Vision-Based Gate Detection (YOLOv5)
Fine-tuned detection + lightweight post-processing for robust racing gate localization.
Computer Vision YOLOv5 Robotics
Selected work across autonomy, computer vision, embedded systems, and more.
Fine-tuned detection + lightweight post-processing for robust racing gate localization.
Competed in Abu Dhabi racing drones autonomously at 110+ mph with zero human control.
Hybrid YOLOv5 perception + MPC control achieving 200%+ improvement over NeurIPS 2019 baseline.
Real-time CV signal processing on-device with a hybrid Java/C++ architecture.
More projects coming soon. Check out my GitHub for the latest work.