LEADER 00879nam0-2200313---450- 001 990009181990403321 005 20100505094343.0 035 $a000918199 035 $aFED01000918199 035 $a(Aleph)000918199FED01 035 $a000918199 100 $a20100505d1983----km-y0itay50------ba 101 0 $aita 102 $aIT 105 $ay-------001yy 200 1 $a<>pace$erealismo di un' utopia$fErnesto Balducci, Lodovico Grassi 210 $aMilano$cPrincipato$d1983 215 $a277 p.$d23 cm 610 0 $aPace$aConcezione$aStoria 676 $a327.172$v21$zita 700 1$aBalducci,$bErnesto$f<1922-1992>$0160111 701 1$aGrassi$bLodovico$0507752 801 0$aIT$bUNINA$gREICAT$2UNIMARC 901 $aBK 912 $a990009181990403321 952 $aFondo Santamaria 258$b45410$fFSPBC 959 $aFSPBC 996 $aPace$9779827 997 $aUNINA LEADER 03277nam 22006375 450 001 9910736004703321 005 20230801002656.0 010 $a3-031-37832-6 024 7 $a10.1007/978-3-031-37832-4 035 $a(MiAaPQ)EBC30670671 035 $a(Au-PeEL)EBL30670671 035 $a(DE-He213)978-3-031-37832-4 035 $a(PPN)272260487 035 $a(CKB)27899796500041 035 $a(EXLCZ)9927899796500041 100 $a20230801d2023 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aInductive Biases in Machine Learning for Robotics and Control /$fby Michael Lutter 205 $a1st ed. 2023. 210 1$aCham :$cSpringer Nature Switzerland :$cImprint: Springer,$d2023. 215 $a1 online resource (131 pages) 225 1 $aSpringer Tracts in Advanced Robotics,$x1610-742X ;$v156 311 08$aPrint version: Lutter, Michael Inductive Biases in Machine Learning for Robotics and Control Cham : Springer,c2023 9783031378317 327 $aIntroduction -- A Differentiable Newton-Euler Algorithm for Real-World Robotics -- Combining Physics and Deep Learning for Continuous-Time Dynamics Models -- Continuous-Time Fitted Value Iteration for Robust Policies -- Conclusion. 330 $aOne important robotics problem is ?How can one program a robot to perform a task?? Classical robotics solves this problem by manually engineering modules for state estimation, planning, and control. In contrast, robot learning solely relies on black-box models and data. This book shows that these two approaches of classical engineering and black-box machine learning are not mutually exclusive. To solve tasks with robots, one can transfer insights from classical robotics to deep networks and obtain better learning algorithms for robotics and control. To highlight that incorporating existing knowledge as inductive biases in machine learning algorithms improves performance, this book covers different approaches for learning dynamics models and learning robust control policies. The presented algorithms leverage the knowledge of Newtonian Mechanics, Lagrangian Mechanics as well as the Hamilton-Jacobi-Isaacs differential equation as inductive bias and are evaluated on physical robots. 410 0$aSpringer Tracts in Advanced Robotics,$x1610-742X ;$v156 606 $aAutomatic control 606 $aRobotics 606 $aAutomation 606 $aComputational intelligence 606 $aControl, Robotics, Automation 606 $aComputational Intelligence 606 $aRobotics 606 $aControl and Systems Theory 615 0$aAutomatic control. 615 0$aRobotics. 615 0$aAutomation. 615 0$aComputational intelligence. 615 14$aControl, Robotics, Automation. 615 24$aComputational Intelligence. 615 24$aRobotics. 615 24$aControl and Systems Theory. 676 $a629.8 676 $a629.892 700 $aLutter$b Michael$01380476 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910736004703321 996 $aInductive Biases in Machine Learning for Robotics and Control$93421911 997 $aUNINA