Sky Seminar Series: Ken Goldberg (UC Berkeley) – Big Robot Data: Streamlining Data Collection for Large Robot Action Models

Speaker: Ken Goldberg
Location: Soda 465H
Date: April 26, 2024
Time: 12-1pm PST

Title:
Big Robot Data: Streamlining Data Collection for Large Robot Action Models
Ken Goldberg, Eric Chen, Silvery Fu, and Peter Schlafhalter

Abstract:
The Robot Transformer (RT-X) project, led by Google with 21 University partners, has an ambitious goal: creating Generative Pretrained Transformers (GPT) aka Large Robot Action Models for robotics: https://robotics-transformer-x.github.io/Collaborators are sharing terabytes of video and robot command data based on human-teleoperated demonstrations of many different robots performing many different tasks in many different environments. Collecting and managing all of this data is currently cumbersome. We have been asked to develop a cloud-based system to streamline data collection and management based on FogROS2, our open-source cloud robotics platform: https://berkeleyautomation.github.io/FogROS2/aboutWe’ll present results in progress. We welcome input and suggestions!

Bio:
Ken Goldberg (IEEE Fellow, 2005) is William S. Floyd Distinguished Chair of Engineering at UC Berkeley and Chief Scientist of Ambi Robotics and Jacobi Robotics. Ken leads research in robotics and automation: grasping, manipulation, and learning for applications in warehouses, industry, homes, agriculture, and robot-assisted surgery. He is Professor of IEOR with appointments in EECS and Art Practice. Ken is Chair of the Berkeley AI Research (BAIR) Steering Committee (60 faculty) and is co-founder and Editor-in-Chief emeritus of the IEEE Transactions on Automation Science and Engineering (T-ASE). He has published ten US patents and over 400 refereed papers. He has presented over 600 invited lectures to academic and corporate
audiences. http://goldberg.berkeley.edu