Status: Abstract submitted to SPIE Defense + Security 2026 (manuscript due April 2026)
Overview
AIRHOUND is an autonomous UAV perception system platform for detect and pursuit of target drones. I serve as PI on a team of 7 and perception lead, driving the computer vision and real-time inference pipeline development.
Project Highlights
- YOLOv8 object detection pipeline with custom dataset labeling and model fine-tuning for real-world field applications
- Real-time inference on NVIDIA Jetson Orin NX edge computing platform with ROS2 integration for autonomous UAV navigation
- SPIE Defense + Security 2026 — Abstract submitted to “Difficult Data in Machine Learning” track; full manuscript due April 2026
Technical Stack
| Category | Tools |
|---|---|
| Object Detection | YOLOv8, PyTorch, OpenCV |
| Edge Computing | NVIDIA Jetson Orin NX |
| Robotics | ROS2, UAV autonomy |
| Languages | Python |
Team
- Role: Principal Investigator, Perception Lead
- Team Size: 7 members
- Affiliation: Embry-Riddle Aeronautical University
Links
Publication
Abstract submitted to SPIE Defense + Commercial Sensing 2026 — “Difficult Data in Machine Learning” track.
Full manuscript due April 2026.