Strategies for autonomous rovers at Mars

Abstract

The science return from future robotic exploration of the Martian surface can be enhanced by performing routine processing using onboard computers. This can be accomplished by using software that recognizes scientifically relevant surface features from imaging and other data and prioritizes the data for return transmission to Earth. Two algorithms have been designed and evaluated with field data to identify the properties of the environment that can be reliably detected with onboard imaging and multispectral observation. One algorithm identifies variations in surface textures in images and successfully distinguishes between rocks and soil and between differences in grain size in a rock of a single composition. A second algorithm utilizes a neural net to recognize selected carbonate minerals from spectral reflectance data and successfully identifies carbonates from a set of spectra collected in the field. These types of algorithms will contribute to the efficiency of a landed instrument suite given the limited resources of time, data storage, and available communications opportunities.