Sciweavers

208 search results - page 30 / 42
» The curious robot - Structuring interactive robot learning
Sort
View
KES
1998
Springer
15 years 1 months ago
Hidden partitioning of a visual feedback-based neuro-controller
Robotic controllers take advantage from neural network learning capabilities as long as the dimensionality of the problem is kept moderate. This paper explores the possibilities of...
Jean-Philippe Urban, Jean-Luc Buessler, Julien Gre...
57
Voted
JETAI
2002
69views more  JETAI 2002»
14 years 9 months ago
The interaction of representations and planning objectives for decision-theoretic planning tasks
We study decision-theoretic planning or reinforcement learning in the presence of traps such as steep slopes for outdoor robots or staircases for indoor robots. In this case, achi...
Sven Koenig, Yaxin Liu
ETFA
2008
IEEE
15 years 4 months ago
Gesture recognition using evolution strategy neural network
A new approach to interact with an industrial robot using hand gestures is presented. System proposed here can learn a first time user’s hand gestures rapidly. This improves pro...
Johan Hägg, Baran Çürükl&uum...
75
Voted
AUSAI
2003
Springer
15 years 2 months ago
BN+BN: Behavior Network with Bayesian Network for Intelligent Agent
Abstract. In the philosophy of behavior-based robotics, design of complex behavior needs the interaction of basic behaviors that are easily implemented. Action selection mechanism ...
Kyung-Joong Kim, Sung-Bae Cho
88
Voted
IJCNN
2006
IEEE
15 years 3 months ago
Reinforcement Learning for Parameterized Motor Primitives
Abstract— One of the major challenges in both action generation for robotics and in the understanding of human motor control is to learn the “building blocks of movement genera...
Jan Peters, Stefan Schaal