I am a computer vision engineer with a deep understanding of machine learning techniques, computer vision algorithms, and robotics systems design. I have extensive experience developing cutting-edge algorithms and software solutions for a diverse range of projects. My technical skills include proficiency in Python and C++, as well as expertise in image and video processing, object recognition and tracking, deep learning, self-supervised learning and localization. For more information, please check my freshly-compiled resume.
Professional Experience
Throughout my positions in industry I have gained experience across a wide variety of technologies and applications in the perception domain. My main areas of focus include machine learning architecture development, model training and deployment, perception system design, computer vision library development, and autonomous systems integration. I have used C++ and Python for the majority of my professional projects in both distributed and embedded environments. Frameworks and libraries such as Pytorch, Tensorflow, OpenCV, Eigen, and ROS.
Visit this page for more information about my specific roles and responsibilities.
![](https://relyea.io/wp-content/uploads/2023/06/Ford-Logo-edited.png)
![](https://relyea.io/wp-content/uploads/2023/05/ToyotaMaterialHandling-1-edited-1024x576.png)
![](https://relyea.io/wp-content/uploads/2023/03/d3-engineering-logo.png)
Research
During my tenure at RIT I was a graduate research assistant in the machine intelligence lab and published several works involving obstacle detection and cutting-edge robot localization. Currently I contribute to internal conferences and presentations at Ford with exploratory proof-of-concept projects, technology workshops, and literature surveys. I also attend outside conferences including Electronic Imaging and CVPR.
Publications
- Multi-Loc: A Multi-Level Machine Learning based Millimeter-Wave Indoor Warehouse Localization System IEEE Journal of IoT (Submitted)
- LiDAR-Camera Fusion for 3D Object Detection Electronic Imaging 2020
Improving Multimodal Localization Through Self-Supervision Electronic Imaging 2020 - Indoor Wireless Localization Using Consumer-Grade 60 GHz Equipment with Machine Learning for Intelligent Material Handling ICCE 2020 (Awarded Best Paper)
- Multimodal Localization for Autonomous Agents, Electronic Imaging 2019
- Autonomous Navigation Using Localization Priors, Sensor Fusion, and Terrain Classification, Electronic Imaging 2019
Education
Computer Engineering M.S. Rochester Institute of Technology (2020), Deep Learning and Robotics Focus
Computer Engineering B.S. Rochester Institute of Technology (2018)
Projects
Intelligent Material Handling System
![](https://relyea.io//wp-content/uploads/2023/03/forktruck-1-1024x576.jpg)
The Intelligent Material Handling System (iMHS) is an autonomous warehouse inventory management project sponsored by Raymond Corp.
Autonomous People Mover
![](https://relyea.io//wp-content/uploads/2023/03/cart-1024x576.png)
An autonomous golf cart platform with various integrated perception systems capable of transporting passengers. Advanced deep-learning based terrain identification improves scene understanding.
CUDA Depth Image to Laserscan Node
![](https://relyea.io//wp-content/uploads/2023/03/laserscan-2-1024x576.png)
The Intelligent Material Handling System (iMHS) is an autonomous warehouse inventory management project sponsored by Raymond Corp.
EE Robotics Projects
![](https://relyea.io//wp-content/uploads/2023/03/robot-1024x576.png)
An autonomous golf cart platform with various integrated perception systems capable of transporting passengers. Advanced deep-learning based terrain identification improves scene understanding.