affiliation:
Freie Univ.Berlin, Germany Centro de Astrobiología (CSIC/INTA), Torrejón de Ardoz, Spain McDonnell Center for the Space Sciences, Washington Univ., St. Louis, USA
C. Gross
Affiliation:
Freie Univ.Berlin, Germany
L. Wendt
Affiliation:
Freie Univ.Berlin, Germany
A. Bonnici
Affiliation:
Department of Systems and Control Engineering, University of Malta, Malta
V. Souza-Egipsy
Affiliation:
Centro de Astrobiología (CSIC/INTA), Torrejón de Ardoz, Spain
J. Ormö
Affiliation:
Centro de Astrobiología (CSIC/INTA), Torrejón de Ardoz, Spain
E. Díaz-Martínez
Affiliation:
Centro de Astrobiología (CSIC/INTA), Torrejón de Ardoz, Spain
B.H. Foing
Affiliation:
ESTEC, Noordwijk, The Netherlands
R. Bose
Affiliation:
McDonnell Center for the Space Sciences, Washington Univ., St. Louis, USA
S. Walter
Affiliation:
Freie Univ.Berlin, Germany
M. Oesker
Affiliation:
Technische Fakultät, Univ. Bielefeld, Germany
J. Ontrup
Affiliation:
Technische Fakultät, Univ. Bielefeld, Germany
R. Haschke
Affiliation:
Technische Fakultät, Univ. Bielefeld, Germany
H. Ritter
Affiliation:
Technische Fakultät, Univ. Bielefeld, Germany
Get access Rights & Permissions [Opens in a new window]

Abstract

In previous work, a platform was developed for testing computer-vision algorithms for robotic planetary exploration. This platform consisted of a digital video camera connected to a wearable computer for real-time processing of images at geological and astrobiological field sites. The real-time processing included image segmentation and the generation of interest points based upon uncommonness in the segmentation maps. Also in previous work, this platform for testing computer-vision algorithms has been ported to a more ergonomic alternative platform, consisting of a phone camera connected via the Global System for Mobile Communications (GSM) network to a remote-server computer. The wearable-computer platform has been tested at geological and astrobiological field sites in Spain (Rivas Vaciamadrid and Riba de Santiuste), and the phone camera has been tested at a geological field site in Malta. In this work, we (i) apply a Hopfield neural-network algorithm for novelty detection based upon colour, (ii) integrate a field-capable digital microscope on the wearable computer platform, (iii) test this novelty detection with the digital microscope at Rivas Vaciamadrid, (iv) develop a Bluetooth communication mode for the phone-camera platform, in order to allow access to a mobile processing computer at the field sites, and (v) test the novelty detection on the Bluetooth-enabled phone camera connected to a netbook computer at the Mars Desert Research Station in Utah. This systems engineering and field testing have together allowed us to develop a real-time computer-vision system that is capable, for example, of identifying lichens as novel within a series of images acquired in semi-arid desert environments. We acquired sequences of images of geologic outcrops in Utah and Spain consisting of various rock types and colours to test this algorithm. The algorithm robustly recognized previously observed units by their colour, while requiring only a single image or a few images to learn colours as familiar, demonstrating its fast learning capability.

Keywords

novelty detectionHopfield neural networksceintific autonomyBluetooth communicationsphone cameralichensdigital microscopewearable computergraphical programming languageimage segmentationuncommon mappingMars Desert Research StationMorrison Formationgypsumsingle-instance learning
Type
Research Article
Information
International Journal of Astrobiology , Volume 9 , Issue 1 , January 2010 , pp. 11 - 27
Copyright
Copyright © Cambridge University Press 2009

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

Aha, D.W., Kibler, D. & Albert, M.K. (1991). Mach. Learn. 6(1), 37–66.Google Scholar
Alexander, D.A. et al. (2006). J. Geophys. Res. 111, E02S02.Google Scholar
Barnes, D. et al. (2006). Int. J. Astrobiol. 5, 221–241.CrossRefGoogle Scholar
Bartolo, A. et al. (2007). Int. J. Astrobiol., 6, 255–261, http://arxiv.org/abs/0707.0808v1.CrossRefGoogle Scholar
Bilbey, S.A. (1998). Modern Geology. 22, 87–120.Google Scholar
Bogacz, R., Brown, M.W. & Giraud-Carrier, C. (1999). High capacity neural networks for familiarity discrimination. In Proc. Artificial Neural Networks. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470), vol. 2, pp. 773–778.CrossRefGoogle Scholar
Bogacz, R., Brown, M.W. & Giraud-Carrier, C. (2001). J. Comput. Neurosci. 10(1), 5–23.CrossRefGoogle Scholar
Borg, J.C., Camilleri, K.P. & Farrugia, P.J. (2003). Innovative Early Stage Design Product Prototyping (InPro), http://www.eng.um.edu.mt/~inpro.Google Scholar
Calvo, J.P., Alonso, A.M. & Garcia del Cura, A.M. (1989). Paleogeography, Paleoclimate Paleoecology, 70, 199–214.CrossRefGoogle Scholar
Castano, R. et al. (2007). Onboard Autonomous Rover Science. In Proc. IEEE Aerospace Conf., Big Sky, MT.CrossRefGoogle Scholar
Castilla Cañamero, G. (2001). Informe sobre las prácticas profesionales realizadas en el Centro de Educación Ambiental: El Campillo. Internal report to the Consejería de Medio Ambiente de la Comunidad de Madrird.Google Scholar
Chen, Y. & Wang, J.Z. (2004). J. Mach. Learn. Res. 5, 913–939.Google Scholar
Dubowsky, S., Iagnemma, K., Liberatore, S., Lambeth, D., Plante, J.S. & Boston, P.A. (2005). Concept mission: microbots for large-scale planetary surface and subsurface exploration. In Proc.s of the 2005 Space Technology and Applications International Forum (STAIF), vol. 746, pp. 1449–1458.CrossRefGoogle Scholar
Farrugia, P.J., Borg, J.C., Camilleri, K.P., Spiteri, C. & Bartolo, A. (2004). A cameraphone-based approach for the generation of 3{D} models from paper sketches. In Proc. Eurographics 2004 Workshop on Sketch-based Interfaces and Modeling, pp. 32–42.Google Scholar
Fink, W., Dohm, J.M., Tarbell, M.A., Hare, T.M. & Baker, V.R. (2005). Planet. Space Sci. 53, 1419–1426.CrossRefGoogle Scholar
Foing, B.H. et al. (2009a). Validation of instruments and robotics from EuroGeoMars & Moon Campaign. In Proc. European Planetary Science Congress (EPSC), Potsdam, Germany, extended abstract 643.Google Scholar
Foing, B.H. et al. (2009b). ExoGeoLab lander/rover instruments and EuroGeoMars MDRS campaign. In Proc. Lunar and Planetary Science Conf. (LPSC), The Woodlands, Texas, extended abstract 2567.Google Scholar
Foing, B.H. et al. (2009c). Daily reports from MDRS (crew 76 and 77), http://desert.marssociety.org/mdrs/fs08/.Google Scholar
Freixenet, J., Munoz, X., Marti, J. & Lladó, X. (2004). Color texture segmentation by region-boundary cooperation. In Proc. Computer Vision-ECCV 2004, Eighth European Conf. on Computer Vision, Prague, Czech Republic, (Part II, Lecture Notes in Computer Science), ed. Pajdla, T. & Matas, J., vol. 3022, pp. 250–261. Springer, also available in the CVonline archive: http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/FREIXENET1/eccv04.html.Google Scholar
Gentner, D. & Namy, L.L. (2006). Curr. Dir. Psychol. Sci. 15(6), 297–301.CrossRefGoogle Scholar
Griffiths, A.D., Coates, A.J., Jaumann, R., Michaelis, H., Paar, G., Barnes, D., Josset, J.-L. & the PanCam Team (2006). Int. J. Astrobiol. 5, 269–275.CrossRefGoogle Scholar
Gross, C. et al. (2009). Testing the Cyborg Astrobiologist at the Mars Desert Research Station (MDRS), Utah. In Proc. European Planetary Science Congress (EPSC), Potsdam, Germany, extended abstract 548.Google Scholar
Gulick, V.C., Hart, S.D., Shi, X. & Siegel, V.L. (2004). Developing an automated science analysis system for Mars surface exploration for MSL and beyond. In Proc. Lunar and Planetary Institute Conf. XXXV, extended abstract #2121.Google Scholar
Gulick, V.C., Morris, R.L., Ruzon, M.A. & Roush, T.L. (2001). J. Geophys. Res. 106, 7745–7764.CrossRefGoogle Scholar
Halatci, I, Brooks, C.A. & Iagnemma, K. (2007). Terrain classification and classifier fusion for planetary exploration rovers. In Proc. IEEE Aerospace Conference, Big Sky, MT, pp. 1–11.CrossRefGoogle Scholar
Halatci, I., Brooks, C.A. & Iagnemma, K. (2008). Robotica 26, 767–779.CrossRefGoogle Scholar
Haralick, R.M., Shanmugam, K. & Dinstein, I. (1973). IEEE Trans. Systems Man and Cybernetics. 3, 610–621.CrossRefGoogle Scholar
IGME (Instituto Geológico y Minero de España). (1975). Mapa geológico de España E 1:50,000, Arganda (segunda serie, primera edicion), Hoja numero 583, Memoria explicativa, pp. 3–25.Google Scholar
Itti, L, Koch, C. & Niebur, E. (1998). IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259.CrossRefGoogle Scholar
King, D.T. Jr. & Petruny, L.W. (2008). Impact spherule-bearing, Cretaceous-Tertiary boundary sand body, Shell Creek stratigraphic section, Alabama, USA. In The Sedimentary Record of Impacts, ed. Evans, K.R., Horton, J.W. Jr., King, D.T. Jr. & Morrow, J.R. Special Paper 437, pp. 179–187. Geological Society of America, Boulder, CO.Google Scholar
Kjemperud, A.V, Schomacker, E.R. & Cross, T.A. (2008). AAPG Bull. 92, 1055–1076.CrossRefGoogle Scholar
Maron, O. & Lozano-Perez, T. (1998). A framework for multiple-instance learning. In Proc. of the 1998 Conf. on Advances in Neural Information Processing Systems (NIPS), vol. 10, pp. 570–576. MIT Press.Google Scholar
Matthies, L. et al. (2007). Int. J. Comput. Vis. 75(1), 67–92.CrossRefGoogle Scholar
McGreevy, M.W. (1992). Presence 1(4), 375–403.CrossRefGoogle Scholar
McGreevy, M.W. (1994). An ethnographic object-oriented analysis of explorer presence in a volcanic terrain environment, NASA Technical Memorandum #108823, Ames Research Center, Moffett field, California.Google Scholar
McGuire, P.C., Fritsch, J., Steil, J.J., Roethling, F., Fink, G.A., Wachsmuth, S., Sagerer, G. & Ritter, H. (2002). Multi-Modal human-machine communication for instructing robot grasping tasks. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Lausanne, Switzerland, pp. 1082–1089. IEEE publications.CrossRefGoogle Scholar
McGuire, P.C., Ormö, J.O., Díaz-Martínez, E., Rodríguez-Manfredi, J.A., Gómez-Elvira, J., Ritter, H., Oesker, M. & Ontrup, J. (2004a). Int. J. Astrobiol. 3, 189–207, http://arxiv.org/abs/cs.CV/0410071.CrossRefGoogle Scholar
McGuire, P.C. et al. (2004b). Cyborg systems as platforms for computer-vision algorithm-development for astrobiology. In Proc. of the III European Workshop on Exo-Astrobiology; Mars: The Search for Life, Centro de Astrobiologia, Madrid, ESA SP- 545, pp. 141–144. http://arxiv.org/abs/cs.CV/0401004.Google Scholar
McGuire, P.C. et al. (2005). Int. J. Astrobiol. 4, 101–113, http://arxiv.org/abs/cs.CV/0505058.CrossRefGoogle Scholar
Ontrup, J., Ehnert, N., Bergmann, M. & Nattkemper, T.W. (2009). Biigle – Web 2.0 enabled labeling and exploring of images from the Arctic deep-sea observatory HAUSGARTEN. In Proc. OCEANS′09 IEEE Bremen. Balancing technology with future needs, abstract.Google Scholar
Purser, A., Bergmann, M., Lundälv, T., Ontrup, J. & Nattkemper, T.W. (2009, in press). Use of machine-learning algorithms for the automated detection of cold-water coral habitats—a pilot study. Mar. Ecol. Progr. doi:10.3354/meps08154.CrossRefGoogle Scholar
Rae, R., Fislage, M. & Ritter, H. (1999). KI-Künstliche Intelligenz, Themenheft Aktive Sehsysteme 01, 18–24, March issue, Hrsg. Bärbel Mertsching.Google Scholar
Read, S.J. (1983). J. Pers. Soc. Psychol. 45(2), 323–334.CrossRefGoogle Scholar
Ritter, H., Steil, J.J., Noelker, C., Roethling, F. & McGuire, P. (2003). Rev. Neurosci. 14, 121–143.CrossRefGoogle Scholar
Ritter, H. et al. (1992, 2002). The Graphical Simulation Tookit, Neo/NST, for more details about the {NEO} project, see: http://ni.www.techfak.uni-bielefeld.de/neo/.Google Scholar
Sebe, N., Tian, Q., Loupias, E., Lew, M. & Huang, T.S. (2003). Image Vis. Comput. Special Issue on Machine Vision, 21, 1087–1095.CrossRefGoogle Scholar
Squyres, S.W. et al. (2004a). Science 305, 794–799.CrossRefGoogle ScholarPubMed
Squyres, S.W. et al. (2004b). Science 306, 1698–1703.CrossRefGoogle ScholarPubMed
Turner, C.E. & Fishman, N.S. (1991). Geol. Soc. Am. Bull. 103, 538–558.2.3.CO;2>CrossRefGoogle Scholar
Volpe, R. (2003). Rover functional autonomy development for the Mars Mobile Science Laboratory. In Proc. IEEE Aerospace Conf., Big Sky, MT, vol. 2, pp. 2_643–2_652.CrossRefGoogle Scholar
Wendt, L. et al. (2009). The Cyborg Astrobiologist: teaching computers to find uncommon or novel areas of geological scenery in real-time. In Proc. European Space Agency International Conf. on Comparative Planetology: Venus – Earth – Mars, ESTEC, Noordwijk, The Netherlands, extended abstract.Google Scholar
Yim, M., Shirmohammadi, B. & Benelli, D. (2007). Amphibious modular robotic astrobiology. In Proc. Unmanned Systems Technology IX, Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, vol. 6561, p. 65611S.CrossRefGoogle Scholar
Zhang, Q. & Goldman, S.A. (2002). EM-DD: An improved multiple-instance learning technique. In Proc. of the 2002 Conf. on Advances in Neural Information Processing Systems (NIPS), vol. 14, pp. 1073–1080. MIT Press.Google Scholar