{"id":5750,"date":"2019-06-19T21:05:32","date_gmt":"2019-06-19T21:05:32","guid":{"rendered":"https:\/\/demos.attesawp.com\/happiness\/?page_id=2"},"modified":"2026-03-17T16:51:18","modified_gmt":"2026-03-17T16:51:18","slug":"home-page-3-2","status":"publish","type":"page","link":"https:\/\/fs.wp.odu.edu\/h1park\/","title":{"rendered":"Physically-Informed Adaptive Agentic AI\u00a0"},"content":{"rendered":"\n\n
\n

🔬 Ongoing Research Projects<\/h2>\n
\n\n
\n \"Nanobot\n
\n

🔮 Nanobot Vascular Drug Delivery<\/h4>\n

Physics-informed AI controls microbot swarms navigating branching capillaries for precision targeted drug delivery in complex vascular networks.<\/p>\n 💸 Partially by NSF — and Pending<\/span>\n Learn More<\/a>\n <\/div>\n <\/div>\n\n

\n \"Data-driven\n
\n

🤖 Data-driven Adaptive AI for Multiagent Autonomy<\/h4>\n

Mixed Entropy Adaptive Autonomy framework for real-time multi-agent coordination under uncertainty with energy-efficient path planning.<\/p>\n 💸 NSF IIS — AFRL — and Pending<\/span>\n Learn More<\/a>\n <\/div>\n <\/div>\n\n

\n \"UAS-based\n
\n

🌀 UAS-based Hurricane Sensing<\/h4>\n

Autonomous drone teams sense active tropical cyclones in real-time, maximizing utility while operating under strong wind field constraints.<\/p>\n 💸 NASA JPL — ONR — and Pending<\/span>\n Learn More<\/a>\n <\/div>\n <\/div>\n\n

\n \"Multimodal\n
\n

🚶 Multimodal Adaptive Condition-based Monitoring<\/h4>\n

Development of self-adapting models that autonomously integrate sub-system\ninteractions to comprehensively explain the state of a ship at the system level.<\/p>\n 💸 MSC — and Pending<\/span>\n Learn More<\/a>\n <\/div>\n <\/div>\n\n

\n \"EV\n
\n

⚡ EV Dynamic Wireless Mobile Charging<\/h4>\n

Intelligent scheduling and route optimization for in-motion wireless charging of electric vehicles across urban transport networks.<\/p>\n 💸 DOE — NSF CIS — USDOT — and Pending<\/span>\n Learn More<\/a>\n <\/div>\n <\/div>\n\n

\n \"Weather-Adaptive\n
\n

🛰 Weather-Adaptive Drones As First Responders<\/h4>\n

Decentralized on-demand task allocation for heterogeneous multi-agent systems with adaptive multimodal sensor integration.<\/p>\n 💸 NASA JPL— VIPC —VDOT —NCDOT — and Pending<\/span>\n Learn More<\/a>\n <\/div>\n <\/div>\n\n<\/div>\n<\/div>\n\n\n\n

\n

My name is John H. Park at ODU. My goal is to develop physically-grounded and mathematically-principled agentic AI frameworks that remain stable, interpretable, and deployable when reality gets messy \u2014 from vascular microbot swarms navigating branching capillaries, to drone teams sensing active storms, to maritime agents operating under multi-second communication delays. We don’t separate solvers from learners: our systems treat multi-agent coordination itself as a numerical problem, where convergence, conditioning, and stability are explicit and testable \u2014 not assumed. Patented and validated through working prototypes in weather-resilient autonomous first response, microbot drug delivery simulation, urban traffic sensing, and ocean-atmospheric coupling, our research bridges the gap between operator theory and edge deployment, producing closed-loop adaptive AI that performs where black-box heuristics fail.<\/h3>\n<\/div>
\"\"<\/figure><\/div>\n\n\n\n
\n
CV Download<\/a><\/div>\n<\/div>\n\n\n\n
\"\"<\/a><\/figure>\n\n\n\n

Data-driven Adaptive AI<\/strong><\/strong> for Multiagent Autonomy<\/h2>\n\n\n\n
\n
\n
\n