Learning Dynamic Systems for Intention Recognition in Human-Robot-Cooperation

This thesis is concerned with intention recognition for a humanoid robot and investigates how the challenges of uncertain and incomplete observations, a high degree of detail of the used models, and real-time inference may be addressed by modeling the human rationale as hybrid, dynamic Bayesian netw...

Full description

Bibliographic Details
Main Author: Krauthausen, Peter
Format: eBook
Language:English
Published: KIT Scientific Publishing 2013
Series:Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory
Subjects:
Online Access:
Collection: Directory of Open Access Books - Collection details see MPG.ReNa
LEADER 01790nma a2200325 u 4500
001 EB001982660
003 EBX01000000000000001145562
005 00000000000000.0
007 cr|||||||||||||||||||||
008 210512 ||| eng
020 |a 9783866449527 
020 |a 1000031356 
100 1 |a Krauthausen, Peter 
245 0 0 |a Learning Dynamic Systems for Intention Recognition in Human-Robot-Cooperation  |h Elektronische Ressource 
260 |b KIT Scientific Publishing  |c 2013 
300 |a 1 electronic resource (XIV, 210 p. p.) 
653 |a Dynamic Systems 
653 |a Intention Recognition 
653 |a Regularization 
653 |a Human-Robot-Cooperation 
653 |a (Conditional) Density Estimation 
041 0 7 |a eng  |2 ISO 639-2 
989 |b DOAB  |a Directory of Open Access Books 
490 0 |a Karlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory 
500 |a Creative Commons (cc), https://creativecommons.org/licenses/by-nc-nd/4.0/ 
024 8 |a 10.5445/KSP/1000031356 
856 4 0 |u https://www.ksp.kit.edu/9783866449527  |x Verlag  |3 Volltext 
856 4 2 |u https://directory.doabooks.org/handle/20.500.12854/51483  |z DOAB: description of the publication 
082 0 |a 140 
520 |a This thesis is concerned with intention recognition for a humanoid robot and investigates how the challenges of uncertain and incomplete observations, a high degree of detail of the used models, and real-time inference may be addressed by modeling the human rationale as hybrid, dynamic Bayesian networks and performing inference with these models. The key focus lies on the automatic identification of the employed nonlinear stochastic dependencies and the situation-specific inference.