Challenges in Planetary Mapping and Surface Navigation

Planetary rover navigation is constrained by a set of specific conditions including a Global Positioning System (GPS) denied environment, extreme illumination conditions, gaps in available terrain resolution, low gravity, extreme temperatures, low power and computational systems available on board.

This talk focuses on computer vision approaches for orbital mapping and rover localization suitable for autonomous planetary exploration in the absence of GPS infrastructure. Given an existing orbital terrain map (image and elevation), and the imagery provided by the onboard stereo camera system, the localization method determines the best rover pose through visual odometry, 3D terrain and horizon curve matching. The method is suitable for current and future NASA missions to Moon and Mars.

About the speakers:

Dr. Ara Nefian is a Senior Scientist at NASA Ames Research Center. His general interest are in the areas of computer vision, machine learning and robotics. Ara led the Lunar Mapping and Modeling from Apollo era imagery and was the principal investigator for the Lunar Albedo Reconstruction project. Since 2012 he led the rover navigation team in supporting NASA future robotics Lunar mission and is a collaborator on the science team for Mars Curiosity rover mission.
In the past he was with Intel Research Labs in Santa Clara, CA involved in several projects including us of the Bayesian networks for face and gesture recognition, audio-visual speech processing, web image clustering and bioinformatics. In 2005 Dr. Nefian was part of the computer vision group within the Stanford racing team (Stanley) that won the DARPA Autonomous Navigation Grand Challenge. He co-authored more than 90 research papers and holds ten US and international patents. Ara Nefian holds a BS from Politehnica University Bucharest (1993) and a MSEE and PhD from Georgia Institute of Technology (1999).

Language of the event: English