Rockster: Onboard Rock Segmentation Through Edge Regrouping

Abstract

To perform more complex space exploration activities with limited human intervention, an intelligent system must be able not only to sense its environment, but also to interpret the sensory data it acquires. Rock Segmentation Through Edge Regrouping is an autonomous perception algorithm for scientific analysis that is deployed on Mars. It conducts onboard analysis of images collected by the Mars Exploration Rover Opportunity and provides a list of closed rock contours to the Autonomous Exploration for Gathering Increased Science software module, which then prioritizes the identified rocks for subsequent targeting based on preferences expressed by scientists. Rock Segmentation Through Edge Regrouping processes images in 600–900 s on the MER RAD6000 flight processor, clocked to operate at 20 million instructions per second, with a guaranteed high-water memory footprint of less than 4 megabytes of RAM. In all runs on Mars with rocks or outcrop present, the top 10 returned targets have been valid rocks or outcrop with one exception, which was a dark patch of soil. In several runs in which there were no rocks present, the algorithm correctly returned no detections. A nearly integer-only parallel version of the algorithm has been demonstrated on a Tilera TILE64 multicore processor.