Autonomous Knowledge Discovery Based on Artificial Curiosity-Driven Learning by Interaction

In this work, we investigate the development of a real-time intelligent systemallowing a robot to discover its surrounding world and to learn autonomouslynew knowledge about it by semantically interacting with humans. The learningis performed by observation and by interaction with a human. We describe thesystem in a general manner, and then we apply it to autonomous learning ofobjects and their colors. We provide experimental results both using simulatedenvironments and implementing the approach on a humanoid robot in a real-world environment including every-day objects. We show that our approachallows a humanoid robot to learn without negative input and from a smallnumber of samples.

[1]  Michael A. Goodrich,et al.  Human-Robot Interaction: A Survey , 2008, Found. Trends Hum. Comput. Interact..

[2]  Kurosh Madani,et al.  Multi-level cognitive machine-learning based concept for human-like "artificial" walking: Application to autonomous stroll of humanoid robots , 2011, Neurocomputing.

[3]  P. Kay,et al.  Biocultural Implications of Systems of Color Naming , 1991 .

[4]  Tomoaki Nakamura,et al.  Autonomous acquisition of multimodal information for online object concept formation by robots , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  T. Regier.  A model of the human capacity for categorizing spatial relations , 1995 .

[6]  Alessandro Saffiotti,et al.  An introduction to the anchoring problem , 2003, Robotics Auton. Syst..

[7]  Kurosh Madani,et al.  Autonomous knowledge acquisition based on artificial curiosity: Application to mobile robots in an indoor environment , 2013, Robotics Auton. Syst..

[8]  Ingo Lütkebohle,et al.  The curious robot - Structuring interactive robot learning , 2009, 2009 IEEE International Conference on Robotics and Automation.

[9]  Jan Hoffmann,et al.  A Vision Based System for Goal-Directed Obstacle Avoidance , 2004, RoboCup.

[10]  Chrystopher L. Nehaniv,et al.  Robot learning of lexical semantics from sensorimotor interaction and the unrestricted speech of human tutors , 2010 .

[11]  Kurosh Madani,et al.  Multilevel Cognitive Machine-Learning-Based Concept for Artificial Awareness: Application to Humanoid Robot Awareness Using Visual Saliency , 2012, Appl. Comput. Intell. Soft Comput..

[12]  James J. Little,et al.  Curious George: An attentive semantic robot , 2008, Robotics Auton. Syst..

[13]  Chen Yu,et al.  The emergence of links between lexical acquisition and object categorization: a computational study , 2005, Connect. Sci..

[14]  S. Waxman,et al.  Early word-learning entails reference, not merely associations , 2009, Trends in Cognitive Sciences.

[15]  D. Berlyne.  A theory of human curiosity. , 1954, British journal of psychology.

[16]  Melissa Bowerman,et al.  How do children avoid constructing an overly general grammar in the absence of feedback about what is not a sentence , 1983 .

[17]  Kurosh Madani,et al.  On Human Inspired Semantic SLAM's Feasibility , 2010, ANNIIP.

[18]  J. Demiris,et al.  Human-robot-communication and Machine Learning Abbr. Title: Human-robot-communication and Ml , 1997 .

[19]  Ramón Moreno,et al.  A machine learning based intelligent vision system for autonomous object detection and recognition , 2013, Applied Intelligence.

[20]  Luc Steels,et al.  Flexible word meaning in embodied agents , 2008, Connect. Sci..

[21]  Tony Belpaeme,et al.  Human-Robot Interaction in Concept Acquisition: a computational model , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[22]  Ramón Moreno,et al.  Image segmentation on spherical coordinate representation of RGB colour space , 2012 .

[23]  Marc Hanheide,et al.  A system for interactive learning in dialogue with a tutor , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.