I received a B.S. in Electrical and Computer Engineering from Cornell University in 2005, where I started my robotics work in Hod Lipson's lab. I went on to graduate from the Ph.D. program at the Robotics Institute at Carnegie Mellon University (CMU) in 2011, where my advisors were Siddhartha Srinivasa and James Kuffner. While at CMU, I worked in the Personal Robotics Lab and completed interships at the Digital Human Research Center in Japan, Intel Labs in Pittsburgh, and LAAS-CNRS in France. In 2012 I completed a post-doc at UC Berkeley working with Ken Goldberg and Pieter Abbeel. I was an Assistant Professor at WPI 2012-2016. I started as faculty at the University of Michigan in 2016. My current research focuses on learning and motion planning for manipulation. I have received the IEEE RAS Early Career Award and the NSF CAREER award.
Research Focus
My research focuses on creating algorithms that allow robots to interact with the world. These general-purpose learning, motion planning, and manipulation algorithms can be applied to robots that work in homes, factories, and operating rooms. I am interested in all aspects of algorithm development; including creating efficient algorithms, proving their theoretical properties, validating them on real-world robots and problems, integrating them with sensing and higher-level reasoning, and distributing them to open-source communities. I draw on ideas in search, optimization, machine learning, motion planning, control theory, and topology to develop these algorithms and to prove their properties. I also seek to develop algorithms which can generalize to many types of practical tasks and application areas.
See the ARM Lab website for current projects and publications.
Talks
A recent talk covering our work on learning where to trust unreliable dynamics models (at MIT, October 2021):
An older talk covering our work on deformable object manipulation (at CMU, November 2017):
The following links point to some documents I've created to guide new robotics researchers. It usually takes at least a year or two for a new student to pick up the unwritten expectations and effective practices needed to conduct research in our field. The documents below can be seen as a "quick start" guide for these expectations and practices. They are by no means exhaustive, instead they convey the basics and are meant to be broadly applicable across robotics subfields. There will no doubt be more specific expectations within each subfield that will need to be learned from an advisor. Also, keep in mind that these are the expectations and practices as I see them. Others will have different opinions, and those may be just as valid. If you are a graduate student and you see a contradiction between what is written here and what your advisors says, listen to your advisor.
