Interactive Learning in the Era of Large Models

Featuring Dorsa Sadigh | Assistant Professor - Computer Science, Stanford University
February 21, 2024 | 12:15PM | Marcus Nanotech 1116

Abstract: In this talk, I will discuss the problem of interactive learning by discussing how we can actively learn objective functions from human feedback capturing their preferences. I will then talk about how the value alignment and reward design problem can have solutions beyond active preference-based learning by tapping into the rich context available from large language models. In the second section of the talk, I will more generally talk about the role of large pretrained models in today’s robotics and control systems.

Learn More Here

Polycentric Truthes Mural Installation Complete in Price Gilbert Library

An interpretation of Galileo’s Dialogue Concerning the Two Chief World Systems, Polycentric Truthes also serves as a commentary on the echo chambers within which contemporary society is situated. It will be painted over two months on Wednesdays and Thursdays, and students, faculty and staff are invited to watch the piece coming to life. 

“This piece has been a design and research exploration for more than a year and is now coming to fruition as the custom robotic technology and conceptual design converge,” said Al-Haddad. “This merger of art, science and engineering illustrates the type of exciting work that can be realized through multi-disciplinary research and design projects at Georgia Tech.”

 In 2023, the Library partnered with former Georgia Tech assistant professor and double-graduate Jacket Al-Haddad for the second installment of the Artist-In-Residence program. Polycentric Truthes is the culmination of the program.

Learn More Here

Lu Gan, Assistant Professor - School of Aerospace Engineering

Lu Gan joined the Daniel Guggenheim School of Aerospace Engineering at the Georgia Institute of Technology as an Assistant Professor in January 2024. She leads the Lu's Navigation and Autonomous Robotics (Lunar) Lab at Georgia Tech, and is on the core faculty of the Institute for Robotics and Intelligent Machines. Her research interests include robot perception, robot learning, and autonomous navigation. Her group explores the use of computer vision, machine learning, estimation, probabilistic inference, kinematics and dynamics to develop autonomous systems in ground, air, and space applications. 

The Lu’s Navigation and Autonomous Robotics (Lunar) Lab at Georgia Tech studies problems related to perception and navigation for robots and autonomous systems in ground, air, and space applications. The lab’s primary goal is to enable robotic systems to operate autonomously in highly unstructured environments under harsh sensing conditions for tasks including search and rescue, daily housework, scientific exploration and discovery. The main research areas of the lab include computer vision, machine learning, deep learning, estimation, and probabilistic inference. 

Research Focus Areas: 

• Aerospace
• Autonomy
• Machine Learning
• Robotics