The initial development of object knowledge by a learning robot

Authors:
Joseph Modayil;Benjamin Kuipers
Affiliations:
Department of Computer Science, University of Rochester, PO Box 270226, Rochester, NY 14627, USA;Department of Computer Sciences, The University of Texas at Austin, 1 University Station, Austin, TX 78712, USA
Venue:
Robotics and Autonomous Systems
Year:
2008

Citing 13
Cited 2

Functional transformations in AI discovery systems

Artificial Intelligence
Acquiring domain knowledge for planning by experimentation

Acquiring domain knowledge for planning by experimentation
Map learning with uninterpreted sensors and effectors

Artificial Intelligence
The spatial semantic hierarchy

Artificial Intelligence
Is there something out there?: Inferring space from sensorimotor dependencies

Neural Computation
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Learning Recursive Control Programs from Problem Solving

The Journal of Machine Learning Research
Common sense data acquisition for indoor mobile robots

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Motion-based autonomous grounding: inferring external world properties from encoded internal sensory states alone

AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Learning planning rules in noisy stochastic worlds

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
A relational representation for procedural task knowledge

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Autonomous development of a grounded object ontology by a learning robot

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2

Learning action effects in partially observable domains

Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Goal emulation and planning in perceptual space using learned affordances

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe how a robot can develop knowledge of the objects in its environment directly from unsupervised sensorimotor experience. The object knowledge consists of multiple integrated representations: trackers that form spatio-temporal clusters of sensory experience, percepts that represent properties for the tracked objects, classes that support efficient generalization from past experience, and actions that reliably change object percepts. We evaluate how well this intrinsically acquired object knowledge can be used to solve externally specified tasks, including object recognition and achieving goals that require both planning and continuous control.