SWARM is a cloud-based simulation platform that provides a simple easy-to-use user interface for building autonomous flight control algorithms used by MIT Lincoln Laboratory, Alarm.com, and others from all levels of backgrounds. With a hassle-free, 2-step installation process with a well-documented, simple API. With an extensive motion planning and obstacle avoidance library to be utilized by customers to help in the development process. Building a platform built for machine learning, reinforcement learning, and autonomous system development.

• Developed a robust camera model that tracks objects using camera vision and provides approximate location data• Designed an image pipeline that takes in ground truth data and images to build bounding boxes around objects of interest in synthetic data to improve the YOLO model training pipeline• Implemented a camera calibration setup pipeline in Unreal Engine to calibrate a variety of cameras that were used in capturing data• Built photo-realistic environments in Unreal Engine to train a YOLO model on synthetic data• Collaborated with university partner research teams leading weekly update meetings

● Utilized Stone-Soup to create a simulated environment for comprehensive data collection, enabling rigorous testing of UVA tracking algorithms● Designed a sensor fusion model for an acoustic sensor system, employing linear algebra techniques to create a sensor repository to help acquire essential test data● Implemented Docker and Kafka brokers to facilitate the development of a robust communication system, enabling seamless interaction between the model and sensors● Developed a program to retrieve weather API, followed by storage on a server, allowing for efficient SQL access● Collaborated with the team to create a machine-learning model leveraging weather data to improve aircraft ETA predictions● Engaged in virtual code review sessions and actively contributed to code quality enhancement and discussions