Science-influenced mobile robot guidance using Bayesian Networks

The high cost of planetary rover missions limits risk-taking and therefore restricts scientific exploration. Also, limited autonomy requires time-consuming manual commands that must be issued to the rover from a great distance. This pa per explores the combination of vision-based geological in formation inferred from a Bayesian Network (BN) with the guidance system of a micro-rover scout. Simulation is used to study the abilities of the developed algorithm.