Efficient Feature Description for Small Body Relative Navigation using Binary Convolutional Neural Networks
This addresses the problem of enabling autonomous feature tracking for spacecraft navigation around small celestial bodies, representing an incremental improvement with practical implementation.
The paper tackles the challenge of designing deep learning architectures for optical feature tracking in small body missions under spacecraft computational constraints by introducing a binary convolutional neural network approach, demonstrating increased performance over traditional methods and feasible runtimes on next-generation processors.
Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While techniques for feature tracking based on deep learning are a promising alternative to current human-in-the-loop processes, designing deep architectures that can operate onboard spacecraft is challenging due to onboard computational and memory constraints. This paper introduces a novel deep local feature description architecture that leverages binary convolutional neural network layers to significantly reduce computational and memory requirements. We train and test our models on real images of small bodies from legacy and ongoing missions and demonstrate increased performance relative to traditional handcrafted methods. Moreover, we implement our models onboard a surrogate for the next-generation spacecraft processor and demonstrate feasible runtimes for online feature tracking.