Science Autonomy in the Atacama

Trey Smith
Proc. of ICML 2003 Workshop on Machine Learning Technologies for Autonomous Space Applications, 2003.


Download
  • Adobe portable document format (pdf) (255KB)
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 have recently embarked on a three-year project, funded by the NASA ASTEP program, to develop robotic astrobiology in the process of learning the limits of life in the Atacama desert of Chile. We see this as an opportunity to develop a more science-aware rover: one that, on encountering a new area, can select interesting features, perform initial experiments, and selectively return relevant data, all before receiving feedback from the science team. Several components of the proposed science autonomy system can make use of classifiers (is this the kind of rock we are looking for?) and clustering algorithms (is this rock like anything we have already sampled?). The unknown character of unexplored areas motivates use of on-line learning techniques.

Keywords
space, rover, science, science autonomy

Notes
Associated Center(s) / Consortia: Field Robotics Center
Associated Project(s): Life in the Atacama
Number of pages: 6

Text Reference
Trey Smith, "Science Autonomy in the Atacama," Proc. of ICML 2003 Workshop on Machine Learning Technologies for Autonomous Space Applications, 2003.

BibTeX Reference
@inproceedings{Smith_2003_4819,
   author = "Trey Smith",
   title = "Science Autonomy in the Atacama",
   booktitle = "Proc. of ICML 2003 Workshop on Machine Learning Technologies for Autonomous Space Applications",
   year = "2003",
}