I develop methods for automated design that identify the inherent capabilities and limitations of AI agents with respect to their environment and find the best way to redesign the environment to account for those limitations and maximize the agents' performance.
My long-term goal is to provide the theoretical foundations for designing AI systems that are capable of effective partnership in sustainable and efficient collaborations of automated agents as well as of automated agents and people. This agenda
is driven by various real-world multi-agent scenarios for which current AI methods are insufficient.
My current focus is on applying these methods of automated design to promote effective multi-robot and human-robot collaborations.
I use the term design to mean anything that does not involve waiting around for more data or technological advancement to maximize the performance of an AI system.
Click on the links below to learn more about my different projects. This is a link to my Rising Stars 2020 poster that summarizes my research.