Towards a Spatial Model for Humanoid Social Robots

This paper presents an approach to endow a humanoid robot with the capability of learning new objects and recognizing them in an unstructured environment. New objects are learnt, whenever an unrecognized one is found within a certain (small) distance from the robot head. Recognized objects are mapped to an ego-centric frame of reference, which together with a simple short-term memory mechanism, makes this mapping persistent. This allows the robot to be aware of their presence even if temporarily out of the field of view, thus providing a primary spatial model of the environment (as far as known objects are concerned). SIFT features are used, not only for recognizing previously learnt objects, but also to allow the robot to estimate their distance (depth perception). The humanoid platform used for the experiments was the iCub humanoid robot. This capability functions together with iCub's low-level attention system: recognized objects enact salience thus attracting the robot attention, by gazing at them, each one in turn. We claim that the presented approach is a contribution towards linking a bottom-up attention system with top-down cognitive information.

[1]  Nils J. Nilsson,et al.  Human-Level Artificial Intelligence? Be Serious! , 2005, AI Mag..

[2]  Alessandro Saffiotti,et al.  Perceptual Anchoring of Symbols for Action , 2001, IJCAI.

[3]  C. Koch,et al.  A saliency-based search mechanism for overt and covert shifts of visual attention , 2000, Vision Research.

[4]  Giulio Sandini,et al.  The RobotCub project -- an open framework for research in embodied cognition , 2006 .

[5]  A. Stoytchev.  Toward Learning the Binding Affordances of Objects : A Behavior-Grounded Approach , 2022 .

[6]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[7]  Carol McKenna Hamilton,et al.  Modern Masters of an Ancient Game , 1997, AI Mag..

[8]  Wai-Kiang Yeap,et al.  Emperor AI, Where Is Your New Mind? , 1997, AI Mag..

[9]  Manuel Lopes,et al.  From pixels to objects: Enabling a spatial model for humanoid social robots , 2009, 2009 IEEE International Conference on Robotics and Automation.

[10]  Silvia Coradeschi,et al.  Perceptual anchoring via conceptual spaces , 2004, AAAI 2004.

[11]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[12]  Giulio Sandini,et al.  A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents , 2007, IEEE Transactions on Evolutionary Computation.

[13]  Axel Pinz,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[14]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[15]  Niko Sünderhauf,et al.  COMPARING SEVERAL IMPLEMENTATIONS OF TWO RECENTLY PUBLISHED FEATURE DETECTORS , 2007 .

[16]  Manuel Lopes,et al.  Learning Object Affordances: From Sensory--Motor Coordination to Imitation , 2008, IEEE Transactions on Robotics.

[17]  Alexandre Bernardino,et al.  Multimodal saliency-based bottom-up attention a framework for the humanoid robot iCub , 2008, 2008 IEEE International Conference on Robotics and Automation.

[18]  K. Prazdny,et al.  Detection of binocular disparities , 2004, Biological Cybernetics.

[19]  Alexander Zelinsky,et al.  A Reactive Vision System: Active-Dynamic Saliency , 2007 .

[20]  Alexandre Bernardino,et al.  A Binocular Stereo Algorithm for Log-Polar Foveated Systems , 2002, Biologically Motivated Computer Vision.