Title: Watch, Understand, Do

Speaker: Dr. Jennifer Barry (RAI)

Location: Nvidia Auditorium (link)

Attendance Link: https://tinyurl.com/robosem-win-26

Time: Friday Mar. 6th, 3:00-4:00PM

Abstract: One of the biggest questions in robotics today is how to simply and easily teach robots new tasks.  In this talk, we explore whether we can teach robots the same way we teach humans: by having the robots watch humans execute the tasks.  We show that despite the huge sensing and morphology gap between robots and humans, robots can understand skill sequencing, object detection, and task geometry just from watching human demonstrations.

Bio: Dr. Jennifer Barry is a Roboticist at the Robotics and Artificial Intelligence (RAI) Institute where she leads a team focused on increasing robot autonomy by reducing the need to manually program robots.  Prior to joining RAI, she worked at Boston Dynamics and Rethink Robotics.  Dr. Barry received her Ph.D. from the Learning and Intelligent Systems group at MIT in 2013.

We still have some openings on her schedule, if you are a professor, postdoc or phd student interested in meeting with her, please sign up here: https://docs.google.com/spreadsheets/d/1WNxX4vwAw0poVJ234dcZmwgKUabMQTtrnV9FtD4u76Q/edit?usp=sharing

This talk will be in-person only, no recordings will be available.

If you’re interested, you’re welcome to join Jenny for lunch at Blend Cafe at 12 PM. Please let Dian (dianwang@stanford.edu) know if you plan to join.