Sciweavers

171 search results - page 3 / 35
» Detecting Execution Failures Using Learned Action Models
Sort
View
ICRA
1995
IEEE
125views Robotics» more  ICRA 1995»
13 years 9 months ago
Inductive Generation of Diagnostic Knowledge for Autonomous Assembly
A generic architecture for evolutive supervision of robotized assembly tasks is presented. This architecture , at different levels of abstraction, functions for dispatching action...
Luís Seabra Lopes, Luis M. Camarinha-Matos
ICASSP
2010
IEEE
13 years 6 months ago
Action change detection in video by covariance matching of silhouette tunnels
Action recognition is an important but challenging problem in video analytics with a number of solutions proposed to date. However, even if a reliable model for action representat...
Kai Guo, Prakash Ishwar, Janusz Konrad
JIRS
2000
144views more  JIRS 2000»
13 years 6 months ago
An Integrated Approach of Learning, Planning, and Execution
Agents (hardware or software) that act autonomously in an environment have to be able to integrate three basic behaviors: planning, execution, and learning. This integration is man...
Ramón García-Martínez, Daniel...
ACL
2009
13 years 4 months ago
Reinforcement Learning for Mapping Instructions to Actions
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer,...
FLAIRS
2007
13 years 8 months ago
Managing Dynamic Contexts Using Failure-Driven Stochastic Models
We describe an architecture for representing and managing context shifts that supports dynamic data interpretation. This architecture utilizes two layers of learning and three lay...
Nikita A. Sakhanenko, George F. Luger, Carl R. Ste...