Hot take of the day

NEW! ICRA Paper Title Generator!

(no GPTs were harmed in the making of the above title)

My Photo
Contact Information: Siebel 3233, 1-217-244-0821 Email kkhauser (at) illinois.edu

Professor

Department of Computer Science

Department of Electrical and Computer Engineering

Department of Mechanical Science and Engineering

Director, Coordinated Sciences Lab Robotics Group

University of Illinois at Urbana-Champaign

Bio

Kris Hauser is a Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign, and Affiliate of the Department of Electrical and Computer Engineering and the Department of Mechanical Science and Engineering. He received his PhD in Computer Science from Stanford University in 2008, bachelor's degrees in Computer Science and Mathematics from UC Berkeley in 2003, and worked as a postdoctoral fellow at UC Berkeley. He then joined the faculty at Indiana University from 2009-2014, where he started the Intelligent Motion Lab, and then joined the faculty of Duke University from 2014-2019. He also has consulted for Google's autonomous driving company, Waymo, from 2019-2023. Prof. Hauser is a recipient of a Stanford Graduate Fellowship, Siebel Scholar Fellowship, Best Paper Award at IEEE International Conference on Humanoid Robots 2015, the NSF CAREER award, and three Amazon Research Awards.

CV...

Research

Research interests include open-world robotics, robot motion planning and control, and semi-autonomous systems, with applications to intelligent vehicles, robotic manipulation, robot-assisted medicine, and legged locomotion.

More information can be found on the Intelligent Motion Lab website...

Selected Publications

Full list...

Information for Prospective Students

  • PhD candidates. I generally accept applications for highly qualified PhD students on a yearly basis through the UIUC CS or ECE departments. Please email me your CV and outline a potential research topic that you would like to investigate with me. This description must include technical detail, including relevant papers and possible approaches that you would use to address the topic. You may wish to investigate recent papers from my lab's website. Once you share this plan, I will be able to provide further advice about whether you would make a good fit. If you do not receive a response, this means that your background probably isn't a good fit for my lab, and your chances of getting accepted are small. There is no need to send repeated emails hoping for a response; they get instantly deleted.

    In a successful Ph.D. student application I primarily look for evidence of research experience that is targeted toward high-quality academic publications in robotics or an area closely related to robotics (such as AI, CV, ML, optimization, controls). If you have not at least submitted a paper as first or second author, your chances of acceptance are small. I also look for strong analytical skills with regards to motion planning, optimization, 3D vision, and/or machine learning; robot systems development experience; and software engineering skills including significant open-source contributions (your personal Github project doesn't count one bit). If your primary interests are in reinforcement learning, imitation learning, LLMs for robotics, computer vision for image processing, or mechanical design, you will not be a good fit for my lab. You probably should have known that before contacting me.

  • Master's students. I do not admit Master's students into UIUC, so please do not bother contacting me about admissions. If you are already a Master's student at UIUC, my policy for accepting students into my lab is as follows:

    • I do not take on Master's students in their first semester, except under rare circumstances where the student is exceptionally qualified (e.g., worked in state-of-the-art R&D at a robotics company or research lab). Your side projects in robotics and machine learning tutorials don't count.
    • In your first semester, you should receive A's or A+'s in relevant coursework (robotics, AI, optimization, and machine learning classes). Your GPA should be 3.8 or above, overall. You may then contact me about starting a research project in your second semester.
    • The first semester you work in the lab is an evaluation semester. To become a full-fledged member of the lab, you must demonstrate your ability to comprehend state-of-the-art research and contribute to a research project that is likely to lead to a high-quality publication.

  • Undergraduate students. I frequently involve undergraduates in my research, both as independent study students and summer interns. My lab also participates in competitions, so I also take on students who are interested in contributing to a team effort. My minimum guidelines are that you have a 3.7 GPA, relevant coursework, and can contribute at least 10 hours per week to research. To introduce yourself, please email me a CV, transcript, and an idea of what projects you would be interested in working on. Better yet, give me your ideas on how you might tackle a specific technical problem.

    Note: because a large fraction of my funding comes from NSF, US citizens are much more likely to receive paid summer internships.

Information for Reviewers

Reviewers are the unsung heroes of the academic enterprise. Although I would prefer that reviewers be fairly compensated by journals and conferences, that doesn't seem like it will happen any time soon. As a small consolation, my standing policy is that if you perform a review for me, I will happily treat you to to a drink or lunch as a token of thanks for your service. Meet me in person (e.g., at a conference) to redeem this offer!

Blog posts and other musings

Prof. Hauser is an avowed atheist, humanist, and socialist. He is a member of the Freedom From Religion Foundation and The Satanic Temple. In his free time he enjoys rock climbing, skiing, diving, and spending quality time with his family and their two Great Danes.

Teaching

Notes

Robotic Systems Book, working draft
HTML format Source and interactive Jupyter notebook
Klampt information
My lab and I maintain the Klamp't package for robot modeling, planning, visualization, simulation, and control. Most people pip install klampt and find it useful for kinematics, geometry manipulation, and visualization.
More information is available in the manual and tutorials (C++, Python).
Why does the Metropolis-Hastings procedure satisfy the detailed balance criterion? pdf