*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Atlanta, GA | Posted: April 11, 2018
David Mitchell
Communications Officer
Summary Sentence:
Boots' research aims to develop new theory and algorithms that bridge the gap between machine learning and engineering approaches to robotics, which have traditionally been studied separately.
Full Summary:
No summary paragraph submitted.
Byron Boots - CompressedSchool of Interactive Computing Assistant Professor Byron Boots earned a CAREER award from the National Science Foundation (NSF). The award is worth $479,527 and will be paid out over the course of five years.
The award was given in support of Boots’ research, a proposal for which was titled Designing Robots that Learn: Closing the Gap Between Machine Learning and Engineering. His research aims to develop new theory and algorithms that bridge the gap between machine learning and engineering approaches to robotics, which have traditionally been studied separately.
“While engineering uses knowledge of physics to provide interpretability, transparency, and guarantees about the reliability and robustness of engineered systems,” Boots said, “machine learning studies data and information, and provides guarantees that focus on the expressivity of models, computational cost, and sample efficiency of learning algorithms.”
Robots are most successful when interactions with their environment can be precisely defined. A notable example is manufacturing, where one of the keys to success is the ability to engineer the task environment to keep interactions simple, repeatable, and, therefore, predictable. However, as robots and their environments become more complex, accurate modeling becomes more difficult, which can lead to suboptimal or even dangerous behavior.
This presents a challenge: For robotics to advance, new approaches are needed for the complex scenarios where conventional modeling fails.
Boots’ research will combine the strengths of hand-crafted, physics-based models with machine learning algorithms, which allow computers to infer predictive models directly from data collected during a robot’s operation. A combined approach, Boots said, will better position engineers to design robots that can rapidly learn to operate in less-structured, real-world environments by observing their own behavior.
The NSF Faculty Early Career Development Program is a Foundation-wide activity that offers the NSF’s most prestigious awards in support of early-career faculty who have the potential to serve as academic role models in research and education.
Boots came to Georgia Tech in 2014 after spending time as a post-doc in the Robotics and State Estimation Lab at the University of Washington. He received his Ph.D. from Carnegie Mellon University.
