Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

18

AAAI
2007

favoriteEmaildiscussreport

152views Intelligent Agents» more AAAI 2007»

Autonomous Development of a Grounded Object Ontology by a Learning Robot

13 years 7 months ago

Autonomous Development of a Grounded Object Ontology by a Learning Robot

Download www.aaai.org

We describe how a physical robot can learn about objects from its own autonomous experience in the continuous world. The robot identiﬁes statistical regularities that allow it to represent a physical object with a cluster of sensations that violate a static world model, track that cluster over time, extract percepts from that cluster, form concepts from similar percepts, and learn reliable actions that can be applied to objects. We present a formalism for representing the ontology for objects and actions, a learning algorithm, and the results of an evaluation with a physical robot.

Joseph Modayil, Benjamin Kuipers

Real-time Traffic

AAAI 2007 | Extract Percepts | Intelligent Agents | Physical Robot | Static World Model |

claim paper

Related Content

» Flying Fast and Low Among Obstacles

» BehaviorGrounded Representation of Tool Affordances

» Towards a cognitive robot that uses internal rehearsal to learn affordance relations

» Bootstrap learning of foundational representations

» Learning to Select Object Recognition Methods for Autonomous Mobile Robots

» Grounded Situation Models for Robots Where words and percepts meet

» Adaptive long range vision in unstructured terrain

» Autonomous Learning of Object Appearances using Colour Contour Frames

» The Marchitecture A Cognitive Architecture for a Robot Baby

Post Info
More Details (n/a)

Added	02 Oct 2010
Updated	02 Oct 2010
Type	Conference
Year	2007
Where	AAAI
Authors	Joseph Modayil, Benjamin Kuipers

Comments (0)