Goal-Oriented Behavior Generation for Visually-Guided Manipulation Task

We propose a new neuro-robotics network architecture that can generate goal-oriented behavior for visually-guided multiple object manipulation task by a humanoid robot. For examples, given a “sequential hit” multiple objects task, the proposed network is able to modulate a humanoid robot's behavior by taking advantage of suitable timing for gazing, approaching and hitting the object and again for the other object. To solve a multiple object manipulation task via learning by examples, the current study considers two important mechanisms: (1) stereo visual attention with depth estimation for movement generation, dynamic neural networks for behavior generation and (2) their adaptive coordination. Stereo visual attention provides a goal-directed shift sequence in a visual scan path, and it can guide the generation of a behavior plan considering depth information for robot movement. The proposed model can simultaneously generate the corresponding sequences of goal-directed visual attention shifts and robot movement timing with regards to the current sensory states including visual stimuli and body postures. The experiments show that the proposed network can solve a multiple object manipulation task through learning, by which some novel behaviors without prior learning can be successfully generated.

[1]  Gunnar Rätsch,et al.  Support Vector Machines and Kernels for Computational Biology , 2008, PLoS Comput. Biol..

[2]  J Saarinen,et al.  Self-Organized Formation of Colour Maps in a Model Cortex , 1985, Perception.

[3]  Minho Lee,et al.  Biologically motivated vergence control system using human-like selective attention model , 2006, Neurocomputing.

[4]  K. Doya,et al.  Memorizing oscillatory patterns in the analog neuron network , 1989, International 1989 Joint Conference on Neural Networks.

[5]  D H Ballard,et al.  Hand-eye coordination during sequential tasks. , 1992, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[6]  Minho Lee,et al.  Developmental learning of integrating visual attention shifts and bimanual object grasping and manipulation tasks , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[7]  R. Johansson,et al.  Eye–Hand Coordination in Object Manipulation , 2001, The Journal of Neuroscience.

[8]  Howard Poizner,et al.  The interaction of visual and proprioceptive inputs in pointing to actual and remembered targets , 2004, Experimental Brain Research.

[9]  Minho Lee,et al.  Stereo saliency map considering affective factors and selective motion analysis in a dynamic environment , 2008, Neural Networks.

[10]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[11]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[12]  Jun Tani,et al.  Development of hierarchical structures for actions and motor imagery: a constructivist view from synthetic neuro-robotics study , 2009, Psychological research.

[13]  Jun Tani,et al.  Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment , 2008, PLoS Comput. Biol..