Title
Developmental learning of integrating visual attention shifts and bimanual object grasping and manipulation tasks
Abstract
In order to achieve visual-guided object manipulation tasks via learning by example, the current neuro-robotics study considers integration of two essential mechanisms of visual attention and arm/hand movement and their adaptive coordination. The present study proposes a new dynamic neural network model in which visual attention and motor behavior are associated with task specific manners by learning with self-organizing functional hierarchy required for the cognitive tasks. The top-down visual attention provides a goal-directed shift sequence in a visual scan path and it can guide a generation of a motor plan for hand movement during action by reinforcement and inhibition learning. The proposed model can automatically generate the corresponding goal-directed actions with regards to the current sensory states including visual stimuli and body postures. The experiments show that developmental learning from basic actions to combinational ones can achieve certain generalizations in learning by which some novel behaviors without prior learning can be successfully generated.
Year
DOI
Venue
2010
10.1109/DEVLRN.2010.5578849
Development and Learning
Keywords
Field
DocType
learning systems,manipulator dynamics,neural nets,robot vision,adaptive coordination,arm-hand movement,bimanual object grasping,body postures,developmental learning,dynamic neural network model,goal-directed shift sequence,inhibition learning,neurorobotics study,reinforcement learning,self-organizing functional hierarchy,top-down visual attention,visual attention shifts integration,visual scan path,visual stimuli,visual-guided object manipulation tasks,action generator,object manipulation task,shift sequence in visual scan path,generators,self organization,visualization,biology,top down
Visual search,Multi-task learning,Computer science,Visualization,Elementary cognitive task,Artificial intelligence,Artificial neural network,Sensory system,Machine learning,Visual perception,Reinforcement learning
Conference
ISBN
Citations 
PageRank 
978-1-4244-6900-0
4
0.47
References 
Authors
7
4
Name
Order
Citations
PageRank
Sungmoon Jeong19915.05
Minho Lee256575.66
Arie, H.3261.92
Jun Tani41508139.42