Acoustic UAV Detection System
Overview
A hybrid drone-detection rig fusing a microphone-array acoustic classifier with a YOLOv5/TensorRT visual tracker across two NVIDIA Jetson Nanos — the acoustic side estimates bearing via direction-of-arrival, while a PID-controlled, PCA9685-driven pan-tilt camera locks onto and follows detected drones in real time.
Key Highlights
- 92% classification precision at 15–20 FPS
- Full 360° direction-of-arrival coverage from the microphone array
- TensorRT-optimized YOLOv5 visual detection at 18–25 FPS (640×640, FP16) driving closed-loop PID camera tracking
- Basis for a first-authored review of 20+ studies (2018–2024), published at IEEE SCC 2025
Documentation
More projects
Water-Hydraulic Soft Robotic Arm
Real-time bare-metal control firmware for a water-hydraulic soft robotic arm, including a reverse-engineered CAN bus protocol, a custom tendon-synchronization algorithm, and sensorless closed-loop positioning.
View case studyASL Fingerspelling Robotic Hand
A dual-arm humanoid robotic hand system that mechanically translates spoken letters into American Sign Language fingerspelling in real time, pairing a Jetson Orin Nano speech-to-text pipeline with a 16-servo-per-arm, tendon-driven hand design validated in MuJoCo simulation before hardware assembly.
View case studyTheeb — VEX U Competition Robot
Theeb, a 22-inch VEX U Pushback competition robot built while directing a 14-member sub-team across CAD, fabrication, and integration. Theeb went through four major hardware revisions — from an X-drive base with an S-shaped scoring channel to a lighter, color-sorting H-drive with linear scoring — backed by a PROS/LemLib software stack for sensor-fused autonomous navigation.
View case study