Collaborative Aided Target Recognition Using Next-Generation Foundation Models for Multi-Domain Unmanned Systems

Description

Develop and demonstrate a collaborative Aided Target Recognition (AiTR) capability for multi-domain unmanned systems (UAS, UGV, USV) that leverages next-generation pre-trained foundation models—including Vision-Language Models (VLMs), Vision-Language-Action models (VLAs), and/or modern State-Space Models (e.g., S4, S5, Mamba, Mamba-2)—to achieve robust, accurate, and predictive multi-platform, multi-modal target disambiguation in cluttered, contested, and partially observed operational environments.