Generalization in embodied intelligence, such as in robotics, requires interactive learning across families of tasks is essential for discovering efficient representation and inference mechanisms. Concurrent systems need a lot of hand-holding to even learn a single cognitive concept or a dexterous skill, say “open a door”, let alone generalizing to new windows and cupboards! This is far from our vision of everyday robots! would require a broader concept of generalization and continual update of representations.
My research vision is to build the Algorithmic Foundations for Generalizable Autonomy, which enables robots to acquire skills in cognitive planning & dexterous interaction, and, in turn, seamlessly interact & collaborate with humans. This study of the science of embodied AI opens three key questions: (a) Representational biases & Causal inference for interactive decision making, (b) Perceptual representations learned by and for interaction, (c) Systems and abstractions for scalable learning.

This talk will focus on decision-making uncovering the many facets of inductive biases in off-policy reinforcement learning in robotics. I will introduce C-Learning to trade off-speed and reliability instead of vanilla Q-Learning. Then I will talk about the discovery of latent causal structure to improve sample efficiency. Moving on from skills, we will describe task graphs for hierarchically structured tasks for manipulation. I will present how to scale structured learning in robot manipulation with Roboturk, and finally, prescribe a practical algorithm for deployment with safety constraints. Taking a step back, I will end with notions of structure in Embodied AI for both perception and decision making.

Biosketch:

Animesh Garg is a CIFAR Chair Assistant Professor of Computer Science at the University of Toronto, a Faculty Member at the Vector Institute and the Robotics Institute. Animesh earned a Ph.D. from UC Berkeley and was a postdoc at the Stanford AI Lab. His work aims to build Generalizable Autonomy which involves a confluence of representations and algorithms for reinforcement learning, control, and perception. In particular, he currently studies three aspects: learning structured inductive biases in Sequential decision making, using data-driven causal discovery, and transfer to real robots: all in the purview of embodied systems.

His work has earned many best-paper recognitions at top-tier venues in Machine Learning and Robotics such as ICRA, IROS, RSS, Hamlyn Symposium, Workshops at NeurIPS, ICML.

Homepage: http://animesh.garg.tech/