國立虎尾科技大學 |

Reinforcement Learning of Bimanual Robot Skills

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Reinforcement Learning of Bimanual Robot Skills/ by Adrià Colomé, Carme Torras.
作者:	Colomé, Adrià.
其他作者:	Torras, Carme.
面頁冊數:	XIX, 182 p. 64 illus., 57 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Control and Systems Theory. -
電子資源:	https://doi.org/10.1007/978-3-030-26326-3
ISBN:	9783030263263

Reinforcement Learning of Bimanual Robot Skills
Colomé, Adrià.

Reinforcement Learning of Bimanual Robot Skills[electronic resource] /by Adrià Colomé, Carme Torras. - 1st ed. 2020. - XIX, 182 p. 64 illus., 57 illus. in color.online resource. - Springer Tracts in Advanced Robotics,1341610-7438 ;. - Springer Tracts in Advanced Robotics,105.

Introduction -- State of the art -- Inverse kinematics and relative arm positioning -- Robot compliant control -- Preliminaries -- Sampling efficiency in learning robot motion -- Dimensionality reduction with MPs -- Generating and adapting ProMPs -- Conclusions.

This book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It proposes practical enhancements to closed-loop inverse kinematics for redundant robots, a procedure to position the two arms to maximize workspace manipulability, and a dynamic model together with a disturbance observer to achieve compliant control and safe robot behavior. In the second part, methods for robot motion learning based on movement primitives and direct policy search algorithms are presented. To improve sampling efficiency and accelerate learning without deteriorating solution quality, techniques for dimensionality reduction, for exploiting low-performing samples, and for contextualization and adaptability to changing situations are proposed. In sum, the reader will find in this comprehensive exposition the relevant knowledge in different areas required to build a complete framework for model-free, compliant, coordinated robot motion learning.

ISBN: 9783030263263

Standard No.: 10.1007/978-3-030-26326-3doiSubjects--Topical Terms:

1211358
Control and Systems Theory.

LC Class. No.: TJ210.2-211.495

Dewey Class. No.: 629.892

Reinforcement Learning of Bimanual Robot Skills
LDR:02969nam a22004215i 4500 001 1023341
003 DE-He213
005 20200701224125.0
007 cr nn 008mamaa
008 210318s2020 gw | s |||| 0|eng d
020 $a 9783030263263 $9 978-3-030-26326-3
024 7 $a 10.1007/978-3-030-26326-3 $2 doi
035 $a 978-3-030-26326-3
050 4 $a TJ210.2-211.495
050 4 $a T59.5
072 7 $a TJFM1 $2 bicssc
072 7 $a TEC037000 $2 bisacsh
072 7 $a TJFM1 $2 thema
082 0 4 $a 629.892 $2 23
100 1 $a Colomé, Adrià. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1319240
245 1 0 $a Reinforcement Learning of Bimanual Robot Skills $h [electronic resource] / $c by Adrià Colomé, Carme Torras.
250 $a 1st ed. 2020.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a XIX, 182 p. 64 illus., 57 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Springer Tracts in Advanced Robotics, $x 1610-7438 ; $v 134
505 0 $a Introduction -- State of the art -- Inverse kinematics and relative arm positioning -- Robot compliant control -- Preliminaries -- Sampling efficiency in learning robot motion -- Dimensionality reduction with MPs -- Generating and adapting ProMPs -- Conclusions.
520 $a This book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It proposes practical enhancements to closed-loop inverse kinematics for redundant robots, a procedure to position the two arms to maximize workspace manipulability, and a dynamic model together with a disturbance observer to achieve compliant control and safe robot behavior. In the second part, methods for robot motion learning based on movement primitives and direct policy search algorithms are presented. To improve sampling efficiency and accelerate learning without deteriorating solution quality, techniques for dimensionality reduction, for exploiting low-performing samples, and for contextualization and adaptability to changing situations are proposed. In sum, the reader will find in this comprehensive exposition the relevant knowledge in different areas required to build a complete framework for model-free, compliant, coordinated robot motion learning.
650 2 4 $a Control and Systems Theory. $3 1211358
650 2 4 $a Artificial Intelligence. $3 646849
650 1 4 $a Robotics and Automation. $3 782979
650 0 $a Control engineering. $3 1249728
650 0 $a Artificial intelligence. $3 559380
650 0 $a Automation. $3 596698
650 0 $a Robotics. $3 561941
700 1 $a Torras, Carme. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1319241
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030263256
776 0 8 $i Printed edition: $z 9783030263270
776 0 8 $i Printed edition: $z 9783030263287
830 0 $a Springer Tracts in Advanced Robotics, $x 1610-7438 ; $v 105 $3 1261025
856 4 0 $u https://doi.org/10.1007/978-3-030-26326-3
912 $a ZDB-2-INR
912 $a ZDB-2-SXIT
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)
950 $a Intelligent Technologies and Robotics (R0) (SpringerNature-43728)