Artificial neural networks for spatial perception: Towards visual object localisation in humanoid robots

In this paper, we present our on-going research to allow humanoid robots to learn spatial perception. We are using artificial neural networks (ANN) to estimate the location of objects in the robot's environment. The method is using only the visual inputs and the joint encoder readings, no camera calibration and information is necessary, nor is a kinematic model. We find that these ANNs can be trained to allow spatial perception in Cartesian (3D) coordinates. These lightweight networks are providing estimates that are comparable to current state of the art approaches and can easily be used together with existing operational space controllers.

[1]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[2]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[3]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[4]  Anne R. Schutte,et al.  Testing the dynamic field theory: working memory for locations becomes more spatially precise over development. , 2003, Child development.

[5]  Aude Billard,et al.  View Sensitive Cells as a Neural Basis for the Representation of Others in a Self-Centered Frame of Reference , 2005 .

[6]  Alexander Gloye,et al.  Reinforcing the Driving Quality of Soccer Playing Robots by Anticipation (Verbesserung der Fahreigenschaften von fußballspielenden Robotern durch Antizipation) , 2005, it Inf. Technol..

[7]  Hod Lipson,et al.  Resilient Machines Through Continuous Self-Modeling , 2006, Science.

[8]  J. Spencer,et al.  The Emerging Spatial Mind , 2007 .

[9]  Nikolaos G. Tsagarakis,et al.  iCub: the design and realization of an open humanoid platform for cognitive and neuroscience research , 2007, Adv. Robotics.

[10]  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.

[11]  Patricia Shaw,et al.  Development of eye-head gaze control on the iCub robot , 2012 .

[12]  Jürgen Leitner,et al.  icVision: A modular vision system for cognitive robotics research , 2012 .

[13]  Mikhail Frank,et al.  Towards Spatial Perception: Learning to Locate Objects From Vision , 2012 .

[14]  Jürgen Leitner,et al.  Transferring spatial perception between robots operating in a shared workspace , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Jürgen Leitner,et al.  The Modular Behavioral Environment for Humanoids and other Robots (MoBeE) , 2012, ICINCO.

[16]  Vinícius Gonçalves Maltarollo,et al.  Applications of Artificial Neural Networks in Chemical Problems , 2013 .