Walker Byrnes

I am a PhD student in the PAIR Lab at Georgia Tech and a Research Engineer at the Georgia Tech Research Institute in Atlanta.

Email  /  CV  /  Scholar  /  Github

profile photo

Recent News

[Sept 2024] In collaboration with members of the PAIR lab, I have officially submitted my first conference paper, CLIMB, to the International Conference on Robotics and Automation (ICRA) 2025 conference.
[Sept 2024] I will be attending the International Food Automation Networking (IFAN) conference at the Georgia Tech Hotel on Sept. 9-10.
[Sept 2024] Website creation.
[Aug 2024] As of August 19th, I am officially starting my PhD journey. I will be working with Prof. Animesh Garg in the People, AI, and Robots (PAIR) lab.
[Aug 2024] Members of CMaT, I am excited to meet with you all at the annual CMaT retreat in Athens, GA on August 7-9.
[Jul 2024] I'm happy to announce that I have been promoted to the rank of Research Engineer II! I'd like to thank my team in the Intelligent Sustainable Technologies Division of GTRI for the opportunities and support.

Research

I am interested in generalizable autonomy and robotics: building intelligence systems that are intuitive, flexible, and ubiquitous. My academic research to date has centered around continual learning for robot task planning and leveraging foundation models to inform agent world representations.

In my professional capacity, I conduct applied automation and robotics research in the fields of biomanufacturing and food processing. In these domains robots and intelligent machines are not present to the same extent as more traditional industries. The complex biochemical processes occurring in cell manufacturing, the heterogeneous and complex physical properties of food products, and the small scales in which such operations take place all pose significant barriers to the development and implementation of automated technologies.

CLIMB: Language-guided Continual Learning for Robot Task Planning
Walker Byrnes, Miroslav Bogdanovic, Avi Balakirsky, Stephen Balakirsky, Animesh Garg,
Submitted to ICRA 2025   (Currently under review)
project page / arXiv (Coming Soon)

A robot task planner that autonomously builds a library of causal world state predicates in the robot's environment by attempting tasks and learning from a large language model teacher on failures.

Current Affiliations

Georgia Tech Research Institute - Aerospace, Transportation, and Advanced Systems Lab

Research Engineer II

Georgia Institute of Technology - People, AI, and Robots Lab

PhD Student (est. graduation 2029)

NSF Engineering Research Center for Cell Manufacturing Technologies (CMaT)

Researcher / Trainee


Website template from Jon Barron. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.