An integrated system for multi-rover scientific exploration
Tara A. Estlin, Alexander Gray, Tobias Mann, Gregg Rabideau, Rebecca Castaño, Steve Chien, Eric Mjolsness · 1999
This paper describes an integrated system for co-ordinating multiple rover behavior with the overall goal of collecting planetary surface data. The Multi-P~over Integrated Science Understanding System com-bines concepts from machine learning with planning and scheduling to perform autonomous scientific ex-ploration by cooperating rovers. The integrated system utilizes a novel machine learning clustering component to analyze science data and direct new science activi-ties. A planning and scheduling system is employed to generate rover plans for achieving science goals and to coordinate activities among rovers. We describe each of these components and discuss some of the key inte-gration issues that arose during development and in-fluenced both system design and performance.