Image feature generation by visio-motor map learning towards selective attention

Visual attention is one of the key issues for robots to accomplish the given tasks, and the existing methods specify the image features and attention control scheme in advance according to the task and the robot. However, in order to cope with environmental changes and/or task variations, the robot should construct its own attention mechanism. As the first step towards selective attention, this paper presents a method for image feature generation by visio-motor map learning for a mobile robot. The teaching data construct the visio-motor mapping that constrains the image feature generation and state vector estimation as well. The resultant image feature and state vector are nothing but task-oriented. The method is applied to indoor navigation and soccer shooting tasks, and a discussion is given.

[1]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[2]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[3]  Hiroshi Ishiguro,et al.  State Space Construction by Attention Control , 1999, IJCAI.

[4]  Ben Kröse,et al.  Learning task-relevant features from robot data , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[5]  Takayuki Nakamura,et al.  Development of self-learning vision-based mobile robots for acquiring soccer robots behaviors , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[6]  PIERRE VAN DE LAAR,et al.  Task-Dependent Learning of Attention , 1997, Neural Networks.

[7]  Ben J. A. Kröse,et al.  Probabilistic localization by appearance models and active vision , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[8]  Noboru Ohnishi,et al.  Active vision system based on information theory , 1998, Systems and Computers in Japan.

[9]  Susan L. Franzel,et al.  Guided search: an alternative to the feature integration model for visual search. , 1989, Journal of experimental psychology. Human perception and performance.

[10]  D. J. Felleman,et al.  Distributed hierarchical processing in the primate cerebral cortex. , 1991, Cerebral cortex.

[11]  Frank P. Ferrie,et al.  Viewpoint selection by navigation through entropy maps , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.