Advanced Bayesian Methods for Lunar Surface Navigation, Phase II

The key innovation of this project is the application of advanced Bayesian methods to integrate real-time dense stereo vision and high-speed optical flow with an Inertial Measurement Unit (IMU) to produce a highly accurate planetary rover navigation system. The software developed in this project leverages current computing technology to implement advanced Visual Odometry (VO) methods that will accurately track much faster rover movements. Our fully Bayesian approach to VO will utilizes information from the images than previous methods are capable of using. Our Bayesian VO does not explicitly select features to track. Instead it implicitly determines what can be learned from each image pixel and weights the information accordingly. This means that our approach can work with images that have no distinct corners, which can be a significant advantage with low contrast images from permanently shadowed areas. We have shown that the error characteristics of the visual processing are complementary to the error characteristics of a low-cost IMU. Therefore, the combination of the two can provide highly accurate navigation.