Dublin Core
Title
Human-Inspired Balancing and Recovery Stepping for Humanoid Robots
Subject
Machine Learning
Humanoid Robotic
Description
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.
Creator
Kaul, Lukas Sebastian
Source
https://www.ksp.kit.edu/9783731509035
Publisher
KIT Scientific Publishing
Date
2019
Rights
https://creativecommons.org/licenses/by-sa/4.0/
Format
Pdf
Language
English
Type
Book
Identifier
10.5445/KSP/1000091605