LEARNING-BASED APPROACH FOR RELEVANT DATA EXTRACTION (LARDE)

Autonomous systems continue to be outfitted with larger amounts of sensors that are capable of collecting extremely large amounts of data over the course of a mission. Even autonomous systems with high storage capacities can run into storage limitations when burdened with large amounts of sensor data over long mission durations. This proposal will develop a Learning-based Approach for Relevant Data Abstraction (LARDA) from a set of sensors that produce a large volume of raw data on-board an autonomous system. LARDA will generate a data abstraction and handling framework that is generic enough to be useful for a variety of current and future autonomous systems, but specific enough to directly support missions fielded with autonomous systems in the near-term. The core algorithms of this framework will comprise both supervised and unsupervised machine learning techniques to extract, cluster, and label relevant features from sensor data that can support planning and decision-making for future autonomous missions.