01783nam 2200421z- 450 991034694650332120231214133255.01000091605(CKB)4920000000101057(oapen)https://directory.doabooks.org/handle/20.500.12854/49648(EXLCZ)99492000000010105720202102d2019 |y 0engurmn|---annantxtrdacontentcrdamediacrrdacarrierHuman-Inspired Balancing and Recovery Stepping for Humanoid RobotsKIT Scientific Publishing20191 electronic resource (X, 235 p. p.)Karlsruhe Series on Humanoid Robotics3-7315-0903-2 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.Maschinelles LernenBalancingOptimierungRegelungstechnikMachine learningBalancierenControl systemsHumanoide RobotikHumanoid roboticsOptimizationKaul Lukas Sebastianauth1294136BOOK9910346946503321Human-Inspired Balancing and Recovery Stepping for Humanoid Robots3022916UNINA