About Me

I am an Assistant Professor of Computer Science at George Mason University, where I lead the Autonomous Robot Interaction (ARI) Laboratory. I am also a member of the Mason Autonomy and Robotics Center.

My mission is to make it as easy as possible for humans to communicate tasks to autonomous robots. This is a difficult problem because robots are designed to think about tasks and social interactions differently from how humans think about them, which leads to unexpected behavior and lower user satisfaction. You can find out more about this on my lab website.

Prior to joining Mason, I was a computer scientist at the US Naval Research Laboratory (NRL), and prior to that, a postdoctoral research associate also at NRL. I received my Ph.D. from the University of Wisconsin-Madison in 2022, advised by Drs. Bilge Mutlu and Aws Albarghouthi. You can find out more from my CV here.

Research Interests

Check out my lab website for a full list of projects, updates, and software that we're working on.

End-User Robot Programming

UIST18, UIST19, CHI20, CHI21, HRI23, HRI24, DIS24, FTROB, DIS26

End-user programming, or EUP for short, focuses on enabling people with a variety of backgrounds and abilities to express long-horizon tasks for robots to perform. My work spans multimodal user interfaces and programming languages, representations, and paradigms for capturing user intent and translating this intent to an executable form.

User-Guided Robot Planning

HRI24, HRI25, CHI25, AAMAS25, ROMAN25, DIS26

Through automated task planning, robots can automatically decide the actions that are necessary in order to achieve a goal. But these robots still require copious amounts of information from end users, including the goals for it to achieve, preferences for how to achieve these goals, and domain knowledge that only they know. I am interested in eliciting this information from users and designing approaches for robots to operationalize this information effectively.

Multimodal Interfaces

UIST19, CHI21, HRI23

Understanding human commands is a difficult problem for robots, because user intent is often channeled through different modalities—spoken language, gestures, eye gaze, etc. My work designs multimodal interfaces for capturing and understanding this intent.

Robot Representations

AAAI-SSS23, ROMAN23, HRI25

A lot of my work seeks to answer the question, how should we computationally represent the knowledge that a robot requires in order to reliably complete tasks in the real world? In seeking to answer this question, I co-organize the annual symposium on Unified Representations for Robot Application Development.

Robot Wranglers

DIS26

I have increasingly become interested in not just the end users of robots, but also the larger ecosystem of people that affect or are affected by robots in different ways—bystanders, supervisors, researchers, maintainers, developers, etc.