← All Projects

AIRHOUND


Overview

AIRHOUND is an autonomous UAV perception system for detect and pursuit of target drones. I serves as the PI on a team of 7, as well as being the project perception lead. I architected the computer vision, sensor fusion, and real-time inference pipeline.

Project Highlights

  • RF-DETR object detction: optimized with TensorRT for ~30ms inference on NVIDIA Jetson Orin 16gb, fused with a Intel RealSense D455 camera for 3D target localization
  • ROS2 autonomy stack: camera driver, detection, depth fusion, and tracking nodes along with inter-process communication feeding the PX4 offboard control
  • Hardware in the loop testing on fully assembled drone
  • ERAU SPARK equipment grant secured for project funding
  • SPIE Defense + Commercial Sensing 2026: presented April 28, 2026 (paper 14030-26 in proceedings)
  • ERAU Beyond: Undergraduate Research Journal: methods paper posted May 26, 2026 (MS #1176)

Links

Publications

Malarchick, R. et al. (2026). "Predictive Target Pursuit for Autonomous UAVs using RF-DETR with Depth-Aware State Estimation and Physics-Informed Trajectory Prediction." SPIE Defense + Security 2026, paper 14030-26 (presented April 28, 2026).

Malarchick, R. et al. (2026). "Robust Real-Time UAV Target Tracking with Onboard Vision-Based Yaw Control." ERAU Beyond: Undergraduate Research Journal, MS #1176 (May 2026).