I'm excited about the potential for human-centered robots to funamentally improve the lives of humans.
Hi! My name is Kyle Morgenstein and I am a third year PhD student in the Human Centered Robotics Lab at the University of Texas at Austin advised by Professor Luis Sentis. I'm excited about building human-centered robots and their potential to fundamentally improve the lives of humans. My work seeks to answer questions surrounding emergent social behaviors with safety and explainability guarantees. More specifically, I employ learning based methods to give robots the ability to understand, learn from, and respond to social context in accordance with observed social norms, and to continue learning from new social situations throughout the robot's deployment.
Additionally, I am an incoming research intern at the Boston Dynamics AI Institute where I will continue my research in social norm setting and robo-ethics. I spent the previous three summers at the NASA Jet Propulsion Laboratory, where I worked on scalable simulation infrastructure and long-term autonomy for space exploration missions. I have supported the PSYCHE, EELS, and CADRE programs.
I graduated from the Massachusetts Institute of Technology (MIT) in spring of 2020 with degrees in Aerospace Engineering and Earth Atmospheric & Planetary Science, and won the Christopher Goetze Award for undergraduate research.
When I'm not playing with robots, I am an an avid hiker, rower, and tinkerer. I also enjoy cooking, drawing, lifting weights, chocolate ice cream (edit: I am now lactose intolerant), and Club Penguin.
Learning Contact-based Navigation in Crowds
What social norms can robots learn from humans in order to behave in ways that are safe and trust-promoting? This research challenges the current use of simple human simulation models and contact-forbidden control paradigms and explores how estimating the human’s perception of the robot may produce more socially accepted behavior. See project here.
Information-theoretic Multi-agent Search
I am applying multi-agent rienforcement learning methods to the problem of dynamic object search / active sensing motivated by traditional methods in information-theoretic optimal area coverage search.
For my undergraduate senior thesis, I experimented with filamentous Cyanobacteria from Shark Bay, Australia to understand how silica controls in the Proterozoic ocean affected the preservation potential of ancient microbial mats. See a talk I gave for the United Nations Office of Outer Space Affairs here.
I am passionate about science outreach, education, and communication:
Since March 2020 I have been an instructor for Skype-A-Scientist, offering guest lectures for K-12 classrooms across the country. I primarily teach astronomy and earth science.
I am also an instructor through Beavers Who Tutor, where I teach "Hands-On Machine Learning for the Curious Novice" for students ranging from high school to graduate-level.
Most recently, I joined Letters to a Pre-Scientist, an organization promoting outreach by matching middle-schoolers with professional STEM pen-pals.
Hot Nozzle Society
I am a founding member, and logistics lead for the Hot Nozzle Society, the organization behind Hot Nozzle Summer.
"Hot Nozzle Summer" is a movement within the amateur rocket community that seeks to break down the barriers that exist within the hobby and make it more accessible to new people, regardless of skill or training in rocketry or engineering. This movement celebrates all aspects of rocketry whether its getting a Level 1 high powered certification through NAR or Tripoli, or just shooting model rockets in the backyard. The event had over 130 participants in its first year, and over 40 high power certification flights.