Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty

Byungchan Kim, Dongseok Ryu, Shin Suk Park, Sungchul Kang

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

Abstract

This paper is a study on an adaptive method for opening a door using a mobile manipulator. In conventional researches on door opening, it has been regarded as a geometry-oriented problem. However, the human does not mind the trajectory but just adapt to the exerting forces, while he/she opens a door. The main idea of this research is that we treat the door opening as a force-oriented problem. We will not assume a door's exact trajectory. Instead of this, only compliance control is executed with a simple command which directs a pulling direction. Finally, the mobile manipulator adapts itself to the door trajectory, with bounded force condition. The main challenge of this research is to find an optimum compliance gain at each configuration of the manipulator, with position error of mobile base. To resolve this problem, we employed an adaptive method based on modern reinforcement learning. Also, we adopt the concept of compliance ellipsoid, which is the graphical representation of a compliance matrix, for the proposed RL algorithm. In this work, we simulated a door opening task, and the simulation results prove that the proposed adaptive strategy was successfully fulfilled the door opening constraints, with permitting large error bound of the mobile base position.

Original languageEnglish
Title of host publication39th International Symposium on Robotics, ISR 2008
Pages142-147
Number of pages6
Publication statusPublished - 2008 Dec 1
Event39th International Symposium on Robotics, ISR 2008 - Seoul, Korea, Republic of
Duration: 2008 Oct 152008 Oct 17

Other

Other39th International Symposium on Robotics, ISR 2008
CountryKorea, Republic of
CitySeoul
Period08/10/1508/10/17

Fingerprint

Reinforcement learning
Manipulators
Trajectories
Compliance control
Uncertainty
Geometry

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Cite this

Kim, B., Ryu, D., Park, S. S., & Kang, S. (2008). Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty. In 39th International Symposium on Robotics, ISR 2008 (pp. 142-147)

Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty. / Kim, Byungchan; Ryu, Dongseok; Park, Shin Suk; Kang, Sungchul.

39th International Symposium on Robotics, ISR 2008. 2008. p. 142-147.

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

Kim, B, Ryu, D, Park, SS & Kang, S 2008, Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty. in 39th International Symposium on Robotics, ISR 2008. pp. 142-147, 39th International Symposium on Robotics, ISR 2008, Seoul, Korea, Republic of, 08/10/15.
Kim B, Ryu D, Park SS, Kang S. Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty. In 39th International Symposium on Robotics, ISR 2008. 2008. p. 142-147
Kim, Byungchan ; Ryu, Dongseok ; Park, Shin Suk ; Kang, Sungchul. / Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty. 39th International Symposium on Robotics, ISR 2008. 2008. pp. 142-147
@inproceedings{6bba7b9410004f03ab0477d4509d78bc,
title = "Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty",
abstract = "This paper is a study on an adaptive method for opening a door using a mobile manipulator. In conventional researches on door opening, it has been regarded as a geometry-oriented problem. However, the human does not mind the trajectory but just adapt to the exerting forces, while he/she opens a door. The main idea of this research is that we treat the door opening as a force-oriented problem. We will not assume a door's exact trajectory. Instead of this, only compliance control is executed with a simple command which directs a pulling direction. Finally, the mobile manipulator adapts itself to the door trajectory, with bounded force condition. The main challenge of this research is to find an optimum compliance gain at each configuration of the manipulator, with position error of mobile base. To resolve this problem, we employed an adaptive method based on modern reinforcement learning. Also, we adopt the concept of compliance ellipsoid, which is the graphical representation of a compliance matrix, for the proposed RL algorithm. In this work, we simulated a door opening task, and the simulation results prove that the proposed adaptive strategy was successfully fulfilled the door opening constraints, with permitting large error bound of the mobile base position.",
author = "Byungchan Kim and Dongseok Ryu and Park, {Shin Suk} and Sungchul Kang",
year = "2008",
month = "12",
day = "1",
language = "English",
pages = "142--147",
booktitle = "39th International Symposium on Robotics, ISR 2008",

}

TY - GEN

T1 - Adaptive reinforcement learning for opening a door using mobile manipulator in geometrical uncertainty

AU - Kim, Byungchan

AU - Ryu, Dongseok

AU - Park, Shin Suk

AU - Kang, Sungchul

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper is a study on an adaptive method for opening a door using a mobile manipulator. In conventional researches on door opening, it has been regarded as a geometry-oriented problem. However, the human does not mind the trajectory but just adapt to the exerting forces, while he/she opens a door. The main idea of this research is that we treat the door opening as a force-oriented problem. We will not assume a door's exact trajectory. Instead of this, only compliance control is executed with a simple command which directs a pulling direction. Finally, the mobile manipulator adapts itself to the door trajectory, with bounded force condition. The main challenge of this research is to find an optimum compliance gain at each configuration of the manipulator, with position error of mobile base. To resolve this problem, we employed an adaptive method based on modern reinforcement learning. Also, we adopt the concept of compliance ellipsoid, which is the graphical representation of a compliance matrix, for the proposed RL algorithm. In this work, we simulated a door opening task, and the simulation results prove that the proposed adaptive strategy was successfully fulfilled the door opening constraints, with permitting large error bound of the mobile base position.

AB - This paper is a study on an adaptive method for opening a door using a mobile manipulator. In conventional researches on door opening, it has been regarded as a geometry-oriented problem. However, the human does not mind the trajectory but just adapt to the exerting forces, while he/she opens a door. The main idea of this research is that we treat the door opening as a force-oriented problem. We will not assume a door's exact trajectory. Instead of this, only compliance control is executed with a simple command which directs a pulling direction. Finally, the mobile manipulator adapts itself to the door trajectory, with bounded force condition. The main challenge of this research is to find an optimum compliance gain at each configuration of the manipulator, with position error of mobile base. To resolve this problem, we employed an adaptive method based on modern reinforcement learning. Also, we adopt the concept of compliance ellipsoid, which is the graphical representation of a compliance matrix, for the proposed RL algorithm. In this work, we simulated a door opening task, and the simulation results prove that the proposed adaptive strategy was successfully fulfilled the door opening constraints, with permitting large error bound of the mobile base position.

UR - http://www.scopus.com/inward/record.url?scp=84876774345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876774345&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84876774345

SP - 142

EP - 147

BT - 39th International Symposium on Robotics, ISR 2008

ER -