February 15, 2023 - Faculty Candidate Seminar - Long-Term Autonomy in Dynamic Real-World Environments

Dr. Ali Ayub
Pennsylvania State University
 

Wednesday, February 15, 2023 at 2:00 pm
Room EV003.309

Abstract

For long-term deployment in real-world environments, autonomous systems need to continually learn new concepts to adapt to their ever-changing environments. However, continual learning in real-world environments poses various challenges. First, machine learning (ML) models for continual learning can forget previously learned knowledge when learning new information, a problem called catastrophic forgetting. Second, the only source of supervision for autonomous systems in everyday environments is their non-expert users, who might provide limited and imperfect information to the system. In this talk, I will discuss how we can draw inspiration from theories of learning in cognitive science to develop ML models that can continually learn from limited data while mitigating catastrophic forgetting. I will then present how these models can be integrated into complete systems that can allow autonomous robots to continually adapt while performing assistive tasks in real-world environments. Finally, I will present how continual learning systems can interact with and learn from non-expert human users. Specifically, I will discuss some of the key factors observed in a long-term human-computer interaction (HCI) study that should be considered when developing continual learning systems for real-world applications. Finally, I will discuss plans for my future research in the near and long term. 

Biography

Dr. Ali Ayub is a Postdoctoral fellow at the University of Waterloo in the Department of Electrical and Computer Engineering, advised by Professor Kerstin Dautenhahn and Professor Chrystopher Nehaniv. He studies long-term autonomy for autonomous systems that continually learn personalized knowledge from people to assist them in their daily environments. His research combines methods from machine learning (ML) and human-computer interaction (HCI) to develop theoretical frameworks that are integrated into practical systems for human-computer interaction in domains like assistive robotic arms and mobile manipulators. Prior to his postdoc, he earned his Ph.D. and MS from The Pennsylvania State University in Electrical Engineering in 2021 and 2017, respectively. He is a recipient of Penn State’s Robert W. Graham Fellowship, the United States Educational Foundation’s Global UGRAD Fellowship, and Google’s diversity, equity, and inclusion (DEI) award. He has also been selected as a Pioneer at the ACM/IEEE International Conference on Human-Robot Interaction (HRI).