wil thomason

I am a fourth-year PhD candidate in the Department of Computer Science at Cornell University. I work on integrated task and motion planning. Specifically, I’m interested in improving the efficiency, robustness, and autonomy of robot task and motion planning.

Though I primarily research robotics, I’m also interested in machine learning, programming languages, and interdisciplinary efforts among these areas. I am graciously funded by the NDSEG Fellowship. I am advised by Professor Ross Knepper in the Robotic Personal Assistants Lab.

Research

I work on integrated task and motion planning. My work explores approaches to task and motion planning that make few domain-specific assumptions but provide high performance and robustness to action failure. My current research continues along these lines, as well as looking into improved planning effort reuse through abstract plan representation and possible fusions of classical planning with modern machine learning for more efficient, automatic planning and execution.

I’m also interested in algorithms for efficient cooperation in heterogeneous multi-robot teams — in particular, for ad hoc teams. I want teams of humans and arbitrary robotic systems to be able to work together in a manner which both “feels” natural and is efficient and effective.

For more about my research, please see my publication and presentation list.

News

Teaching

Outreach

  • I have taught 7th and 8th grade girls about state machines and programming at Cornell’s Expanding your Horizons conference (Spring 2016, 2017, and 2018)

Departmental Service

Links

This site contains references to my CV, a list of my publications and presentations, my (infrequently updated) blog, and my Github profile.

Contact

  • wbthomason ( at ) {my department, abbr.}.{my university}.edu
  • {firstname}(dot){lastname}@{Google’s mail service}
  • Twitter: [@wilthomason](https://twitter.com/wilthomason)
  • Github: wbthomason