Vision-Based Gate Detection (YOLOv5)
Fine-tuned detection + lightweight post-processing for robust racing gate localization.
Computer Vision YOLOv5 Robotics
Champaign, IL • USA
Computer Engineering @ UIUC • Robotics / Computer Vision / Autonomy / Machine Learning
Krishna Dubey
About Me
I'm Krishna Dubey, a Computer Engineering senior at UIUC focused on vision-based drone autonomy and reliable robotics. My interests lie in applying machine learning and deep learning to build perception and control systems that turn camera data into safe, high-performance flight. My work is driven by a core question: how can we design deep learning-enabled autonomous controllers that not only perform well in ideal conditions but remain resilient, reliable, and, ultimately, certifiably safe in the real world? This site highlights my research, projects, and work-in-progress across autonomy, computer vision, and more.
Education
University of Illinois Urbana-Champaign
B.S. Computer Engineering • Minor in Business
Focus: Robotics, Computer Vision, Deep Learning, Safe Autonomy
Research Interests
Autonomous drones Computer vision Deep learning Reliable autonomy Embedded systems
Contact
[email protected]
Open to research collaborations and opportunities
Featured Projects
A few highlights from my work in autonomy and computer vision.
A2RL International Autonomous Drone Racing Competition
Competed in Abu Dhabi racing drones autonomously at 110+ mph with zero human control.
Autonomous Drones Computer Vision Robotics AI
Read Article
Autonomous Drone Racing - Vision-Based Gate Detection and MPC Control (ECE484)
Hybrid YOLOv5 perception + MPC control achieving 200%+ improvement over NeurIPS 2019 baseline.
Autonomy YOLOv5 MPC Computer Vision AirSim