Sciweavers

1270 search results - page 178 / 254
» Dogged Learning for Robots
Sort
View
ICRA
2010
IEEE
170views Robotics» more  ICRA 2010»
13 years 8 months ago
Categorizing object-action relations from semantic scene graphs
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
AI50
2006
14 years 1 months ago
Intrinsically Motivated Machines
Abstract. Children seem intrinsically motivated to manipulate, to explore, to test, to learn and they look for activities and situations that provide such learning opportunities. I...
Frédéric Kaplan, Pierre-Yves Oudeyer
ROBOCUP
2007
Springer
99views Robotics» more  ROBOCUP 2007»
14 years 4 months ago
Instance-Based Action Models for Fast Action Planning
Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is lear...
Mazda Ahmadi, Peter Stone
IROS
2006
IEEE
144views Robotics» more  IROS 2006»
14 years 4 months ago
Estimating Probability Distribution with Q-learning for Biped Gait Generation and Optimization
— A new biped gait generation and optimization method is proposed in the frame of Estimation of Distribution Algorithms (EDAs) with Q-learning method. By formulating the biped ga...
Lingyun Hu, Changjiu Zhou, Zengqi Sun
ICRA
2005
IEEE
210views Robotics» more  ICRA 2005»
14 years 3 months ago
Improving Grid-based SLAM with Rao-Blackwellized Particle Filters by Adaptive Proposals and Selective Resampling
— Recently Rao-Blackwellized particle filters have been introduced as effective means to solve the simultaneous localization and mapping (SLAM) problem. This approach uses a par...
Giorgio Grisetti, Cyrill Stachniss, Wolfram Burgar...