Bernadette Bucher

Bernadette Bucher

About

I am a PhD Student in the GRASP lab at University of Pennsylvania advised by Dr. Kostas Daniilidis. During my PhD studies, I completed a M.S.E. in Robotics from University of Pennsylvania in 2020.

My research interests lie in the intersection of robotics, computer vision, and machine learning. My long term goal is to enable robots to operate in complex and diverse environments designed for humans. To achieve this goal, robots need to both be able to act based on their perception of the environment and take actions in order to improve their perception of the environment. The focus of my research is how to actively choose data to train convolutional neural networks online which I think is key to enabling successful robot autonomy in a varied and changing world.

Prior to starting my PhD, I was a Senior Software Engineer at Lockheed Martin Corporation where I worked from 2014 to 2019. I received an M.A. in Mathematics, M.A. in Economics, and B.S. in Mathematics and Economics from The University of Alabama in 2014.

Publications

Portrait Style Representations

Sadat Shaik*, Bernadette Bucher*, Nephele Agrafiotis, Stephen Phillips, Kostas Daniilidis, William Schmenner.
Learning Portrait Style Representations.
arXiv Preprint, 2020.

arXiv / dataset / labeling tool / bibtex

Adversarial Curiosity

Bernadette Bucher*, Karl Schmeckpeper*, Nikolai Matni, Kostas Daniilidis.
An Adversarial Objective for Scalable Exploration.
arXiv Preprint, 2020.

arXiv / project page / code / bibtex

Action for Better Prediction

Bernadette Bucher*, Karl Schmeckpeper*, Nikolai Matni, Kostas Daniilidis.
Action for Better Prediction.
RSS Workshop on Visual Learning and Reasoning for Robotic Manipulation, 2020.

paper / project page / bibtex

Curiosity Increases Equality

Bernadette Bucher*, Siddharth Singh*, Clélia de Mulatier, Kostas Daniilidis, Vijay Balasubramanian.
Curiosity Increases Equality in Competitive Resource Allocation.
ICLR Workshop on Bridging AI and Cognitive Science, 2020.

paper / bibtex

RoboNet

Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, Chelsea Finn.
RoboNet: Large-Scale Multi-Robot Learning.
Conference on Robot Learning (CoRL), 2019.
NeurIPS Workshop on Deep Reinforcement Learning, 2019.

arXiv / project page / code / bibtex

Perception-Driven Curiosity

Bernadette Bucher, Anton Arapin, Ramanan Sekar, Feifei Duan, Marc Badger, Kostas Daniilidis, Oleh Rybkin.
Perception-Driven Curiosity with Bayesian Surprise.
RSS Workshop on Combining Learning and Reasoning Towards Human-Level Robot Intelligence, 2019.

paper / bibtex

Unsupervised Monocular Depth

Kenneth Chaney*, Bernadette Bucher*, Evangelos Chatzipantazis, Jianbo Shi, Kostas Daniilidis.
Unsupervised Monocular Depth And Latent Structure.
CVPR Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics, 2019.

paper / bibtex