Sim-to-real with domain randomization for tumbling robot control

Amalia Schwartzwald, Nikolaos Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Tumbling locomotion allows for small robots to traverse comparatively rough terrain, however, their motion is complex and difficult to control. Existing tumbling robot control methods involve manual control or the assumption of at terrain. Reinforcement learning allows for the exploration and exploitation of diverse environments. By utilizing reinforcement learning with domain randomization, a robust control policy can be learned in simulation then transferred to the real world. In this paper, we demonstrate autonomous setpoint navigation with a tumbling robot prototype on at and non- at terrain. The flexibility of this system improves the viability of nontraditional robots for navigational tasks.

Original languageEnglish (US)
Title of host publication2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4411-4417
Number of pages7
ISBN (Electronic)9781728162126
DOIs
StatePublished - Oct 24 2020
Event2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020 - Las Vegas, United States
Duration: Oct 24 2020Jan 24 2021

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
Country/TerritoryUnited States
CityLas Vegas
Period10/24/201/24/21

Bibliographical note

Funding Information:
VI. ACKNOWLEDGEMENTS The authors would like to thank all the members of the Center for Distributed Robotics Laboratory for their help. This material is based upon work partially supported by the Corn Growers Association of MN, the Minnesota Robotics Institute (MnRI), Honeywell, and the National Science Foundation through grants CNS-1439728, CNS-1531330, and CNS-1939033. USDA/NIFA has also supported this work through the grant 2020-67021-30755. The source code used for URDF generation is provided in a repository at https://github.com/MOLLYBAS/urdf randomizer.

Publisher Copyright:
© 2020 IEEE.

Fingerprint

Dive into the research topics of 'Sim-to-real with domain randomization for tumbling robot control'. Together they form a unique fingerprint.

Cite this