Abstract
In order for vision-based navigation algorithms to extend to long-term autonomy applications, they must have the ability to reliably associate images across time. This ability is challenged in unstructured and outdoor environments, where appearance is highly variable. This is especially true in temperate winter climates, where snowfall and low sun elevation rapidly change the appearance of the scene. While there have been proposed techniques to perform localization across extreme appearance changes, they are not suitable for many navigation algorithms such as autonomous path following, which requires constant, accurate, metric localization during the robot traverse. Furthermore, recent methods that mitigate the effects of lighting change for vision algorithms do not perform well in the contrast-limited environments associated with winter. In this paper, we highlight the successes and failures of two state-of-the-art path-following algorithms in this challenging environment. From harsh lighting conditions to deep snow, we show through a series of field trials that there remain serious issues with navigation in these environments, which must be addressed in order for long-term, vision-based navigation to succeed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Comput. Vis. Image Underst. 110(3), 346–359 (2008)
Churchill, W.S., Newman, P.: Experience-based navigation for long-term localisation. Int. J. Robot. Res. 32(14), 1645–1661 (2013)
Corke, P., Paul, R., Churchill, W., Newman, P.: Dealing with shadows: capturing intrinsic scene appearance for image-based outdoor localisation. In: Proceedings of the International Conference on Intelligent Robots and Systems (IROS), Nov 2013
Furgale, P., Barfoot, T.D.: Visual teach and repeat for long-range rover autonomy. J. Field Robot. 27(5), 534–560 (2010)
Hrabar, S., Corke, P., Bosse, M.: High dynamic range stereo vision for outdoor mobile robotics. In: Robotics and Automation (ICRA) (2009)
Krüsi, P., Bücheler, B., Pomerleau, F., Schwesinger, U., Siegwart, R., Furgale, P.: Lighting-invariant adaptive route following using ICP. J. Field Robot. (2014)
McManus, C., Churchill, W., Maddern, W., Stewart, A., Newman, P.: Shady dealings: robust, long-term visual localisation using illumination invariance. In: Robotics and Automation (ICRA) (2014)
McManus, C., Furgale, P., Stenning, B., Barfoot, T.D.: Visual teach and repeat using appearance-based lidar. In: Robotics and Automation (ICRA) (2012)
McManus, C., Upcroft, B., Newman, P.: Scene signatures: localised and point-less features for localisation. In: Robotics Science and Systems (RSS) (2014)
Milford, M.J., Wyeth, G.F.: SeqSLAM: visual route-based navigation for sunny summer days and stormy winter nights. In: Robotics and Automation (ICRA) (2012)
Naseer, T., Spinello, L., Burgard, W., Stachniss, C.: Robust visual robot localization across seasons using network flows. In: AAAI (2014)
Neubert, P., Sunderhauf, N., Protzel, P.: Appearance change prediction for long-term navigation across seasons. In: Mobile Robots (ECMR) (2013)
Otsu, K., Otsuki, M., Kubota, T.: Experiments on stereo visual odometry in feature-less volcanic fields. In: Field and Service Robotics. Springer Tracts in Advanced Robotics, vol. 105, pp. 365–378 (2015)
Paton, M., McTavish, K., Ostafew, C., Barfoot, T.D.: It’s not easy seeing green: lighting-resistant visual teach & repeat using color-constant images. In: Robotics and Automation (ICRA), May 2015a
Paton, M., Pomerlau, F., Barfoot, T.D.: Eyes in the back of your head: robust visual teach & repeat using multiple stereo cameras. In: Computer and Robot Vision (CRV), June 2015b. To Appear
Ratnasingam, S., Collins, S.: Study of the photodetector characteristics of a camera for color constancy in natural scenes. J. Opt. Soc. Am. A 27(2), 286–294 (2010)
Williams, S., Howard, A.M.: Developing monocular visual pose estimation for arctic environments. J. Field Robot. 27(2), 145–157 (2010)
Acknowledgments
This work was supported by the Natural Sciences and Engineering Research Council (NSERC) through the NSERC Canadian Field Robotics Network (NCFRN). We would also like to thank Jack Collier and the DRDC for conducting a field trial on our behalf in the Canadian High Arctic and Chris Ostafew for assisting in the field trials leading up to this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Paton, M., Pomerleau, F., Barfoot, T.D. (2016). In the Dead of Winter: Challenging Vision-Based Path Following in Extreme Conditions. In: Wettergreen, D., Barfoot, T. (eds) Field and Service Robotics. Springer Tracts in Advanced Robotics, vol 113. Springer, Cham. https://doi.org/10.1007/978-3-319-27702-8_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-27702-8_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27700-4
Online ISBN: 978-3-319-27702-8
eBook Packages: EngineeringEngineering (R0)