Sciweavers

152 search results - page 25 / 31
» Statistical Learning for Humanoid Robots
Sort
View
134
Voted
AAAI
1998
15 years 4 months ago
Alternative Essences of Intelligence
We present a novel methodology for building humanlike artificially intelligent systems. We take as a model the only existing systems which are universally accepted as intelligent:...
Rodney A. Brooks, Cynthia Breazeal, Robert Irie, C...
124
Voted
NN
2010
Springer
125views Neural Networks» more  NN 2010»
15 years 1 months ago
Parameter-exploring policy gradients
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Frank Sehnke, Christian Osendorfer, Thomas Rü...
113
Voted
ECAI
2000
Springer
15 years 7 months ago
Autonomous Environment and Task Adaptation for Robotic Agents
This paper investigates the problem of improving the performance of general state-of-the-art robot control systems by autonomously adapting them to specific tasks and environments...
Michael Beetz, Thorsten Belker
ROMAN
2007
IEEE
191views Robotics» more  ROMAN 2007»
15 years 8 months ago
Learning and Recognition of Object Manipulation Actions Using Linear and Nonlinear Dimensionality Reduction
— In this work, we perform an extensive statistical evaluation for learning and recognition of object manipulation actions. We concentrate on single arm/hand actions but study th...
Isabel Serrano Vicente, Danica Kragic, Jan-Olof Ek...
123
Voted
ICRA
2010
IEEE
158views Robotics» more  ICRA 2010»
15 years 1 months ago
Coping with imbalanced training data for improved terrain prediction in autonomous outdoor robot navigation
Abstract— Autonomous robot navigation in unstructured outdoor environments is a challenging and largely unsolved area of active research. The navigation task requires identifying...
Michael J. Procopio, Jane Mulligan, Gregory Z. Gru...