Robot Learning From Randomized Simulations: A Review

41Citations
Citations of this article
93Readers
Mendeley users who have this article in their library.

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.

Cite

CITATION STYLE

APA

Muratore, F., Ramos, F., Turk, G., Yu, W., Gienger, M., & Peters, J. (2022, April 11). Robot Learning From Randomized Simulations: A Review. Frontiers in Robotics and AI. Frontiers Media S.A. https://doi.org/10.3389/frobt.2022.799893

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free