Autonomous science augments the capabilities of planetary rovers by shifting the identification and selection of science targets from remote operators to the rover itself. This shift frees the rover from wasteful idle time and allows for more selective data collection. This paper presents an approach to autonomous science that is comprised of three components: a Bayesian network that uses image data to identify features; an evaluation algorithm that selects the best features; and, a path-planning algorithm that guides the rover to the most scientifically valuable features. Within this framework, the effectiveness of pairing a larger prime rover with a smaller scout rover to improve autonomous science is investigated. Laboratory-based experiments were used to validate the effectiveness of the Bayesian network for feature identification and the scoring algorithm that has been developed for feature evaluation. Simulations were used to compare the traditional use of a solo prime rover to that of also employing a scout. The results presented here indicate that the inclusion of a scout rover can allow the prime rover to avoid pitfalls or routes with low scientific value.

Additional Metadata
Keywords Autonomous science, Bayesian networks, Planetary robotics
Persistent URL
Journal Journal of Intelligent and Robotic Systems: Theory and Applications
Gallant, M.J. (Marc J.), Ellery, A, & Marshall, J. (2013). Rover-based autonomous science by probabilistic identification and evaluation. Journal of Intelligent and Robotic Systems: Theory and Applications, 72(3-4), 591–613. doi:10.1007/s10846-013-9818-6