Sciweavers

83 search results - page 3 / 17
» One-Shot Procedure Learning from Instruction and Observation
Sort
View
ICIA
2007
13 years 8 months ago
Task Learning by Instruction: Benefits and Challenges for Intelligent Interactive Systems
The CALO desktop assistant aims to provide assistance through many AI technologies, including several techniques for learning to perform tasks. Based on our experiences implementi...
Jim Blythe, Prateek Tandon, Mandar Tillu
ICML
1999
IEEE
13 years 10 months ago
Learning Hierarchical Performance Knowledge by Observation
Developing automated agents that intelligently perform complex real world tasks is time consuming and expensive. The most expensive part of developing these intelligent task perfo...
Michael van Lent, John E. Laird
HCI
2007
13 years 7 months ago
Learning Topologies of Situated Public Displays by Observing Implicit User Interactions
In this paper we present a procedure to learn a topological model of Situated Public Displays from data of people traveling between these displays. This model encompasses the dista...
Hans Jörg Müller, Antonio Krüger
IUI
2009
ACM
14 years 3 months ago
From geek to sleek: integrating task learning tools to support end users in real-world applications
Numerous techniques exist to help users automate repetitive tasks; however, none of these methods fully support enduser creation, use, and modification of the learned tasks. We pr...
Aaron Spaulding, Jim Blythe, Will Haines, Melinda ...
ICRA
2009
IEEE
137views Robotics» more  ICRA 2009»
14 years 29 days ago
Unsupervised learning of 3D object models from partial views
— We present an algorithm for learning 3D object models from partial object observations. The input to our algorithm is a sequence of 3D laser range scans. Models learned from th...
Michael Ruhnke, Bastian Steder, Giorgio Grisetti, ...