Robot Learning From Randomized Simulations: A Review

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data gener...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in robotics and AI Vol. 9; p. 799893
Main Authors: Muratore, Fabio, Ramos, Fabio, Turk, Greg, Yu, Wenhao, Gienger, Michael, Peters, Jan
Format: Journal Article
Language:English
Published: Switzerland Frontiers Media S.A 11.04.2022
Subjects:
domain randomization
reality gap
reinforcement learning
robotics
Robotics and AI
simulation
simulation optimization bias
simulation optimization bias
reality gap
simulation
robotics
sim-to-real
domain randomization
reinforcement learning
ISSN:2296-9144, 2296-9144
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the “reality gap.” We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named “domain randomization” which is a method for learning from randomized simulations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
ObjectType-Review-3
content type line 23
Konstantinos Chatzilygeroudis, University of Patras, Greece
Reviewed by: Akansel Cosgun, Monash University, Australia
This article was submitted to Robot Learning and Evolution, a section of the journal Frontiers in Robotics and AI
Edited by: Antonio Fernández-Caballero, University of Castilla-La Mancha, Spain
ISSN:2296-9144
2296-9144
DOI:10.3389/frobt.2022.799893