Relative optical navigation around small bodies via extreme learning machines

To perform close proximity operations under a low-gravity environment, relative and absolute position are vital information to the spacecraft maneuver. Hence navigation is inseparably integrated in space travel. This paper presents Extreme Learning Machine (ELM) as an optical navigation method around small celestial bodies. ELM is a Single Layer feed-Forward Network (SLFN), a brand of neural network (NN). The algorithm based on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model composes of the output weights which can be used to develop into a hypotheses. The proposed method is used to estimate the position of the spacecraft from optical images obtained through a navigation camera. The results show this approach is promising and potentially suitable for on-board navigation.