Chelsea Finn: Teaching robots to learn

Berkeley Engineering 150Chelsea FinnFor children, playing with toys isn’t just fun — it’s a key way to learn about the world around them. As it turns out, robots can also learn through play, as Chelsea Finn (Ph.D.’18 EECS) is showing through her groundbreaking work in deep reinforcement learning. A post-doctoral researcher at the Berkeley Artificial Intelligence Research Lab (BAIR) and a scientist at Google Brain, Finn is developing algorithms that enable robots to learn on their own, as children do, by building on previous explorations and observations.

At BAIR, Finn has robots tackling a wide variety of tasks in real-world settings, in hopes that robots can eventually acquire common sense to be used in unpredictable situations. The robots are learning to manipulate, rearrange and grasp objects, mastering challenges like a wooden shape-sorting toy, through a process of trial-and-error instead of programming.

A recent graduate, Finn is already drawing accolades for her research, including her selection for MIT Technology Review’s 2018 list of “35 Innovators Under 35.”

Montage of images from Berkeley Engineering history

Milestones of engineering

Want to learn more about where Berkeley Engineers have been, and what they've accomplished? Visit our timeline of college history.