April 17 seminar: Abee Alazzwi

April 17, 2026

Hierarchical Safe Reinforcement Learning for Mission Aware Multi UAV

Abee Alazzwi, UNM

3:00 pm, UNM Centennial Engineering Center, Room 1026
Online Guests: Contact Prof. Santhanam <bsanthan@unm.edu> for a Zoom link

Abstract: Unmanned Aerial Vehicle ( assisted communication systems enable flexible and adaptive connectivity by dynamically supporting Internet of Things ( networks under changing conditions Hierarchical Safe Reinforcement Learning (HS RL), a multi timescale decision making framework, can provide effective solutions for joint optimization of UAV placement, traffic load balancing, and real time control while ensuring safety constraints through control barrier functions.

In this talk, we will explore the use of hierarchical reinforcement learning to coordinate multiple UAVs across strategic and tactical layers for mission aware operations, and evaluate system performance in terms of latency, energy efficiency, fairness, and reliability We will compare the results with those of conventional optimization and flat reinforcement learning methods under dynamic network scenarios If time permits, we will also explore extensions toward risk aware learning and graph based safety mechanisms to improve scalability and robustness in multi UAV systems

Bio: Dr Abee Alazzwi is a Ph D candidate in Electrical and Computer Engineering at the University of New Mexico ( where she also received her M S in Electrical Engineering and B S in Computer Engineering Her graduate research involves developing reinforcement learning frameworks, signal processing methods, and machine learning techniques for UAV assisted communication systems and intelligent IoT networks, with a focus on dynamic optimization, traffic load balancing, and autonomous decision making under uncertainty.

She has worked as a federal engineer with the National Nuclear Security Administration ( as well as at Sandia National Laboratories, where she developed and applied signal processing, digital image processing, and machine learning techniques for real time systems and advanced engineering applications.

Her recent and current research spans hierarchical and multi agent reinforcement learning, safety critical AI, and edge enabled UAV networks to enable scalable, mission aware, and provably safe autonomous systems.

Dr Alazzwi’s research contributes to advancing intelligent autonomous systems and next generation wireless communications for both civilian and mission critical applications.