Sciweavers

567 search results - page 9 / 114
» Learning Pedestrian Dynamics from the Real World
Sort
View
ICCV
1995
IEEE
15 years 1 months ago
Closed-World Tracking
A new approach to tracking weakly modeled objects in a semantically rich domain is presented. We define a closed-world as a space-time region of an image sequence in which the co...
Stephen S. Intille, Aaron F. Bobick
ECML
2005
Springer
15 years 3 months ago
Machine Learning of Plan Robustness Knowledge About Instances
Abstract. Classical planning domain representations assume all the objects from one type are exactly the same. But when solving problems in the real world systems, the execution of...
Sergio Jiménez, Fernando Fernández, ...
AGENTS
1998
Springer
15 years 1 months ago
Learning Situation-Dependent Costs: Improving Planning from Probabilistic Robot Execution
Physical domains are notoriously hard to model completely and correctly, especially to capture the dynamics of the environment. Moreover, since environments change, it is even mor...
Karen Zita Haigh, Manuela M. Veloso
ECTEL
2008
Springer
14 years 11 months ago
Measuring Learning Object Reuse
This paper presents a quantitative analysis of the reuse of learning objects in real world settings. The data for this analysis was obtained from three sources: Connexions' mo...
Xavier Ochoa, Erik Duval
ICML
2004
IEEE
15 years 10 months ago
Learning low dimensional predictive representations
Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
Matthew Rosencrantz, Geoffrey J. Gordon, Sebastian...