Human-Inspired Balancing and Recovery Stepping for Humanoid Robots

• Autore: Kaul Lukas Sebastian
• Pubblicazione: KIT Scientific Publishing, 2019
• Descrizione fisica: 1 electronic resource (X, 235 p. p.)
• Soggetto non controllato: Maschinelles Lernen; Balancing; Optimierung; Regelungstechnik; Machine learning; Balancieren; Control systems; Humanoide Robotik; Humanoid robotics; Optimization
• Sommario/riassunto: 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.
• Titolo autorizzato: Human-Inspired Balancing and Recovery Stepping for Humanoid Robots
• ISBN: 1000091605
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910346946503321
• Lo trovi qui: Univ. Federico II