SPIE Defense + Security Poster

Poster presentation describing a Physics-Informed Attentive Neural Process (PI-AttNP) framework for multi-time-scale vehicle state estimation using Automatic Identification System (AIS) ship-tracking and Automatic Dependent Surveillance–Broadcast (ADS-B) aircraft-tracking datasets. The approach incorporates simplified physics-based motion models directly into an attentive neural process architecture to improve predictive accuracy across widely varying temporal resolutions.

Experimental evaluation demonstrated improved estimation performance relative to several state-of-the-art neural and probabilistic estimation baselines while maintaining real-time inference capability. The work was accepted for both paper + presentation at SPIE Defense + Security 2026.