Learning Control

Sylvain Calinon; Dongheui Lee

doi:10.1007/978-94-007-6046-2_68

Learning Control

Sylvain Calinon
, Dongheui Lee

Computation, Information and Technology

IDIAP Research Institute
Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

50 Scopus citations

Abstract

This chapter presents an overview of learning approaches for the acquisition of controllers and movement skills in humanoid robots. The term learning control refers to the process of acquiring a control strategy to achieve a task. While the definition is in some cases restrained to trial-and-error learning, we present here learning control in a broader perspective, with a focus on the representation of skills to be acquired, and on the different learning strategies that can contribute to the acquisition of robust and adaptive controllers for humanoids.

Original language	English
Title of host publication	Humanoid Robotics
Subtitle of host publication	A Reference
Publisher	Springer Netherlands
Pages	1261-1312
Number of pages	52
ISBN (Electronic)	9789400760462
ISBN (Print)	9789400760455
DOIs	https://doi.org/10.1007/978-94-007-6046-2_68
State	Published - 1 Jan 2018

Keywords

Dynamic Movement Primitives (DMP)
Gaussian Mixture Regression (GMR)
Hidden semi-Markov Model (HSMM)
Humanoid Robotics
Kinesthetic Teaching

Access to Document

10.1007/978-94-007-6046-2_68

Cite this

@inbook{6bd74977db5e4b0ab90c1aa444ddb96d,

title = "Learning Control",

abstract = "This chapter presents an overview of learning approaches for the acquisition of controllers and movement skills in humanoid robots. The term learning control refers to the process of acquiring a control strategy to achieve a task. While the definition is in some cases restrained to trial-and-error learning, we present here learning control in a broader perspective, with a focus on the representation of skills to be acquired, and on the different learning strategies that can contribute to the acquisition of robust and adaptive controllers for humanoids.",

keywords = "Dynamic Movement Primitives (DMP), Gaussian Mixture Regression (GMR), Hidden semi-Markov Model (HSMM), Humanoid Robotics, Kinesthetic Teaching",

author = "Sylvain Calinon and Dongheui Lee",

note = "Publisher Copyright: {\textcopyright} Springer Nature B.V. 2019.",

year = "2018",

month = jan,

day = "1",

doi = "10.1007/978-94-007-6046-2\_68",

language = "English",

isbn = "9789400760455",

pages = "1261--1312",

booktitle = "Humanoid Robotics",

publisher = "Springer Netherlands",

}

TY - CHAP

T1 - Learning Control

AU - Calinon, Sylvain

AU - Lee, Dongheui

N1 - Publisher Copyright: © Springer Nature B.V. 2019.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This chapter presents an overview of learning approaches for the acquisition of controllers and movement skills in humanoid robots. The term learning control refers to the process of acquiring a control strategy to achieve a task. While the definition is in some cases restrained to trial-and-error learning, we present here learning control in a broader perspective, with a focus on the representation of skills to be acquired, and on the different learning strategies that can contribute to the acquisition of robust and adaptive controllers for humanoids.

AB - This chapter presents an overview of learning approaches for the acquisition of controllers and movement skills in humanoid robots. The term learning control refers to the process of acquiring a control strategy to achieve a task. While the definition is in some cases restrained to trial-and-error learning, we present here learning control in a broader perspective, with a focus on the representation of skills to be acquired, and on the different learning strategies that can contribute to the acquisition of robust and adaptive controllers for humanoids.

KW - Dynamic Movement Primitives (DMP)

KW - Gaussian Mixture Regression (GMR)

KW - Hidden semi-Markov Model (HSMM)

KW - Humanoid Robotics

KW - Kinesthetic Teaching

UR - https://www.scopus.com/pages/publications/85138943318

U2 - 10.1007/978-94-007-6046-2_68

DO - 10.1007/978-94-007-6046-2_68

M3 - Chapter

AN - SCOPUS:85138943318

SN - 9789400760455

SP - 1261

EP - 1312

BT - Humanoid Robotics

PB - Springer Netherlands

ER -

Learning Control

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this