Article Source

• Towards Generalizable Autonomy

Towards Generalizable Autonomy

• Towards Generalizable Autonomy: Duality of Discovery & Bias
• Animesh Garg of Georgia Tech/NVIDIA
• October 21, 2022

Abstract

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. 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.

About the speaker

Animesh Garg is an Assistant Professor of Computer Science at University of Toronto and a Faculty Member at the Vector Institute. He directs the UofT People, AI and Robotics (PAIR) group. He is affiliated with Mechanical and Industrial Engineering (courtesy) and UofT Robotics Institute and also a Sr. Research Scientist at Nvidia. Learn more on his website: https://animesh.garg.tech/