Hi, I'm Ege Özgül

Robotics and AI Engineer

I build autonomous systems that work in the real world, from perception pipelines and real-time decision-making to full autonomy stacks deployed on physical robots. Trained in Electrical and Computer Engineering at Tufts University and Robotics Engineering (EECE concentration) at Northeastern University, I've shipped production robotics at Amazon Robotics, Rivian, and Samsung, and conducted research at both institutions. My work is grounded in a deep embedded and hardware background, which lets me build things that actually run on real platforms and not just in simulation.

Explore My Work

Projects

Robotics and Artificial Intelligence
GTSAM Optimization

3D Pointcloud Reconstruction

An incremental Structure from Motion (SfM) pipeline that reconstructs a sparse 3D point cloud from a sequence of images, recovering both scene geometry and camera trajectory.

OpenCVPython
View Project
Stretch 3 Simulation

Stretch 3 Simulation Environment

MuJoCo-based simulation environment for the Hello Robot Stretch 3 platform with ROS 2 integration. Models a kitchen workspace with manipulable objects for validating Reinforcement Learning algorithms, including a Macro MARL PPO model developed at Northeastern University.

MuJoCoROS 2Python
View Project
GTSAM Optimization

2D Mosaic Reconstruction

A 2D image stitching pipeline that builds globally consistent panoramas from overlapping image sequences by combining covariance-weighted graph construction, loop closure detection, and a GTSAM factor graph optimization to eliminate accumulated drift.

GTSAMPython
View Project
Architecture

Equivariant β-VAE for 3D Shape Generation

Designed and trained a β-Variational Autoencoder with a 3D convolutional encoder-decoder architecture to learn probabilistic latent representations of human spinal bone geometry from voxelized mesh data, evaluating both a standard CNN variant and a group-equivariant steerable CNN with octahedral symmetry across reconstruction and generative metrics.

PyTorchPythonEquivariant Steerable CNNs
View Project
Electrical and Embedded Systems
Smart Motor Driver

Feedback Motor Controller

Open-source closed-loop DC motor driver with custom PCB, STM32 firmware in C, onboard PID control and trapezoidal trajectory planning on a 30×40mm board. Plugs directly into any Raspberry Pi or microcontroller via Qwiic connectors — no soldering required. Up to 112 units daisy-chainable on a single I2C bus.

KiCadC/C++STM32
View Project
snowBoard

snowBoard

Rugged electronic development board built for low-power outdoor deployment. Features onboard sensing, wireless communication, and a compact form factor designed for field robotics and remote data collection.

KiCadC/C++
View Project
Tension Sensing Thread Factory

Tension Sensing Thread Factory

Manufacturing system with real-time tension monitoring and closed-loop control for automated thread production. Integrates custom sensing hardware with embedded control firmware.

KiCadC/C++Fusion 360
View Project
Other Explorations
Convertible Wing Drone

Convertible Wing Drone

Custom built drone that converts to flying wing. AVR based microcontroller is integrated on a custom PCB which runs the custom flight controller firmware.

AVRC/C++KiCad
View Project
3D Software Rendering Engine

3D Software Rendering Engine

Custom 3D graphics engine built from scratch, featuring real-time rendering and advanced shading techniques.

C++
View Project
Procedural Spherical Map Generator

Procedural Spherical Map Generator

OpenGL-based tool for generating realistic planetary surfaces using procedural algorithms and noise functions.

OpenGLC++
View Project
Large Volume 3D Printer

Large Volume 3D Printer

Custom-built FDM 3D printer with a 110×75×40 cm build volume — large enough to print a full human torso in one piece. Supports swappable extruders including a syringe extruder. Designed so anyone can replicate it at any size.

Fusion 360
View Project
Rational Number Computing Accelerator

Rational Number Computing Accelerator

Hardware accelerator design in VHDL for efficient rational number computations in embedded systems.

VHDL
View Project