Muratore, Fabio ; Ramos, Fabio ; Turk, Greg ; Yu, Wenhao ; Gienger, Michael ; Peters, Jan (2022):
Robot Learning From Randomized Simulations: A Review. (Publisher's Version)
In: Frontiers in Robotics and AI, 9, Frontiers, e-ISSN 2296-9144,
DOI: 10.26083/tuprints-00021227,
[Article]
![]() |
Text
frobt-09-799893.pdf Copyright Information: CC BY 4.0 International - Creative Commons, Attribution. Download (1MB) |
Item Type: | Article |
---|---|
Origin: | Secondary publication via sponsored Golden Open Access |
Status: | Publisher's Version |
Title: | Robot Learning From Randomized Simulations: A Review |
Language: | English |
Abstract: | 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. |
Journal or Publication Title: | Frontiers in Robotics and AI |
Volume of the journal: | 9 |
Place of Publication: | Darmstadt |
Publisher: | Frontiers |
Collation: | 19 Seiten |
Classification DDC: | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik |
Divisions: | 20 Department of Computer Science > Intelligent Autonomous Systems |
Date Deposited: | 04 May 2022 13:47 |
Last Modified: | 23 Aug 2022 09:41 |
DOI: | 10.26083/tuprints-00021227 |
Corresponding Links: | |
URN: | urn:nbn:de:tuda-tuprints-212275 |
Additional Information: | Keywords: robotics, simulation, reality gap, simulation optimization bias, reinforcement learning, domain randomization, sim-to-real |
URI: | https://tuprints.ulb.tu-darmstadt.de/id/eprint/21227 |
PPN: | 494561076 |
Export: |
![]() |
View Item |