|
I am a Masters student in the School of Interactive Computing at Georgia Tech where I am getting my Masters in Computer Science with a specialization in computational perception and robotics. I work in the Robotic Learning and Reasoning Lab (RL2) and my thesis advisor is Danfei Xu . My research lies at the intersection of Robotics and Machine Learning I received my BS in EECS and Mechanical Engineering from UC Berkeley (2017-2021). At Berkeley I worked on computer vision for stem cell tracking and segmentation in the Sohn Microfluidics Laboratory under Lydia Sohn. I have also spent time as a Computer Vision intern at the Schlumberger-Doll Research Center (2021) where I worked on anomoly detection and transfer learning under Suraj Kiran and Tianxiang Su. And time as a Machine Learning Scientist at Symbotic (2023) where I worked on failure prediction under Shahab Ilbeigi and Daniel Burns. |
|
|
My research goal is to improve the quality of life for all people by enabling embodied AI agents to safely and autonomously opperate in our human-centric world. To this end, I work on deep learning for robotics with a focuses on offline policy generation and data driven approaches to human robot interaction. I am interested in learning from large-scale, unstructed, offline datasets as these are the most abundant and accessible sources of data. Developing algorithims that learn effectively from these datasets is a key step towards deployable robotic agents. I am also interested in how we can leverage humans to help robots gather data, learn new skills, and contend with uncertainty. Algorithms that allow for safe and effective human robot collaboration even in the face of out of distribution data are key to the success of future robotic agents.
|
|
Teaching Assistant:
|
|
|
 
|
Matthew Bronars, Shuo Cheng, Danfei Xu Preprint (under review for RA-L 2024) Keywords: Human Robot Interaction, Diffusion Models,Imitation Learning TL;DR: By leveraging diffusion model guidance, Legibility Diffuser is able to clone the most legible trajectories from a dataset of multi-modal, multi-task human demonstrations. |
|
|
Sachit Kuhar, Shuo Cheng, Shivang Chopra, Matthew Bronars, Danfei Xu Conference on Robot Learning (CoRL 2023) Keywords: Imitation Learning, Preference Learning, Manipulation TL;DR: Learning to Discern (L2D) is an imitation learning framework for learning from suboptimal demonstrations. By training a quality evaluator in a learned latent space, L2D can generalize to new demonstrators given only a small subset of labeled data. |
|
Matthew Bronars, Danfei Xu ICML Workshop on Interactive Learning from Human Feedback (2023) Keywords: Generative Modeling, Human Robot Interaction, Learning from Demonstrations TL;DR: We introduce Generative Legible Motion Models (GLMM), a framework that utilizes conditional generative models to learn legible trajectories from human demonstrations. |
|
Matthew Bronars, Kristen Cotner, Lydia Sohn UC Berkeley Undergraduate Research Fair, 2021 Keywords: Computer Vision, Image Segmentation, Tracking TL;DR: Trained a U-Net CNN to segment stem cells and wrote a python script to track them through the timelapse. |
|
Matthew Bronars, Suraj Raman, Tianxiang Su Schlumberger-Doll Research, 2021 Keywords: Computer Vision, Transfer Learning TL;DR: Designed transfer learning pipeline for implementing cable tracking and damage detection on multiple well sites. *US Patent Pending |
|
Matthew Bronars, Josiah Polhemous UC Berkeley, 2021 Keywords: Mechatronics TL;DR: Designed, built, and programmed a pasta making machine for automated food production. |