Animesh Garg

I am an Assistant Professor of Computer Science at University of Toronto and a Faculty Member at the Vector Institute. I direct the UofT People, AI and Robotics (PAIR) group. I am affiliated with Mechanical and Industrial Engineering (courtesy) and UofT Robotics Institute. I am also a Sr. Research Scientist at Nvidia.

I earned M.S. in Computer Science and Ph.D. in Operations Research from UC, Berkeley. I worked with Ken Goldberg at Berkeley AI Research (BAIR). I also worked closely with Pieter Abbeel, Alper Atamturk & UCSF Radiation Oncology. I was later a postdoc at Stanford AI Lab with Fei-Fei Li and Silvio Savarese.

My research vision is to build the Algorithmic Foundations for Generalizable Autonomy, that enables robots to acquire skills, at both cognitive & dexterous levels, and to seamlessly interact & collaborate with humans in novel environments. My group focuses on understanding structured inductive biases and causality for decision making. In particular we are looking at multi-modal object-centric and spatiotemporal event representations, self-supervised pre-training for reinforcement learning & control, principle of efficient dexterous skill learning.

I will be a Stephen Fleming Early Career Professor in Computer Science at Georgia Tech in Fall 2023. I will be in Interactive Computing affiliated with Robotics and Machine Learning programs.

Research Interests: Robotics, Reinforcement Learning & Optimal Control, Computer Vision
Current Applications: Mobile-Manipulation in Retail/Warehouse, personal, and surgical robotics. Read more at PAIR Website

Link to (reasonably recent) CV.
Follow me:

Contact me: Georgia Tech: animesh.garg@gatech.edu | UofT: garg@cs.toronto.edu

Potential Applicants

I am accepting new students at all levels at Georgia Tech. Thanks for your interest in my group.
Please apply to either Computer Science, Robotics or Machine Learning Graduate Programs.
However, kindly do not contact me directly with regard to Graduate Application Evaluations. I do not make admissions decisions.
Please see the opportunities on lab website and contact me accordingly.

Recent Talks

The following talks cover the progression of research over in my group since 2019.

Stanford University Robotics Seminar (October 2022)

MIT Deep Learning Seminar highlighting recent work (January 2020)

Topical Workshop Talks

• Robot Learning with Implicit Representations: Perception, Action, and Simulation
  RSS Workshop on Implicit Representations for Robotic Manipulation, (Jun 2022)

• Paving the Path to Robot Autonomy with Simulation
  ICRA Workshop on Releasing Robots into the Wild, (May 2022)

• Structure in Reinforcement Learning for Robotics, Slides PDF
  ICRA Workshop on Behavior Priors in RL, (May 2022)

• Structured Inductive Bias for Imitation from Videos
  CVPR Workshop on Learning from Instructional Videos, (Jun 2020).

• Unsupervised Representations towards Counterfactual Predictions
  CVPR Workshop on Compositionality in Computer Vision, (Jun 2020).