About Me

I am a postdoctoral researcher and CI Fellow at UC Berkeley, working with Professor Ken Goldberg in the AUTOLAB. Previously, I was a PhD student in Control and Dynamical Systems at Caltech, where I was fortunate to be advised by Professors Yisong Yue and Joel W. Burdick. My research focuses on learning from human feedback, with applications to robot manipulation and human-robot interaction. In addition, my interests include creating intelligent assistive devices, reinforcement learning, sequential decision-making, and applications of machine learning to healthcare. Outside of research, my other goals include positively impacting people’s lives through teaching and outreach.

Publications

PhD Dissertation:

Online Learning from Human Feedback with Applications to Exoskeleton Gait Optimization
Ellen Novoseller
CaltechTHESIS repository, 2020
PDF

Pre-Prints:

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning
Ryan Hoque, Ashwin Balakrishna, Carl Putterman, Michael Luo, Daniel S. Brown, Daniel Seita, Brijen Thananjeyan, Ellen Novoseller, Ken Goldberg
ArXiv Preprint, 2021
PDF

Conference Publications:

ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes
Kejun Li, Maegan Tucker, Erdem Bıyık, Ellen Novoseller, Joel W. Burdick, Yanan Sui, Dorsa Sadigh, Yisong Yue, and Aaron D. Ames
IEEE Conference on Robotics and Automation (ICRA), 2021
PDF     Code     Website

Human Preference-Based Learning for High-Dimensional Optimization of Exoskeleton Walking Gaits
Maegan Tucker, Myra Cheng, Ellen Novoseller, Richard Cheng, Yisong Yue, Joel W. Burdick, and Aaron D. Ames
IEEE Conference on Intelligent Robots and Systems (IROS), 2020
PDF     Code

Dueling Posterior Sampling for Preference-Based Reinforcement Learning
Ellen Novoseller, Yibing Wei, Yanan Sui, Yisong Yue, and Joel W. Burdick
Conference on Uncertainty in Artificial Intelligence (UAI), 2020
PDF     Code

Preference-Based Learning for Exoskeleton Gait Optimization
Maegan Tucker*, Ellen Novoseller*, Claudia Kann, Yanan Sui, Yisong Yue, Joel W. Burdick, and Aaron D. Ames
IEEE Conference on Robotics and Automation (ICRA), 2020
(*equal contribution)
PDF     Video     Code     Website
Received Best Conference Paper Award and Best Paper in Human-Robot Interaction Award.

Modeling Motor Responses of Paraplegics under Epidural Spinal Cord Stimulation
Ellen Feldman and Joel W. Burdick
IEEE Conference on Neural Engineering (NER), 2017
PDF

Towards Robot-Assisted Vitreoretinal Surgery: Force-Sensing Micro-Forceps Integrated with a Handheld Micromanipulator
Berk Gonenc, Ellen Feldman, Peter Gehlbach, James Handa, Russell H. Taylor, and Iulian Iordachita
IEEE Conference on Robotics and Automation (ICRA), 2014
PDF     Video

Workshop Publications:

Preference-Based Bayesian Optimization in High Dimensions with Human Feedback
Myra Cheng, Ellen Novoseller, Maegan Tucker, Richard Cheng, Joel W. Burdick, and Yisong Yue
Workshop on Real World Experiment Design and Active Learning, International Conference on Machine Learning (ICML), 2020
PDF     Code

Dueling Posterior Sampling for Preference-Based Reinforcement Learning
Ellen Novoseller, Yanan Sui, Yisong Yue, and Joel W. Burdick
Workshop on Real-world Sequential Decision Making: Reinforcement Learning and Beyond, International Conference on Machine Learning (ICML), 2019
PDF