Pratik Chaudhari

I am an Assistant Professor in the Electrical and Systems Engineering department and the GRASP Robotics Laboratory. I hold a secondary appointment in the Computer and Information Sciences department and am a member of the Applied Mathematics (AMCS) and Penn Institute for Computational Science (PICS) graduate groups.

Previously, I held a joint position as a Senior Applied Scientist at Amazon Web Services and a post-doctoral researcher at the California Institute of Technology in the Computing and Mathematical Sciences department.

I defended my PhD thesis in the Computer Science department at University of California, Los Angeles in 2018 where I worked with Stefano Soatto in the UCLA Vision Lab. I have an Engineer's (2014) and Master's (2012) degrees in Aeronautics & Astronautics from the Massachusetts Institute of Technology where I worked with Emilio Frazzoli at the Laboratory of Information and Decision Systems (LIDS). I was in the Aerospace Engineering department at IIT Bombay for my undergraduate studies until 2010.

I have worked extensively on self-driving cars in the areas of computer vision, planning and control at nuTonomy Inc (now Aptiv).

Research Interests: I am interested in machine learning, in particular deep neural networks, robotics and computer vision. My ambition is to bring the dream of cybernetics closer to reality and enable Embodied Intelligence. The ability to perceive and control the environment, with cognition acting as the glue in between, is the hallmark of intelligent beings; the interplay between these three is the core of my research. In my group, we perform highly multi-disciplinary research. We study ideas from statistical physics, optimization, computer vision, control theory and motion-planning. The work can be theoretical, empirical and or really anything in between: everyone from hands-on roboticists, to engineers, computer scientists and mathematicians are welcome.

NeurIPS 2020 Workshop on Deep Learning through Information Geometry: We organized a workshop recently to brainstorm how ideas in information geometry and information theory inform questions of optimization and generalization in deep learning. You can find the recorded keynote talks and accepted submissions at here.

New Students: I am always looking for exciting researchers who can be a part of my research group. I would love to hear from you. These videos give a flavor of some recent results from our group.

If you are an existing student at Penn, send me an email and we can set up a time to talk. If you are not at Penn, please use this form to contact me about open positions.

Brief Overview

Understanding Deep Learning

Learning with few labeled data

Resume CV Research Statement


Contact

pratikac at seas dot upenn dot edu

Levine Hall 470

GitHub Twitter


Research Group

Doctoral students

Yansong Gao (AMCS)

Jialin Mao (AMCS)

Rahul Ramesh (CIS)

Rubing Yang (AMCS)

Undergraduate and Master's students

Sebastian Peralta (Physics/ESE BS, Robo MS)

Megharjun Nanda (Robo MS)

Alumni

Xiaoyi (Sherry) Chen (EE/MNT BS, CIS MS, now at nuro.ai)

Ashish Mehta (Robo MS, now at Qualcomm)

Christopher Hsu (ESE MS, now at ARL)

Wenbo Zhang (Robotics MS, now at grayscale.ai)


Teaching

ESE 546 Principles of Deep Learning (Fall 2020)
[Syllabus] [Notes: Fall 2020]

ESE 650 Learning in Robotics (Spring 2021)
[Syllabus] [Notes: Spring 2020]


Publications

See Google Scholar for the latest list of publications and citations.

Theses

A picture of the energy landscape of deep neural networks
PhD, Computer Science, University of California, Los Angeles, 2018

Algorithms for autonomous urban navigation with formal specifications
Engineer, Aeronautics-Astronautics, Massachusetts Institute of Technology, 2014

Incremental sampling based algorithms for state estimation
SM, Aeronautics-Astronautics, Massachusetts Institute of Technology, 2012