Jared Beard

EDUCATION

    BS Mechanical Engineering, West Virginia University (2018)

    MS Mechanical Engineering, West Virginia University (2020)

        Thesis: “Environment Search Subject to High Robot Localization Uncertainty”

    PhD Aerospace Engineering, West Virginia University (EST 2023)

DIGITAL FOOTPRINT

LinkedIn
Github
Google Scholar

BIO

Growing up, Jared had always wondered what made things tick. This led him to pursue studies in Engineering. He spent a few years studying nanotechnology in the WVU FEST lab with Dr. Kostas Sierros, before finding his passion for robotics during his senior year robotics capstone. His undergraduate experience gave him the opportunity to study in Crete, Greece for 6 weeks into the development of gas sensors. As an undergraduate Jared became a Goldwater Scholar and received a West Virginia Space Grant Undergraduate Research Fellowship. Before graduating, Jared was the lead mechanical engineer for the WV payload in the 2018 RockSat-X program. When starting his Master’s Jared joined the Interactive Robotics Lab with Dr. Gu. During his time as a Master’s student, Jared spent a summer doing high degree of freedom controls at NASA’s Jet Propulsion Laboratory and earned a West Virginia Space Grant Graduate Research Fellowship. Jared is currently a Ruby Doctoral Fellow and focuses his efforts on robot autonomy. This is primarily centered around ROS2 based development of planning and decision making systems from the mission and task level to controls. His primary interest is in exploring the uncertainties which we and robots make decisions. In his off time, Jared enjoys reading, hiking, and playing with his dog Kobe. He volunteers as a mentor for the Mountaineer Area RoboticS (MARS) high school FIRST robotics team, as well.

RESEARCH STATEMENT

Decision making is integral to every aspect of our lives--from what we wear to how we interact with people to how we do our jobs. Often humans rely on heuristics to reduce the mental burden of this litany of decisions; this leads to error and biases in outcomes. Thus far, our many robotic decision makers have similarly relied on a great deal of heuristics. We have started to see the advent of more theoretically sound ways to solve these problems. Often this involves formulation as a class of Markov Decision Process (MDP). Such approaches fall short in real world applications. This is due in large part to the ambiguity surrounding how real world systems operate and their complexity. To this end, my aim is to study autonomous decision makers and explore methods for handling uncertainties in  our knowledge of systems. In this way we can push robots into more unknown environments. We may even be able to learn something about solving problems more broadly.