Chelsea Finn

Presentation - Why Robots Should Learn in the Real World

Deploying robots in unstructured environments remains a major challenge. In this talk, I will argue that machine learning can help in two major ways. First, robots deployed in the wild will inevitably face new, unforeseen circumstances that are notably difficult to prepare for a priori. Robots that are capable of learning on the fly during deployment will be much greater equipped to handle such circumstances. To this end, I will present one work that enables robots to learn autonomously from their own experience in the real world, with minimal human intervention or supervision. Second, the real world contains a myriad of objects and interactions that are difficult to simulate. Motivated by this challenge, I will present a simple learning-based approach that enables low-cost bi-manual robots to complete fine-grained motor control tasks. In particular, using only 10 minutes worth of demonstration data per task, the robot can complete tasks such as tearing a piece of tape to put on a box, sliding open a ziploc bag, and putting a shoe on a foot.

Biography

Chelsea Finn is an Assistant Professor in Computer Science and Electrical Engineering at Stanford University, and the William George and Ida Mary Hoover Faculty Fellow. Her research interests lie in the capability of robots and other agents to develop broadly intelligent behavior through learning and interaction. To this end, her work has pioneered end-to-end deep learning methods for vision-based robotic manipulation, meta-learning algorithms for few-shot learning, and approaches for scaling robot learning to broad datasets. Her research has been recognized by awards such as the Sloan Fellowship, the IEEE RAS Early Academic Career Award, and the ACM doctoral dissertation award, and has been covered by various media outlets including the New York Times, Wired, and Bloomberg. Prior to Stanford, she received her Bachelor's degree in Electrical Engineering and Computer Science at MIT and her PhD in Computer Science at UC Berkeley.