A cognitive approach for robots' autonomous learning

Authors:
Dominik M. Ramík;Kurosh Madani;Christophe Sabourin
Affiliations:
Signals, Images, and Intelligent Systems Laboratory (LISSI / EA 3956), Senart-FB Institute of Technology, University Paris-Est Creteil, Lieusaint, France;Signals, Images, and Intelligent Systems Laboratory (LISSI / EA 3956), Senart-FB Institute of Technology, University Paris-Est Creteil, Lieusaint, France;Signals, Images, and Intelligent Systems Laboratory (LISSI / EA 3956), Senart-FB Institute of Technology, University Paris-Est Creteil, Lieusaint, France
Venue:
IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I
Year:
2013

Citing 6
Cited 0

Human-robot interaction: a survey

Foundations and Trends in Human-Computer Interaction
Curious George: An attentive semantic robot

Robotics and Autonomous Systems
Flexible word meaning in embodied agents

Connection Science - Social Learning in Embodied Agents
Human-Robot Interaction in Concept Acquisition: a computational model

DEVLRN '09 Proceedings of the 2009 IEEE 8th International Conference on Development and Learning
The curious robot-structuring interactive robot learning

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Hybrid Salient Object Extraction Approach with Automatic Estimation of Visual Attention Scale

SITIS '11 Proceedings of the 2011 Seventh International Conference on Signal Image Technology & Internet-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we contribute to development of a real-time intelligent system allowing to discover and to learn autonomously new knowledge about the surrounding world by semantically interacting with human. The learning is accomplished by observation and by interaction with a human tutor. We provide experimental results as well using simulated environment as implementing the approach on a humanoid robot in a real-world environment including every-day objects. We show, that our approach allows a humanoid robot to learn without negative input and from small number of samples.