Andreea Bobu

Berkeley Artificial Intelligence Research
Electrical Engineering and Computer Science
University of California Berkeley
8043-5 Berkeley Way West, 2121 Berkeley Way, Berkeley, CA 94704

I am on the faculty job market in Fall 2022.

I am a Ph.D. candidate at UC Berkeley in EECS, where I am advised by Anca Dragan in the InterACT Lab. My Ph.D. is supported by the Apple AI/ML Fellowship. I previously received a B.S. in Computer Science and Engineering at MIT in 2017.

I work at the intersection of robotics, mathematical human modeling, and deep learning. In my research, I study algorithmic human-robot interaction, with a focus on how robots and humans can efficiently arrive at shared representations of their tasks for more seamless and reliable interaction. I ground my work in experiments with robotic systems like assistive robot arms and in user studies with real human participants.


Dec 9, 2022

Giving an invited talk at the Robotics Colloquium at UW.

Dec 5, 2022

Giving an invited talk at the New Trends in Aerospace Seminar Series at MIT.

Dec 2, 2022

New paper accepted to HRI, "SIRL: Similarity-based Implicit Representation Learning", where we enable robots to learn salient feature representations by asking humans to gauge how similar different behaviors are.

Dec 1, 2022

I gave an invited talk at the Robotics Seminar at Cornell.

Nov 28, 2022

I was invited to speak at University of Utah's CS 6960: Human-AI Alignment graduate course.

Nov 16, 2022

I gave an invited talk in the Robot Autonomy and Interactive Learning (RAIL) Lab at Georgia Tech.

Oct 21, 2022

I gave an invited talk at the Illinois Robotics Seminar at UIUC.

Oct 14, 2022

I gave an invited talk in the Intelligent and Interactive Autonomous Systems Group (ILIAD) Group at Stanford.

Aug 1, 2022

I am grateful to have been selected for the Rising Star in EECS Academic Career Workshop!

Jul 23, 2022

I gave an invited talk at the Workshop on Complex Feedback in Online Learning at ICML.

Jun 29, 2022

New paper accepted to IROS, "Teaching Robots to Span the Space of Functional Expressive Motion", where we enable people to efficiently teach robots expressive motions during task execution.

Jun 14, 2022

New paper accepted to Robotics and Automation Letters, "Learning Perceptual Concepts by Bootstrapping from Human Queries". In this work, we ask for human input to learn a low-dimensional variant of the perceptual concept, then use it to generate a larger data set for learning the concept in the high-dimensional space.

May 25, 2022

I gave an invited talk at Apple's AI/ML seminar.

May 16, 2022
May 13, 2022