I'm Briana Skinner — an emerging robotics and AI researcher focused on autonomous systems, safety, and making sure the next generation of engineers knows there's room for them too.
I want to build robots people can trust. Not just technically reliable — but fundamentally safe, fair, and transparent in how they make decisions. That's the thread running through everything I do.
My research interests sit at the intersection of autonomous systems and trustworthy AI. At FIU, I'll be focused on how intelligent systems navigate uncertain terrain — environments where the stakes are high and the margin for error is low. Long term, I'm working toward a PhD and a career in research and academia, where I can both advance the field and build space for researchers who, like me, took a road less traveled to get here.
I currently serve as a Research Assistant and Laboratory Assistant at Broward College, contributing to robotics and AI projects through Project ACCESS — a program bridging Broward College and FIU's Applied Research Center. I've also had the privilege of teaching over 80 students how to program and fly drones, which reminded me why the mentorship side of research matters just as much as the science.
I'm completing a Bachelor of Applied Science in Data Analytics & AI at Broward College and beginning my M.S. in Computer Engineering at Florida International University in Fall 2026.
Designed, assembled, and tested a functional remotely operated vehicle through Project ACCESS. Performed electrical wiring, soldering, waterproofing, and controller assembly, gaining hands-on experience with hardware integration and underwater systems.
A five-page interactive Power BI dashboard built for Miami-Dade County's Water & Sewer Department, Construction Contracts Division. Replaced legacy reporting with a daily-refreshing system tracking active construction projects, contracting officer workload, bid timelines, and process progression from procurement through Notice to Proceed. Built on a custom data model spanning multiple Databricks SQL sources with DAX measures and SharePoint calendar integration.
Built and evaluated three machine learning models (Decision Tree, Naive Bayes, SVM) to detect disparities in AI-driven risk assessment, using a real-world COMPAS dataset as a case study. Found that a sensitive trait's absence does not guarantee fairness: excluding age produced little disparity in most models, but including it directly caused a dramatic bias increase in the Decision Tree specifically (false-positive rate for under-25 defendants rose from 15.2% to 50.8%). Also found consistent sex-based disparities across all three models. Presented findings via research poster to Broward College and FIU faculty and research staff, with implications for bias risk in autonomous and robotic systems.
Presented Summer 2026 — Broward College & FIU Applied Research Center.
Viewing only — reach out via email if you'd like a PDF copy.
Open to research collaborations, fellowship opportunities, and conversations about robotics, AI safety, and the future of autonomous systems.