抄録
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. This paper presents a method for image feature and state space construction by visio-motor learning for a mobile robot towards visual attention. The learning model which consists of the image feature generation and state vector estimation is suggested by a visual cortex architecture. The teaching data constructs the visio-motor mapping that constrains the image feature and state space construction as well. The method is applied to indoor navigation and soccer shooting tasks, and discussion is given.
