Published Paper Details:

The integration of Geospatial Intelligence (GEOINT) with Autonomous Mobility Systems (AMS) is revolutionizing the way machines perceive, navigate, and interact with physical environments. This review explores recent advancements in applying artificial intelligence (AI) models - such as convolutional neural networks (CNNs), graph neural networks (GNNs), and transformers - to geospatial data for enabling autonomy in vehicles, drones, and intelligent transport systems. We present a theoretical framework, experimental results, comparative model evaluations, and key findings from over a decade of research. Challenges including real-time data fusion, generalization, explainability, and privacy preservation are discussed. The review concludes by outlining future directions such as federated learning, edge AI, 4D spatial modeling, and sustainable mobility planning. As cities become smarter and autonomous platforms more widespread, the convergence of GEOINT and AI will be critical to achieving reliable, context-aware, and environmentally conscious mobility solutions.