Peripersonal space and object recognition for humanoids

This work is concerned with a framework for visual object recognition in real world tasks. Our approach is motivated by biological findings of the representation of space around the body, the so-called peripersonal space. We show that the principles behind those findings can lead to a natural structuring of object recognition tasks in artificial systems. We demonstrate this by the supervised learning and recognition of 20 complex-shaped objects from unsegmented visual input

[1]  Antonio A. F. Oliveira,et al.  Towards a framework for robot cognition , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[2]  Ales Ude,et al.  Object recognition on humanoids with poveated vision , 2004, 4th IEEE/RAS International Conference on Humanoid Robots, 2004..

[3]  Gordon Cheng,et al.  Support vector machines and Gabor kernels for object recognition on a humanoid with active foveated vision , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[4]  Heiko Wersing,et al.  Learning Optimized Features for Hierarchical Models of Invariant Object Recognition , 2003, Neural Computation.

[5]  Giulio Sandini,et al.  Learning about objects through action - initial steps towards artificial cognition , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[6]  Inna Mikhailova,et al.  Conditions of activity bubble uniqueness in dynamic neural fields , 2005, Biological Cybernetics.

[7]  F. Ferlazzo,et al.  Functional Representation of 3d Space in Endogenous Attention Shifts , 2003, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[8]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[9]  Bernt Schiele,et al.  Towards Robust Multi-cue Integration for Visual Tracking , 2001, ICVS.

[10]  Dario Floreano,et al.  Active Perception: A Sensorimotor Account of Object Categorization , 2002 .

[11]  Stefan Schaal,et al.  Biomimetic Oculomotor Control , 2001, Adapt. Behav..

[12]  Artur Arsenio.  Object Recognition from Multiple Percepts , 2004 .

[13]  E. Reed.  The Ecological Approach to Visual Perception , 1989 .

[14]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[15]  Michael Gienger,et al.  Task-oriented whole body motion for humanoid robots , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[16]  F. Kaplan,et al.  The challenges of joint attention , 2006 .

[17]  M. Arterberry,et al.  The Cradle of Knowledge: Development of Perception in Infancy , 1998 .

[18]  Kunihiko Fukushima,et al.  Neocognitron: A hierarchical neural network capable of visual pattern recognition , 1988, Neural Networks.

[19]  Antonio A. F. Oliveira,et al.  Tracing Patterns and Attention: Humanoid Robot Cognition , 2000, IEEE Intell. Syst..

[20]  Paul Atchley,et al.  Allocation of Attention in Three-Dimensional Space , 2005 .

[21]  G. Rizzolatti,et al.  The mirror-neuron system. , 2004, Annual review of neuroscience.

[22]  A. Maravita,et al.  Tools for the body (schema) , 2004, Trends in Cognitive Sciences.

[23]  K. Zilles,et al.  Neural consequences of acting in near versus far space: a physiological basis for clinical dissociations. , 2000, Brain : a journal of neurology.