Lead a team of researchers within the Human-Autonomy Teaming Essential Research Program to improve our understanding of how teams of humans and AI/ML-enabled agents may work together. Specific topics of interest include how to effectively translate human intent to agent behaviors on short timescales, how to leverage human knowledge to recover performance when algorithms fail, and what information is necessary to promote trust and higher performance in these teams.

Research Engineer conducting research to create more effective teaming between humans and AI-enabled agents. The primary focus of my research is opportunistic sensing, which involves interpreting passively sensed human behavior/states to partially label data that can be used to update algorithms and provide necessary context to AI-enabled agents.

Determine collaboration opportunities for ongoing research within the Human Research and Engineering Directorate of the CCDC Army Research Laboratory. Interested in academic, industry, and government collaboration related to various aspects of human-agent teaming, including diverse fields such as AI/ML, cognition, and complex systems science.Check out the Strengthening Teamwork for Robust Operations in Novel Groups (STRONG) Collaborative Research Alliance (CRA) for a key collaboration opportunity! (https://www.arl.army.mil/business/collaborative-alliances/current-cras/strong-cra/?doing_wp_cron=1616628211.0785288810729980468750)

My primary research focused upon the improvement of brain-computer interfaces through collection of longitudinal EEG data and identifying cognitive states in this data using machine learning.

I worked as a PhD Candidate in the Thompson Laboratory for Regenerative Orthopaedics conducting biomechanics research.Over my graduate career I worked on a wide range of research projects. These ranged from composite material creation for bone implants, to evaluating robotic systems for manufacturability, to constructing machine learning models to evaluate articular cartilage mechanics.My dissertation research focused on creating predictive models for cartilage biomechanics using proteomic and histologic biomarkers. These models were created using machine learning techniques, specifically neural networks and genetic programming. The research resulted in weakly predictive models of the biomechanics of cartilage samples using a small number of samples from a relatively homogeneous patient population. Most importantly, one model achieved relatively high accuracy using only concentrations of proteomic factors that can be clinically determined from a synovial fluid draw. This may have long-term implications in the early diagnosis of osteoarthritis and development of interventions.

I taught Engineering Thermodynamics at the University of Missouri. This involved creating presentations, exams, and homework for the course, managing the Teaching Assistant for the course, and teaching students both during class hours and during requested office hours.