Research Areas
- Deep learning theory, optimization, and learning dynamics (gradient-based methods)
- Representation learning, inductive bias, and interpretable learning mechanisms
- Reinforcement learning for safety-critical and real-world systems (cyber defense, autonomous control)
- AI for Mathematics (AI4Math): auto-formalization and neuro-symbolic reasoning
- Signal-centric remote sensing (sonar, radar) and ML
- Autonomous aerial and underwater vehicles (sim-to-real)
- AI for anomaly detection and sustainability in orbital mechanics and space traffic management
Research Groups
-
Reasoning and Learning Group, Georgia Institute of Technology (2025–Present).
AI4Math / auto-formalization research under Dr. Vijay Ganesh; contributing to LogicComplexityLib, auto-formalizing logic and model theory textbooks using neuro-symbolic reasoning tools. -
Agile Research Group, Embry-Riddle Aeronautical University (2024–2026).
Satellite trajectory optimization research under Dr. Omar Ochoa; developed a PPO-based RL framework for fuel-aware satellite collision avoidance.
Research Posters
Below is a selected collection of research posters from 2022–2026, representing my work across reinforcement learning, optimization, sonar processing, remote sensing, sim-to-real robotics, and aviation NLP.
AERO-Sim2Real: Reinforcement Learning For Sim-to-Real Drone Deployment (2026)
Trains PPO-based flight-control policies in NVIDIA IsaacLab and deploys them on Crazyflie 2.1 nano-quadrotors, quantifying sim-to-real divergence across hover, waypoint-following, and figure-eight trajectory tasks.
Learning Causal Structures from Aviation Accident Narratives (2026)
Compares rule-based NLP, transformer (DistilBERT), and few-shot LLM (Mistral-7B) approaches for extracting causal relationships from NTSB aviation accident narratives and representing them as knowledge graphs.
Satellite Proposal Poster (2025)
This poster introduces the proposes a development framework for satellite anomaly detection. It outlines the motivation, mission impact, and design plan prior to full implementation.
Satellite Trajectory Research Poster (2024)
Displays the full research results for PPO-based orbital collision avoidance, including stabilized low-fuel orbits and debris-avoidance maneuvers. This poster was presented as the research matured into publishable form.
Hierarchical Dueling Q-Learning for Intrusion Detection (2024)
This poster outlines a two-agent Q-learning and Dueling DQN system for classifying and responding to cyberattacks. It demonstrates near-perfect binary and multi-class accuracy on large intrusion datasets.
Sonar Contrastive Learning Research (2024)
Presents a semi-supervised contrastive learning model for sonar-based object detection. Highlights both noise reduction strategies and adaptation potential for radar systems.