Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization

Min Sung Ahn; Hosik Chae; Colin Togashi; Dennis Hong; Joohyung Kim; Sungjoon Choi

doi:10.1109/UR55393.2022.9826279

Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization

Min Sung Ahn, Hosik Chae, Colin Togashi, Dennis Hong, Joohyung Kim, Sungjoon Choi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

During loco-manipulation, instabilities to the robot's base can be introduced by the manipulator's motions. Trajectories that are generated on-the-fly may jeopardize the stability and safety of the robot and its surroundings. This work proposes a self-supervised learning-based pipeline to keep a robot stable while executing a given trajectory. Empirical results show that the desired objective can be achieved with the proposed pipeline. Experiments are done in simulation and on hardware on a unique multi-modal, manipulation-capable legged robot, and its scalability is tested on a conventional manipulator.

Original language	English
Title of host publication	2022 19th International Conference on Ubiquitous Robots, UR 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	129-136
Number of pages	8
ISBN (Electronic)	9781665482530
DOIs	https://doi.org/10.1109/UR55393.2022.9826279
Publication status	Published - 2022
Event	19th International Conference on Ubiquitous Robots, UR 2022 - Jeju, Korea, Republic of Duration: 2022 Jul 4 → 2022 Jul 6

Publication series

Name	2022 19th International Conference on Ubiquitous Robots, UR 2022

Conference

Conference	19th International Conference on Ubiquitous Robots, UR 2022
Country/Territory	Korea, Republic of
City	Jeju
Period	22/7/4 → 22/7/6

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

ASJC Scopus subject areas

Artificial Intelligence
Hardware and Architecture
Mechanical Engineering
Control and Optimization

Access to Document

10.1109/UR55393.2022.9826279

Cite this

Ahn, M. S., Chae, H., Togashi, C., Hong, D., Kim, J., & Choi, S. (2022). Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization. In 2022 19th International Conference on Ubiquitous Robots, UR 2022 (pp. 129-136). (2022 19th International Conference on Ubiquitous Robots, UR 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UR55393.2022.9826279

Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization. / Ahn, Min Sung; Chae, Hosik; Togashi, Colin et al.
2022 19th International Conference on Ubiquitous Robots, UR 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 129-136 (2022 19th International Conference on Ubiquitous Robots, UR 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ahn, MS, Chae, H, Togashi, C, Hong, D, Kim, J & Choi, S 2022, Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization. in 2022 19th International Conference on Ubiquitous Robots, UR 2022. 2022 19th International Conference on Ubiquitous Robots, UR 2022, Institute of Electrical and Electronics Engineers Inc., pp. 129-136, 19th International Conference on Ubiquitous Robots, UR 2022, Jeju, Korea, Republic of, 22/7/4. https://doi.org/10.1109/UR55393.2022.9826279

@inproceedings{d08295345f6f45d3a0b489df587d0c96,

title = "Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization",

abstract = "During loco-manipulation, instabilities to the robot's base can be introduced by the manipulator's motions. Trajectories that are generated on-the-fly may jeopardize the stability and safety of the robot and its surroundings. This work proposes a self-supervised learning-based pipeline to keep a robot stable while executing a given trajectory. Empirical results show that the desired objective can be achieved with the proposed pipeline. Experiments are done in simulation and on hardware on a unique multi-modal, manipulation-capable legged robot, and its scalability is tested on a conventional manipulator.",

author = "Ahn, {Min Sung} and Hosik Chae and Colin Togashi and Dennis Hong and Joohyung Kim and Sungjoon Choi",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th International Conference on Ubiquitous Robots, UR 2022 ; Conference date: 04-07-2022 Through 06-07-2022",

year = "2022",

doi = "10.1109/UR55393.2022.9826279",

language = "English",

series = "2022 19th International Conference on Ubiquitous Robots, UR 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "129--136",

booktitle = "2022 19th International Conference on Ubiquitous Robots, UR 2022",

}

TY - GEN

T1 - Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization

AU - Ahn, Min Sung

AU - Chae, Hosik

AU - Togashi, Colin

AU - Hong, Dennis

AU - Kim, Joohyung

AU - Choi, Sungjoon

PY - 2022

Y1 - 2022

N2 - During loco-manipulation, instabilities to the robot's base can be introduced by the manipulator's motions. Trajectories that are generated on-the-fly may jeopardize the stability and safety of the robot and its surroundings. This work proposes a self-supervised learning-based pipeline to keep a robot stable while executing a given trajectory. Empirical results show that the desired objective can be achieved with the proposed pipeline. Experiments are done in simulation and on hardware on a unique multi-modal, manipulation-capable legged robot, and its scalability is tested on a conventional manipulator.

AB - During loco-manipulation, instabilities to the robot's base can be introduced by the manipulator's motions. Trajectories that are generated on-the-fly may jeopardize the stability and safety of the robot and its surroundings. This work proposes a self-supervised learning-based pipeline to keep a robot stable while executing a given trajectory. Empirical results show that the desired objective can be achieved with the proposed pipeline. Experiments are done in simulation and on hardware on a unique multi-modal, manipulation-capable legged robot, and its scalability is tested on a conventional manipulator.

UR - http://www.scopus.com/inward/record.url?scp=85136128521&partnerID=8YFLogxK

U2 - 10.1109/UR55393.2022.9826279

DO - 10.1109/UR55393.2022.9826279

M3 - Conference contribution

AN - SCOPUS:85136128521

T3 - 2022 19th International Conference on Ubiquitous Robots, UR 2022

SP - 129

EP - 136

BT - 2022 19th International Conference on Ubiquitous Robots, UR 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International Conference on Ubiquitous Robots, UR 2022

Y2 - 4 July 2022 through 6 July 2022

ER -

Learning-based Motion Stabilizer Leveraging Offline Temporal Optimization

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this