Sidharth Talia
I am a CS Ph.D. student at the University of Washington Seattle, part of Dr. Siddhartha Srinivasa's Personal Robotics Lab. I’ve had the opportunity to work on a wide variety of systems ---hardware and software--- and contribute to some awesome open-source projects, such as the MuSHR project. I generally take an interest in any aspect of robotics that requires contending with the physics and uncertainty of the real world. I also enjoy optimizing slow algorithms/methods to run on real hardware. Off-road autonomy is one problem area that sits at the intersection of all three, and to work on problems related to it, I have made a small-scale research platform at PRL, UW. Apart from robotics, I know my way around hacking hardware in general.
​
If you're interested in seeing the projects I've made (pre-Ph.D.) from the ground up, peruse my project blogs here or on the top right corner by clicking on "Project-stories". I also TA for the CSE478: Autonomous Robotics at UW regularly.
About me
I’ve had an interest in cars, planes, humanoids, jet engines, and so on from a very young age; as a kid, I would often go to the library in my school specifically to learn what makes them tick from one of those "how it works" books. ​I have always enjoyed tinkering with hardware and at the same time explaining the behaviors being observed mathematically. Having worked at various tech-related start-ups, either as an intern or a consultant, as well as research labs, the insights I bring to the table consider the practical as well as fundamental aspects.
​
I am particularly interested in problems that would have a positive real impact if solved. For instance, It is a privilege for me to have access to massive computing resources when I work at UW. Sadly this is not a privilege shared by many. As such, one of the problems that sits close to my heart is that of democratizing robotics, particularly, the idea of doing more with less in terms of computation. Apart from the societal impact, it effectively forces one to consider the fundamental aspects of the problem at hand and exploit any mathematical properties in the problem structure to gain computational advantage.
​