Dekorationsartikel gehören nicht zum Leistungsumfang.
Inductive Biases in Machine Learning for Robotics and Control
Buch von Michael Lutter
Sprache: Englisch

128,39 €*

inkl. MwSt.

Versandkostenfrei per Post / DHL

Aktuell nicht verfügbar

Kategorien:
Beschreibung
One 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.
One 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.
Inhaltsverzeichnis
Introduction.- 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.
Details
Erscheinungsjahr: 2023
Fachbereich: Nachrichtentechnik
Genre: Technik
Rubrik: Naturwissenschaften & Technik
Medium: Buch
Seiten: 136
Reihe: Springer Tracts in Advanced Robotics
Inhalt: xv
119 S.
3 s/w Illustr.
20 farbige Illustr.
119 p. 23 illus.
20 illus. in color.
ISBN-13: 9783031378317
ISBN-10: 3031378318
Sprache: Englisch
Ausstattung / Beilage: HC runder Rücken kaschiert
Einband: Gebunden
Autor: Lutter, Michael
Auflage: 1st ed. 2023
Hersteller: Springer Nature Switzerland
Springer International Publishing
Springer Tracts in Advanced Robotics
Maße: 241 x 160 x 14 mm
Von/Mit: Michael Lutter
Erscheinungsdatum: 01.08.2023
Gewicht: 0,377 kg
preigu-id: 127155736
Inhaltsverzeichnis
Introduction.- 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.
Details
Erscheinungsjahr: 2023
Fachbereich: Nachrichtentechnik
Genre: Technik
Rubrik: Naturwissenschaften & Technik
Medium: Buch
Seiten: 136
Reihe: Springer Tracts in Advanced Robotics
Inhalt: xv
119 S.
3 s/w Illustr.
20 farbige Illustr.
119 p. 23 illus.
20 illus. in color.
ISBN-13: 9783031378317
ISBN-10: 3031378318
Sprache: Englisch
Ausstattung / Beilage: HC runder Rücken kaschiert
Einband: Gebunden
Autor: Lutter, Michael
Auflage: 1st ed. 2023
Hersteller: Springer Nature Switzerland
Springer International Publishing
Springer Tracts in Advanced Robotics
Maße: 241 x 160 x 14 mm
Von/Mit: Michael Lutter
Erscheinungsdatum: 01.08.2023
Gewicht: 0,377 kg
preigu-id: 127155736
Warnhinweis

Ähnliche Produkte

Ähnliche Produkte