Learning task manifolds for constrained object manipulation

Miao Li, Kenji Tahara, Aude Billard

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Reliable physical interaction is essential for many important challenges in robotic manipulation. In this paper, we consider Constrained Object Manipulations tasks (COM), i.e. tasks for which constraints are imposed on the grasped object rather than on the robot’s configuration. To enable robust physical interaction with the environment, this paper presents a manifold learning approach to encode the COM task as a vector field. This representation enables an intuitive task-consistent adaptation based on an object-level impedance controller. Simulations and experimental evaluations demonstrate the effectiveness of our approach for several typical COM tasks, including dexterous manipulation and contour following.

Original languageEnglish
Pages (from-to)159-174
Number of pages16
JournalAutonomous Robots
Volume42
Issue number1
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Robotics
Robots
Controllers

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Learning task manifolds for constrained object manipulation. / Li, Miao; Tahara, Kenji; Billard, Aude.

In: Autonomous Robots, Vol. 42, No. 1, 01.01.2018, p. 159-174.

Research output: Contribution to journalArticle

Li, Miao ; Tahara, Kenji ; Billard, Aude. / Learning task manifolds for constrained object manipulation. In: Autonomous Robots. 2018 ; Vol. 42, No. 1. pp. 159-174.
@article{75b2fadfa1d347ae9419db2760e2d529,
title = "Learning task manifolds for constrained object manipulation",
abstract = "Reliable physical interaction is essential for many important challenges in robotic manipulation. In this paper, we consider Constrained Object Manipulations tasks (COM), i.e. tasks for which constraints are imposed on the grasped object rather than on the robot’s configuration. To enable robust physical interaction with the environment, this paper presents a manifold learning approach to encode the COM task as a vector field. This representation enables an intuitive task-consistent adaptation based on an object-level impedance controller. Simulations and experimental evaluations demonstrate the effectiveness of our approach for several typical COM tasks, including dexterous manipulation and contour following.",
author = "Miao Li and Kenji Tahara and Aude Billard",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/s10514-017-9643-z",
language = "English",
volume = "42",
pages = "159--174",
journal = "Autonomous Robots",
issn = "0929-5593",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Learning task manifolds for constrained object manipulation

AU - Li, Miao

AU - Tahara, Kenji

AU - Billard, Aude

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Reliable physical interaction is essential for many important challenges in robotic manipulation. In this paper, we consider Constrained Object Manipulations tasks (COM), i.e. tasks for which constraints are imposed on the grasped object rather than on the robot’s configuration. To enable robust physical interaction with the environment, this paper presents a manifold learning approach to encode the COM task as a vector field. This representation enables an intuitive task-consistent adaptation based on an object-level impedance controller. Simulations and experimental evaluations demonstrate the effectiveness of our approach for several typical COM tasks, including dexterous manipulation and contour following.

AB - Reliable physical interaction is essential for many important challenges in robotic manipulation. In this paper, we consider Constrained Object Manipulations tasks (COM), i.e. tasks for which constraints are imposed on the grasped object rather than on the robot’s configuration. To enable robust physical interaction with the environment, this paper presents a manifold learning approach to encode the COM task as a vector field. This representation enables an intuitive task-consistent adaptation based on an object-level impedance controller. Simulations and experimental evaluations demonstrate the effectiveness of our approach for several typical COM tasks, including dexterous manipulation and contour following.

UR - http://www.scopus.com/inward/record.url?scp=85021051527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021051527&partnerID=8YFLogxK

U2 - 10.1007/s10514-017-9643-z

DO - 10.1007/s10514-017-9643-z

M3 - Article

AN - SCOPUS:85021051527

VL - 42

SP - 159

EP - 174

JO - Autonomous Robots

JF - Autonomous Robots

SN - 0929-5593

IS - 1

ER -