Ajou University repository

Hierarchical Reinforcement Learning using Gaussian Random Trajectory Generation in Autonomous Furniture Assembly
  • Yun, Won Joon ;
  • Mohaisen, David ;
  • Jung, Soyi ;
  • Kim, Jong Kook ;
  • Kim, Joongheon
Citations

SCOPUS

0

Citation Export

Publication Year
2022-10-17
Journal
International Conference on Information and Knowledge Management, Proceedings
Publisher
Association for Computing Machinery
Citation
International Conference on Information and Knowledge Management, Proceedings, pp.3624-3633
Keyword
assembly controlhierarchical reinforcement learningreinforcement learningrobotics
Mesh Keyword
Assembly controlsAssembly problemsGaussiansHierarchical reinforcement learningHigh level policiesHuman likeManipulation taskReinforcement learning methodReinforcement learningsTrajectory generation
All Science Classification Codes (ASJC)
Business, Management and Accounting (all)Decision Sciences (all)
Abstract
In this paper, we propose a Gaussian Random Trajectory guided Hierarchical Reinforcement Learning (GRT-HL) method for autonomous furniture assembly. The furniture assembly problem is formulated as a comprehensive human-like long-horizon manipulation task that requires a long-term planning and a sophisticated control. Our proposed model, GRT-HL, draws inspirations from the semi-supervised adversarial autoencoders, and learns latent representations of the position trajectories of the end-effector. The high-level policy generates an optimal trajectory for furniture assembly, considering the structural limitations of the robotic agents. Given the trajectory drawn from the high-level policy, the low-level policy makes a plan and controls the end-effector. We first evaluate the performance of GRT-HL compared to the state-of-the-art reinforcement learning methods in furniture assembly tasks. We demonstrate that GRT-HL successfully solves the long-horizon problem with extremely sparse rewards by generating the trajectory for planning.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36845
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85140836688&origin=inward
DOI
https://doi.org/10.1145/3511808.3557078
Type
Conference
Funding
This work was supported by Samsung Electronics (IO201208-07855-01) and also by MSIT, Korea, under ITRC (IITP-2022-2017-0-01637) supervised by IITP. The authors thank to Mr. MyungJae Shin for his contribution on research initiation, during his master study under the guidance of Prof. Joongheon Kim. Soyi Jung, Jong-Kook Kim, and Joongheon Kim are the corresponding authors.
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Jung, Soyi Image
Jung, Soyi정소이
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.