Research
I'm interested in machine learning and computer vision applied to robotics. The focus of my research is to develop methods leveraging offline data that distill perceptual and behavioral priors into embodied agents, enabling them to learn robust policies from minimal environment interactions.
|
|
Hearing Touch: Audio-Visual Pretraining for Contact-Rich Manipulation
Jared Mejia, Victoria Dean, Tess Hellebrekers, Abhinav Gupta
IEEE International Conference on Robotics and Automation (ICRA), 2024
2024 ICRA Best Paper Award in Robot Manipulation Finalist
project page |
abstract
Although pre-training on a large amount of data is beneficial for robot learning, current paradigms only perform large-scale pretraining for visual representations, whereas representations for other modalities are trained from scratch. In contrast to the abundance of visual data, it is unclear what relevant internet-scale data may be used for pretraining other modalities such as tactile sensing. Such pretraining becomes increasingly crucial in the low-data regimes common in robotics applications. In this paper, we address this gap by using contact microphones as an alternative tactile sensor. Our key insight is that contact microphones capture inherently audio-based information, allowing us to leverage large-scale audio-visual pretraining to obtain representations that boost the performance of robotic manipulation. To the best of our knowledge, our method is the first approach leveraging \emph{large-scale multisensory pre-training} for robotic manipulation.
|
|
World Models for Multi-task Robotic Pretraining
Jared Mejia, Mohan Kumar
CMU 10-707: Advanced Deep Learning, 2023
pdf
|
|
DaDRA: A Python Library for Data-Driven Reachability Analysis
Jared Mejia, Alex Devonport, Murat Arcak
arXiv, 2021
arXiv | code
|
|
Investigating Neural Network Architectures, Techniques, and Datasets for Autonomous Navigation in Simulation
Oliver Chang, Chrstiana Marchese, Jared Mejia, Anthony Clark
IEEE Symposium Series on Computational Intelligence (SSCI), 2021
pdf
|
|
Teaching Assistant
(10-417/617) Intermediate Deep Learning - Professors Ruslan Salakhutdinov and Yuanzhi Li
|
|
Teaching Assistant
(CSCI158) Machine Learning - Professor David Kauchak
(CSCI101) Introduction to Langauges and Theory of Computation - Professor Kim Bruce
(CSCI062) Data Structures and Advanced Programming - Professors Anthony Clark and David Kauchak
(CSCI051) Introduction to Computer Science - Professors Tzu-Yi Chen and Eleanor Birrell
(ECON052) Principles of Microeconomics - Profesor Malte Dolde
|
Website template from here.
|
|