Self-Supervised Classification for Planetary Rover Terrain Sensing
2007 (English)In: Aerospace Conference, 2007 IEEE, Piscataway: IEEE Press, 2007, p. 1-9Conference paper, Published paper (Refereed)
Abstract [en]
Autonomous mobility in rough terrain is key to enabling increased science data return from planetary rover missions. Current terrain sensing and path planning approaches can be used to avoid geometric hazards, such as rocks and steep slopes, but are unable to remotely identify and avoid non-geometric hazards, such as loose sand in which a rover may become entrenched. This paper proposes a self-supervised classification approach to learning the visual appearance of terrain classes which relies on vibration-based sensing of wheel-terrain interaction to identify these terrain classes. Experimental results from a four-wheeled rover in Mars analog terrain demonstrate the potential for this approach.
Place, publisher, year, edition, pages
Piscataway: IEEE Press, 2007. p. 1-9
Series
IEEE Aerospace Conference. Proceedings, ISSN 1095-323X
Keywords [en]
Costs, Extraterrestrial measurements, Hazards, Mars, Mechanical engineering, Mobile robots, Path planning, Robot sensing systems, Soil measurements, Wheels, Aerospace robotics, Path planning, Planetary rovers, Autonomous mobility, Planetary rover terrain sensing, Self supervised classification, Vibration based sensing, Wheel terrain interaction
National Category
Robotics
Identifiers
URN: urn:nbn:se:hh:diva-20821DOI: 10.1109/AERO.2007.352693ISI: 000251235302086Scopus ID: 2-s2.0-34548811371ISBN: 1-4244-0525-4 ISBN: 978-1-4244-0524-4 OAI: oai:DiVA.org:hh-20821DiVA, id: diva2:586712
Conference
2007 IEEE Aerospace Conference, Big Sky, MT, MAR 03-10, 2007
2013-01-122013-01-122018-03-22Bibliographically approved