When: Thursday 12th of Octo, 1pm AEDT
Where: This seminar will be partially presented at the lvl 4 Conference Room at J18 and partially online via Zoom. RSVP
Speaker: Nicholas Harrison
Title: From Optimization Loops to Autonomous Science
Optimization loops are integrated into the way we live and think and manifest themselves in the systems we design. Starting from a high-level perspective of these loops, we can find bridges to using robotics within the scientific method. I demonstrate a specific example of this from my recent research in autonomously testing and forming hypotheses in natural environments. This work uses Multi-Task Gaussian Processes and information-based objective functions to utilize relationships in the environment and increase information gain.
Nicholas Harrison is a third-year Ph.D. student at the University of Sydney, researching with SIRIS/ACFR under the supervision of Salah Sukkarieh. Prior to commencing at USyd, Nicholas received a BS in Physics at Brigham Young University and a MS in Robotics at the University of Utah. His research interests include complex systems, optimization, and inference.