I am a Assistant Professor of Computer Science at University of Toronto and a Faculty Member at the Vector Institute. I lead the Toronto People, AI and Robotics (PAIR) research group.

I am affiliated with Mechanical and Industrial Engineering (courtesy) and Toronto Robotics Institute.
I also share time as a senior research scientist at Nvidia in ML and Robotics.

Prior to this, I was a postdoc at Stanford AI Lab working with Fei-Fei Li and Silvio Savarese. I received MS in Computer Science and Ph.D. in Operations Research from the UC, Berkeley in 2016. I was advised by Ken Goldberg in the Automation Lab as a part of the Berkeley AI Research Lab (BAIR). I also worked closely with Pieter Abbeel, Alper Atamturk and UCSF Radiation Oncology.

My current research focuses on machine learning algorithms for perception and control in robotics. I develop algorithmic methods to enable efficient robot learning for long-term sequential tasks through Generalizable Autonomy. The principal focus of my research is to understand representations and algorithms to enable the efficiency and generality of learning for interaction in autonomous agents.

Research Interests: Robotics, Reinforcement Learning, Computer Vision and Optimal Control. I work on applications of autonomous manipulation in surgical, personal and warehouse robotics.

Contact me: garg@cs·stanford·edu
Find me on:   ·     ·     ·  

Prospective Applicants

🌟 I am accepting new students at all levels. Thanks for your interest in my group. However, kindly do not contact me directly with regard to MS or PhD admissions. Please read this before contacting me and apply accordingly:

Recent News

Recent Research

Rethinking Generalization in Robot Learning
At Stanford, I am leading the effort in Rethinking Generalization in Robot Learning. It is a multi-proged effort in developing hierarcical Deep RL abstractions along with learning from video demonstrations. Read More
Learning & Automation in Surgical Subtasks
We are working towards surgical sub-task automation and exploring a data driven approach for reduction in training effort with unsupervised task structure learning. Read More

Coverage in Media/Press

  • TechXplore
  • TechXplore
  • TechXplore
  • IEEE Spectrum
  • IEEE Spectrum
  • IEEE Spectrum
  • New York Times
  • Med Gadget
  • 3D Printing World
  • Phys.Org

Locations of visitors to this page