Feature-Aware Deep Learning for Maritime Intent Recognition
Abstract
Presenting work on feature-aware deep learning architectures that incorporate bearing-rate, CPA/TCPA, and motion derivatives to classify vessel intent early under noisy, sparse observations. The models achieve ~97% accuracy on seven maritime behaviors using only initial trajectory segments, supporting threat-aware decision-making for naval agents.
Date
Nov 2, 2025 9:00 AM — Nov 5, 2025 5:00 PM
Event
Location
Anaheim, California, USA
Anaheim, California
I will present our paper Feature-Aware Deep Learning for Maritime Intent Recognition at IEEE FMLDS 2025 in Anaheim, California (Nov 2–5, 2025).
