Sciweavers

334 search results - page 48 / 67
» Habitable 3D Learning Environments for Situated Learning
Sort
View
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...
EELC
2006
121views Languages» more  EELC 2006»
15 years 8 months ago
Symbol Grounding Through Cumulative Learning
Abstract. We suggest that the primary motivation for an agent to construct a symbol-meaning mapping is to solve a task. The meaning space of an agent should be derived from the tas...
Samarth Swarup, Kiran Lakkaraju, Sylvian R. Ray, L...
IROS
2008
IEEE
123views Robotics» more  IROS 2008»
15 years 10 months ago
Learning predictive terrain models for legged robot locomotion
— Legged robots require accurate models of their environment in order to plan and execute paths. We present a probabilistic technique based on Gaussian processes that allows terr...
Christian Plagemann, Sebastian Mischke, Sam Prenti...
CIVR
2004
Springer
248views Image Analysis» more  CIVR 2004»
15 years 8 months ago
Automated Person Identification in Video
Abstract. We describe progress in the automatic detection and identification of humans in video, given a minimal number of labelled faces as training data. This is an extremely cha...
Mark Everingham, Andrew Zisserman
ICRA
1998
IEEE
154views Robotics» more  ICRA 1998»
15 years 8 months ago
Environmental Complexity Control for Vision-Based Learning Mobile Robot
This paper discusses how a robot can develop its state vector according to the complexity of the interactions with its environment. A method for controlling the complexity is prop...
Eiji Uchibe, Minoru Asada, Koh Hosoda