Skip to content
View Sujjay02's full-sized avatar
3 followers · 7 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report Sujjay02

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Sujjay02/README.md

Sujjay Karthikeyan

Mechanical Engineering + Physics @ UNC Charlotte · AI minor · May 2028

Building autonomous systems that operate in the physical world — from multi-UAV swarms navigating contested airspace to carbon fiber airframes fabricated by hand. Undergraduate researcher at the SmartNet Lab, where my current focus is closing the loop between RL policy and real multi-robot coordination. Interning at Kathedra in Conover, NC across mechanical design and software integration.

Director of InspireNC, a STEM nonprofit partnered with the US Air Force, MetLife, and Lenovo.

What I'm building
Multi-UAV coverage Q-learning policy over a 3-drone Gazebo swarm on MRS UAV System. Optimizing coverage paths and handoff logic between agents.
VTOL UAV Custom two-axis tilt-rotor from scratch — SolidWorks/Onshape, carbon fiber airframe, bespoke flight controller integration.
Perception pipeline YOLOv8 + multi-object tracking streamed live to a Flask dashboard over SSE. Built for real-time activity monitoring.

Stack

Languages

Python C++ Java TypeScript

Robotics & Simulation

ROS Gazebo OpenCV

ML / AI

PyTorch YOLOv8

CAD & Hardware

SolidWorks Onshape Fusion 360

Projects

Project Description
Drone-Simulation-Q-Learning Multi-UAV coverage optimization via Q-learning — 3 DJI F450s in Gazebo, MRS UAV System
ROS2-Drone-Simulation ROS2 multi-drone coordination and trajectory simulation
Camera-Detection-for-Fast-Food Real-time activity tracking — YOLOv8 + multi-object tracking, live Flask/SSE dashboard
Forge AI-powered CAD assistant built on the Gemini API
SpaceToSoilChallenge NASA Space to Soil — SoilSentinel SmallSat + drone swarm for precision crop monitoring
frc6908/2026-Robot FRC Team 6908 Infuzed — 2026 competition robot (Java, WPILib)

Portfolio   LinkedIn   Email

Pinned Loading

  1. Drone-Simulation-Q-Learning Drone-Simulation-Q-Learning Public

    Multi-UAV coverage optimization using Q-learning in Gazebo. Three DJI F450 drones coordinate to sweep ground targets in a custom simulated environment built on the MRS UAV system.

    Python

  2. frc6908/2026-Robot frc6908/2026-Robot Public

    FRC 6908 Infuzed's 2026 robot code.

    Java 2 2

  3. Forge Forge Public

    Shell for a CAD developing AI Software, still under work

    HTML 2

  4. Camera-Detection-for-Fast-Food Camera-Detection-for-Fast-Food Public

    Real-time worker activity tracking and wait time estimation using YOLOv8 + multi-object tracking, served through a live Flask dashboard with SSE streaming.

    Python

  5. SpaceToSoilChallenge SpaceToSoilChallenge Public

    Adaptive onboard flash drought early warning for SmallSat constellations, NASA ESTO Space to Soil 2026

    JavaScript