000922635 000__ 03220cam\a2200493Ii\4500
000922635 001__ 922635
000922635 005__ 20230306150846.0
000922635 006__ m\\\\\o\\d\\\\\\\\
000922635 007__ cr\cn\nnnunnun
000922635 008__ 190916s2020\\\\sz\a\\\\ob\\\\000\0\eng\d
000922635 019__ $$a1125768109
000922635 020__ $$a9783030263263$$q(electronic book)
000922635 020__ $$a3030263266$$q(electronic book)
000922635 020__ $$z9783030263256
000922635 0247_ $$a10.1007/978-3-030-26326-3$$2doi
000922635 035__ $$aSP(OCoLC)on1119668702
000922635 035__ $$aSP(OCoLC)1119668702$$z(OCoLC)1125768109
000922635 040__ $$aGW5XE$$beng$$erda$$epn$$cGW5XE$$dUKMGB$$dYDX$$dOCLCF$$dSFB
000922635 049__ $$aISEA
000922635 050_4 $$aTJ211.412$$b.C65 2020eb
000922635 08204 $$a629.8/92$$223
000922635 1001_ $$aColomé, Adrià,$$eauthor.
000922635 24510 $$aReinforcement learning of bimanual robot skills /$$cAdrià Colomé, Carme Torras.
000922635 264_1 $$aCham :$$bSpringer,$$c[2020]
000922635 264_4 $$c©2020
000922635 300__ $$a1 online resource :$$billustrations.
000922635 336__ $$atext$$btxt$$2rdacontent
000922635 337__ $$acomputer$$bc$$2rdamedia
000922635 338__ $$aonline resource$$bcr$$2rdacarrier
000922635 4901_ $$aSpringer tracts in advanced robotics,$$x1610-7438 ;$$vvolume 134
000922635 504__ $$aIncludes bibliographical references.
000922635 5050_ $$aIntroduction -- State of the art -- Inverse kinematics and relative arm positioning -- Robot compliant control -- Preliminaries -- Sampling efficiency in learning robot motion -- Dimensionality reduction with MPs -- Generating and adapting ProMPs -- Conclusions.
000922635 506__ $$aAccess limited to authorized users.
000922635 520__ $$aThis book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It proposes practical enhancements to closed-loop inverse kinematics for redundant robots, a procedure to position the two arms to maximize workspace manipulability, and a dynamic model together with a disturbance observer to achieve compliant control and safe robot behavior. In the second part, methods for robot motion learning based on movement primitives and direct policy search algorithms are presented. To improve sampling efficiency and accelerate learning without deteriorating solution quality, techniques for dimensionality reduction, for exploiting low-performing samples, and for contextualization and adaptability to changing situations are proposed. In sum, the reader will find in this comprehensive exposition the relevant knowledge in different areas required to build a complete framework for model-free, compliant, coordinated robot motion learning.
000922635 588__ $$aOnline resource; title from PDF title page (SpringerLink, viewed September 16, 2019).
000922635 650_0 $$aRobots$$xKinematics.
000922635 650_0 $$aRobots$$xDynamics.
000922635 650_0 $$aMachine learning.
000922635 7001_ $$aTorras, Carme,$$eauthor.
000922635 830_0 $$aSpringer tracts in advanced robotics ;$$vv. 134.
000922635 852__ $$bebk
000922635 85640 $$3SpringerLink$$uhttps://univsouthin.idm.oclc.org/login?url=http://link.springer.com/10.1007/978-3-030-26326-3$$zOnline Access$$91397441.1
000922635 909CO $$ooai:library.usi.edu:922635$$pGLOBAL_SET
000922635 980__ $$aEBOOK
000922635 980__ $$aBIB
000922635 982__ $$aEbook
000922635 983__ $$aOnline
000922635 994__ $$a92$$bISE