Robot teaching and learning with everyday users in mind
ECE 595 Seminar Series
February 17, 2025
11:00 AM - 12:15 PM
Robot teaching and learning with everyday users in mind
Speaker: Maram Sakr, University of British Columbia & Monash University
Abstract: Robots have the potential to enhance our quality of life, not by replacing humans, but by collaborating with them to achieve shared goals. Achieving seamless interaction between humans and robots is critical to realizing this vision. Learning from Demonstration (LfD) allows robots to learn new tasks by observing user demonstrations, enabling everyday users to teach robots without programming expertise. However, the quality and quantity of these demonstrations directly influence the robot's ability to learn and generalize effectively. While everyday users are skilled in their tasks, they often lack the robotics expertise needed to provide high-quality demonstrations, posing challenges for traditional LfD techniques that rely on expert data.
My research addresses this challenge by 1) understanding the robot’s learning needs to ensure demonstrations meet those needs, 2) training and guiding users to provide informative demonstrations—particularly in uncertain areas of the task space—and 3) designing intuitive interfaces that facilitate seamless collaboration between humans and robots. In this talk, I will demonstrate how identifying a robot’s learning needs and guiding users can significantly enhance robot learning. I will also explore how these findings can inform the design of innovative human-robot interfaces, paving the way for seamless interactions between robots and everyday users.
Speaker bio: Maram Sakr is a PhD candidate in the joint program between the Department of Mechanical Engineering at the University of British Columbia and the Department of Electrical and Computer Engineering at Monash University, under the guidance of Professors Elizabeth Croft, Dana Kulić, and Mike Van der Loos. She was a visiting scholar at the Intuitive Computing Lab at Johns Hopkins University. Sakr is an experimental roboticist working at the intersection of robotics, machine learning, and human-robot interaction. Her research focuses on enabling everyday users to intuitively and effectively collaborate with and teach robots. She holds a master’s degree from Simon Fraser University, Canada, and a bachelor’s degree from Mansoura University, Egypt. Sakr is the recipient of the prestigious Alexander Graham Bell Canada Graduate Scholarship from the Natural Sciences and Engineering Research Council of Canada (NSERC) and was the top ranked student in the Computing Science Committee nationwide. She was selected as an HRI Pioneer in 2022 and an RSS Pioneer in 2023.
Faculty host: Miloš Žefran
Date posted
Feb 17, 2025
Date updated
Feb 17, 2025