KIT | KIT-Bibliothek | Impressum | Datenschutz

Human-Inspired Balancing and Recovery Stepping for Humanoid Robots

Kaul, Lukas Sebastian

Abstract:
Robustly maintaining balance on two legs is an important challenge for humanoid robots. The work presented in this book represents a contribution to this area. It investigates efficient methods for the decision-making from internal sensors about whether and where to step, several improvements to efficient whole-body postural balancing methods, and proposes and evaluates a novel method for efficient recovery step generation, leveraging human examples and simulation-based reinforcement learning.

Open Access Logo


Volltext §
DOI: 10.5445/IR/1000092689
Veröffentlicht am 26.03.2019
Coverbild
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Hochschulschrift
Jahr 2019
Sprache Englisch
Identifikator urn:nbn:de:swb:90-926891
KITopen-ID: 1000092689
Verlag KIT, Karlsruhe
Umfang X, 235 S.
Abschlussart Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik und Robotik (IAR)
Prüfungsdatum 23.01.2019
Referent/Betreuer Prof. T. Asfour
Schlagworte Humanoid Robotics, Optimal Control, Machine Learning
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page