Sciweavers

14 search results - page 1 / 3
» Toward designing a robot that learns actions from parental d...
Sort
View
ICRA
2008
IEEE
210views Robotics» more  ICRA 2008»
13 years 10 months ago
Toward designing a robot that learns actions from parental demonstrations
— How to teach actions to a robot as well as how a robot learns actions is an important issue to be discussed in designing robot learning systems. Inspired by human parentinfant ...
Yukie Nagai, Claudia Muhl, Katharina J. Rohlfing
ATAL
2010
Springer
13 years 5 months ago
Learning multirobot joint action plans from simultaneous task execution demonstrations
The central problem of designing intelligent robot systems which learn by demonstrations of desired behaviour has been largely studied within the field of robotics. Numerous archi...
Murilo Fernandes Martins, Yiannis Demiris
ATAL
2007
Springer
13 years 8 months ago
Confidence-based policy learning from demonstration using Gaussian mixture models
We contribute an approach for interactive policy learning through expert demonstration that allows an agent to actively request and effectively represent demonstration examples. I...
Sonia Chernova, Manuela M. Veloso
ICRA
2009
IEEE
259views Robotics» more  ICRA 2009»
13 years 11 months ago
Constructing action set from basis functions for reinforcement learning of robot control
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawar...
HICSS
2003
IEEE
174views Biometrics» more  HICSS 2003»
13 years 9 months ago
Linking Perception and Action in a Control Architecture for Human-Robot Domains
Human-robot interaction is a growing research domain; there are many approaches to robot design, depending on the particular aspects of interaction being focused on. In this paper...
Monica N. Nicolescu, Maja J. Mataric