The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

We investigate context-sensitive models for rover onboard data analysis. These ?cience maps?consider not only raw rover sensor data but also the sampling location. They improve onboard data understanding by revealing environmental trends and boundaries that can inform autonomous sampling and data return decisions. They also help identify novel features by highlighting anomalies that are unexpected in context of the local environment. In this work, tests with navigation imagery suggest that context-sensitive data analysis using a Hidden Markov Model offers performance benefits for novelty detection during rover traverse.

Keywords

science autonomy, image processing, hidden Markov models

Notes

Associated Center(s) / Consortia: Field Robotics Center

Associated Project(s): Science Autonomy

Text Reference

David R. Thompson, Trey Smith, and David Wettergreen, "Autonomous Detection of Novel Biologic and Geologic Features in Atacama Desert Rover Imagery," Proc. of the Lunar and Planetary Science Conference, March, 2006.

BibTeX Reference

@inproceedings{Thompson_2006_5308,
   author = "David R Thompson and Trey Smith and David Wettergreen",
   title = "Autonomous Detection of Novel Biologic and Geologic Features in Atacama Desert Rover Imagery",
   booktitle = "Proc. of the Lunar and Planetary Science Conference",
   month = "March",
   year = "2006",
}

The Robotics Institute

Menu