PAIR
People, AI, & Robots. Research Group

PAIR Lab is directed by Animesh Garg in the Department of Computer Science at the University of Toronto.
Our 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. We focus on understanding structured inductive biases and causality on a quest for general-purpose embodied intelligence that learns from imprecise information and achieves flexibility & efficiency of human reasoning.



Research: Our current research focuses on machine learning algorithms for perception and control in robotics. The principal focus of this research is to understand representations and algorithms to enable the efficiency and generality of learning for interaction in autonomous agents. We work on challenging open problems at the intersection of computer vision, machine learning, and robotics. We develop algorithms and systems that unify reinforcement learning, control theoretic modeling, causality, and 2D/3D visual scene understanding to teach robots to perceive and to interact with the physical world. Read more
Research Interests: Robotics, Reinforcement Learning, Causality, Perception
Current Applications: Mobile-Manipulation in Retail/Warehouse, Personal/Sevice, and Surgical/Medical robotics.
Getting Involved
We are accepting new students at all levels!
Please see openings for details.
Recent News
Feb 28, 2021 | Four papers: LASER, LEAF, Legged Robots, Hand Design accepted at ICRA. |
Jan 18, 2021 |
AAAI-21 New Faculty Highlights speaker. ![]() |
Jan 18, 2021 |
Unsupervised Keypoint Representation accepted in T-PAMI. ![]() |
Jan 12, 2021 | Three papers: CSC, C-Learning, Skill Transfer accepted at ICLR. |
Dec 1, 2020 | The paper on DIBS accepted at AAAI 2021. |
Nov 30, 2020 | Area Chair for ICLR’21, ICRA’21, RSS’21, CVPR’21, and ICCV’21. |
Oct 18, 2020 | Co-organizing COSPAR 2021 workshop on Autonomy in Space Science |
Oct 15, 2020 |
1 new paper on Learning based Hybrid control accepted at CoRL 2020! ![]() |
Oct 1, 2020 | Publicity Chair for CoRL’20 and Area Chair for NeurIPS’20 & CoRL’20. |
Sep 25, 2020 |
3 new papers on Causality and Deep Learning accepted at NeurIPS 2020! ![]() |