Fuzzy logic expert system for tier-scalable planetary reconnaissance

Future unconstrained, science-driven, smart planetary reconnaissance will require higher levels of onboard automation, including autonomous determination of sites where the probability of significant scientific findings is highest. In this paper, we describe the design of an expert system that, when embedded in a tier-scalable mission architecture deployed to collect information at multiple scales and using multiple instruments, is capable of autonomously performing synthesis of spatial, "in-transit" collected information to optimally home in on locales for further exploration. More specifically, the fuzzy logic framework has been used to design a system capable of "following-the-water", i.e. ingesting the appropriate water indicators to autonomously evaluate/assess the potential exhibited by the observed locale to host past and/or extant water. The system relies on a set of IF-THEN rules extracted to mimick the investigative approach of a planetary geologist/hydrologist. The system is simulated on hypothesized martian scenarios to show the potential of the overall approach.