Sciweavers

352 search results - page 43 / 71
» Efficient learning algorithms for changing environments
Sort
View
IROS
2007
IEEE
172views Robotics» more  IROS 2007»
15 years 10 months ago
Motor control optimization of compliant one-legged locomotion in rough terrain
— While underactuated robotic systems are capable of energy efficient and rapid dynamic behavior, we still do not fully understand how body dynamics can be actively used for ada...
Fumiya Iida, Russ Tedrake
ATAL
2010
Springer
15 years 5 months ago
Cultivating desired behaviour: policy teaching via environment-dynamics tweaks
In this paper we study, for the first time explicitly, the implications of endowing an interested party (i.e. a teacher) with the ability to modify the underlying dynamics of the ...
Zinovi Rabinovich, Lachlan Dufton, Kate Larson, Ni...
CVPR
2010
IEEE
15 years 9 months ago
Visual Tracking via Weakly Supervised Learning from Multiple Imperfect Oracles
Long-term persistent tracking in ever-changing environments is a challenging task, which often requires addressing difficult object appearance update problems. To solve them, most...
Bineng Zhong, Hongxun Yao, Sheng Chen, Xiaotong Yu...
ACMACE
2008
ACM
15 years 6 months ago
Evaluation of a pervasive game for domestic energy engagement among teenagers
In this paper, we present Power Agent - a pervasive game designed to encourage teenagers and their families to reduce energy consumption in the home. The idea behind this mobile p...
Anton Gustafsson, Magnus Bång
JFR
2006
140views more  JFR 2006»
15 years 4 months ago
Improving robot navigation through self-supervised online learning
In mobile robotics, there are often features that, while potentially powerful for improving navigation, prove difficult to profit from as they generalize poorly to novel situations...
Boris Sofman, Ellie Lin, J. Andrew Bagnell, John C...