The National Science Foundation (NSF) awarded a $599,830 project grant under the Computer and Information Science and Engineering (CISE) program to the University of Alabama in Huntsville (UAH) from October 1, 2025 through September 30, 2028.
The project aims to develop a novel distributed learning framework based on federated learning to enable multi-modal learning across networks of unmanned aerial vehicles (UAVs). This will address challenges in training high-performance machine learning models on diverse data collected by UAVs, such as privacy concerns, bandwidth limitations, and latency constraints associated with centralized training approaches. The project's key innovations focus on enabling coordinated multi-modal federated learning to handle data modality imbalances, as well as addressing adversarial threats and system-level heterogeneity. The broader significance of this work lies in advancing the resilience and reliability of distributed AI systems for airborne platforms, particularly in time-sensitive, resource-constrained, and adversarial environments.