Machine Learning for Robotics: Learning Methods for Robot Motor Skills

4 avg rating
( 3 ratings by Goodreads )
 
9783639021103: Machine Learning for Robotics: Learning Methods for Robot Motor Skills

Autonomous robots have been a vision of robotics, artificial intelligence, and cognitive sciences. An important step towards this goal is to create robots that can learn to accomplish a multitude of different tasks triggered by environmental context and higher-level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s showed that handcrafted approaches do not suffice and that machine learning is needed. However, off the shelf learning techniques often do not scale into real-time or to the high-dimensional domains of manipulator and humanoid robotics. In this book, we investigate the foundations for a general approach to motor skill learning that employs domain-specific machine learning methods. A theoretically well-founded general approach to representing the required control structures for task representation and execution is presented along with novel learning algorithms that can be applied in this setting. The resulting framework is shown to work well both in simulation and on real robots.

"synopsis" may belong to another edition of this title.

About the Author:

Jan Peters heads the Robot Learning Lab at Max-Planck Institute for Biological Cybernetics. He graduated from Univ. of Southern California with a PhD in Computer Science. He studied Computer Science, Electrical & Mechanical Engineering in Munich, Singapore and Los Angeles and was a visiting researcher at National Univ. of Singapore and ATR in Japan. His research centers on motor skill learning and robotics.

"About this title" may belong to another edition of this title.

Top Search Results from the AbeBooks Marketplace

1.

Jan Peters
Published by VDM Verlag 2008-05-01 (2008)
ISBN 10: 363902110X ISBN 13: 9783639021103
New paperback Quantity Available: > 20
Seller
Blackwell's
(Oxford, OX, United Kingdom)
Rating
[?]

Book Description VDM Verlag 2008-05-01, 2008. paperback. Book Condition: New. Bookseller Inventory # 9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 48.75
Convert Currency

Add to Basket

Shipping: US$ 3.80
From United Kingdom to U.S.A.
Destination, Rates & Speeds

2.

Peters, Jan
Published by VDM Verlag Dr. Mueller e.K. (2016)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Paperback Quantity Available: 1
Print on Demand
Seller
Ria Christie Collections
(Uxbridge, United Kingdom)
Rating
[?]

Book Description VDM Verlag Dr. Mueller e.K., 2016. Paperback. Book Condition: New. PRINT ON DEMAND Book; New; Publication Year 2016; Not Signed; Fast Shipping from the UK. No. book. Bookseller Inventory # ria9783639021103_lsuk

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 50.62
Convert Currency

Add to Basket

Shipping: US$ 4.91
From United Kingdom to U.S.A.
Destination, Rates & Speeds

3.

Peters, Jan
ISBN 10: 363902110X ISBN 13: 9783639021103
New Quantity Available: 1
Seller
Rating
[?]

Book Description Book Condition: New. Publisher/Verlag: VDM Verlag Dr. Müller | Learning Methods for Robot Motor Skills | Autonomous robots have been a vision of robotics, artificial intelligence, and cognitive sciences. An important step towards this goal is to create robots that can learn to accomplish amultitude of different tasks triggered by environmental context and higher-level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s showed that handcrafted approaches do not suffice and that machine learning is needed. However, off the shelf learning techniques often do not scale into real-time or to the high-dimensional domains of manipulator and humanoid robotics. In this book, we investigate the foundations for a general approach to motor skilllearning that employs domain-specific machine learning methods. A theoretically well-founded general approach to representing the required control structures for task representation and executionis presented along with novel learning algorithms that can be applied in this setting. The resulting framework is shown to work well both in simulation and on real robots. | Format: Paperback | Language/Sprache: english | 180 gr | 220x150x7 mm | 128 pp. Bookseller Inventory # K9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 66.91
Convert Currency

Add to Basket

Shipping: US$ 2.22
From Germany to U.S.A.
Destination, Rates & Speeds

4.

Jan Peters
Published by VDM Verlag Dr. Mueller E.K. (2008)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Quantity Available: > 20
Print on Demand
Seller
Pbshop
(Wood Dale, IL, U.S.A.)
Rating
[?]

Book Description VDM Verlag Dr. Mueller E.K., 2008. PAP. Book Condition: New. New Book. Shipped from US within 10 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Bookseller Inventory # IQ-9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 69.13
Convert Currency

Add to Basket

Shipping: US$ 3.99
Within U.S.A.
Destination, Rates & Speeds

5.

Jan Peters
Published by VDM Verlag (2008)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Quantity Available: > 20
Print on Demand
Seller
Books2Anywhere
(Fairford, GLOS, United Kingdom)
Rating
[?]

Book Description VDM Verlag, 2008. PAP. Book Condition: New. New Book. Delivered from our UK warehouse in 3 to 5 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Bookseller Inventory # LQ-9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 63.54
Convert Currency

Add to Basket

Shipping: US$ 11.41
From United Kingdom to U.S.A.
Destination, Rates & Speeds

6.

Jan Peters
Published by VDM Verlag Dr. Mueller e.K., Germany (2013)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Paperback Quantity Available: > 20
Print on Demand
Seller
The Book Depository EURO
(London, United Kingdom)
Rating
[?]

Book Description VDM Verlag Dr. Mueller e.K., Germany, 2013. Paperback. Book Condition: New. 231 x 157 mm. Language: English . Brand New Book ***** Print on Demand *****.Autonomous robots have been a vision of robotics, artificial intelligence, and cognitive sciences. An important step towards this goal is to create robots that can learn to accomplish a multitude of different tasks triggered by environmental context and higher-level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s showed that handcrafted approaches do not suffice and that machine learning is needed. However, off the shelf learning techniques often do not scale into real-time or to the high-dimensional domains of manipulator and humanoid robotics. In this book, we investigate the foundations for a general approach to motor skill learning that employs domain-specific machine learning methods. A theoretically well-founded general approach to representing the required control structures for task representation and execution is presented along with novel learning algorithms that can be applied in this setting. The resulting framework is shown to work well both in simulation and on real robots. Bookseller Inventory # AAV9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 82.33
Convert Currency

Add to Basket

Shipping: US$ 3.81
From United Kingdom to U.S.A.
Destination, Rates & Speeds

7.

Jan Peters
Published by VDM Verlag Dr. Müller E.K. Nov 2013 (2013)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Taschenbuch Quantity Available: 1
Seller
Agrios-Buch
(Bergisch Gladbach, Germany)
Rating
[?]

Book Description VDM Verlag Dr. Müller E.K. Nov 2013, 2013. Taschenbuch. Book Condition: Neu. 220x150x8 mm. Neuware - Autonomous robots have been a vision of robotics, artificial intelligence, and cognitive sciences. An important step towards this goal is to create robots that can learn to accomplish amultitude of different tasks triggered by environmental context and higher-level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s showed that handcrafted approaches do not suffice and that machine learning is needed. However, off the shelf learning techniques often do not scale into real-time or to the high-dimensional domains of manipulator and humanoid robotics. In this book, we investigate the foundations for a general approach to motor skilllearning that employs domain-specific machine learning methods. A theoretically well-founded general approach to representing the required control structures for task representation and executionis presented along with novel learning algorithms that can be applied in this setting. The resulting framework is shown to work well both in simulation and on real robots. 128 pp. Englisch. Bookseller Inventory # 9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 67.86
Convert Currency

Add to Basket

Shipping: US$ 19.13
From Germany to U.S.A.
Destination, Rates & Speeds

8.

Jan Peters
Published by VDM Verlag Dr. Müller E.K. Nov 2013 (2013)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Taschenbuch Quantity Available: 1
Seller
Rheinberg-Buch
(Bergisch Gladbach, Germany)
Rating
[?]

Book Description VDM Verlag Dr. Müller E.K. Nov 2013, 2013. Taschenbuch. Book Condition: Neu. 220x150x8 mm. Neuware - Autonomous robots have been a vision of robotics, artificial intelligence, and cognitive sciences. An important step towards this goal is to create robots that can learn to accomplish amultitude of different tasks triggered by environmental context and higher-level instruction. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s showed that handcrafted approaches do not suffice and that machine learning is needed. However, off the shelf learning techniques often do not scale into real-time or to the high-dimensional domains of manipulator and humanoid robotics. In this book, we investigate the foundations for a general approach to motor skilllearning that employs domain-specific machine learning methods. A theoretically well-founded general approach to representing the required control structures for task representation and executionis presented along with novel learning algorithms that can be applied in this setting. The resulting framework is shown to work well both in simulation and on real robots. 128 pp. Englisch. Bookseller Inventory # 9783639021103

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 67.86
Convert Currency

Add to Basket

Shipping: US$ 19.13
From Germany to U.S.A.
Destination, Rates & Speeds

9.

Jan Peters
Published by VDM Verlag Dr. Müller (2013)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Paperback Quantity Available: 1
Seller
Irish Booksellers
(Rumford, ME, U.S.A.)
Rating
[?]

Book Description VDM Verlag Dr. Müller, 2013. Paperback. Book Condition: New. book. Bookseller Inventory # 363902110X

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 87.83
Convert Currency

Add to Basket

Shipping: FREE
Within U.S.A.
Destination, Rates & Speeds

10.

Jan Peters
Published by VDM Verlag Dr. Mueller e.K. (2008)
ISBN 10: 363902110X ISBN 13: 9783639021103
New Paperback Quantity Available: 1
Print on Demand
Seller
Ergodebooks
(RICHMOND, TX, U.S.A.)
Rating
[?]

Book Description VDM Verlag Dr. Mueller e.K., 2008. Paperback. Book Condition: New. This item is printed on demand. Bookseller Inventory # DADAX363902110X

More Information About This Seller | Ask Bookseller a Question

Buy New
US$ 94.78
Convert Currency

Add to Basket

Shipping: US$ 3.99
Within U.S.A.
Destination, Rates & Speeds

There are more copies of this book

View all search results for this book