Artificial Curiosity Emerging Human-like Behaviour - A Fundation for Fully Autonomous Cognitive Machines

This paper is devoted to autonomous cognitive machines by mean of the design of an artificial curiosity based cognitive system for autonomous high-level knowledge acquisition from visual information. Playing a chief role as well in visual attention as in interactive high-level knowledge construction, the artificial curiosity (e.g. perceptual and epistemic curiosities) is realized through combining visual saliency detection and Machine-Learning based approaches. Experimental results validating the deployment of the investigated system have been obtained using a humanoid robot acquiring visually knowledge about its surrounding environment interacting with a human tutor. As show the reported results and experiments, the proposed cognitive system allows the machine to discover autonomously the surrounding world in which it may evolve, to learn new knowledge about it and to describe it using human-like natural utterances.

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

[2]  J. Wolfe,et al.  What attributes guide the deployment of visual attention and how do they do it? , 2004, Nature Reviews Neuroscience.

[3]  Samuel M. McClure,et al.  The Wick in the Candle of Learning , 2009, Psychological science.

[4]  Zheru Chi,et al.  Salient object detection using content-sensitive hypergraph representation and partitioning , 2012, Pattern Recognit..

[5]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[6]  Masaki Ogino,et al.  How can humanoid acquire lexicon? -active approach by attention and learning biases based on curiosity- , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Jordan Litman.  Interest and deprivation factors of epistemic curiosity , 2008 .

[8]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[9]  Dare A. Baldwin,et al.  Evidence for ‘motionese’: modifications in mothers’ infant-directed action , 2002 .

[10]  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..

[11]  D. Kuhn.  Strategies of Knowledge Acquisition , 1995 .

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

[13]  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.

[14]  Nanning Zheng,et al.  Learning to Detect a Salient Object , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  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 .

[16]  Sabine Süsstrunk,et al.  Salient Region Detection and Segmentation , 2008, ICVS.

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

[18]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

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

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

[21]  Kurosh Madani,et al.  A Real-time Robot Vision Approach Combining Visual Saliency and Unsupervised Learning , 2011 .

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