A cognitive robot architecture based on tactile and visual information

In this paper, we propose an architecture for a cognitive robot based on tactile and visual information. Visual information contains various features such as location and area of each colored region. Most of these features are irrelevant for object recognition to achieve the given task. In the architecture, tactile information plays a key role in selection of visual features and discritization of selected features. In order to find appropriate visual features we use correlation coefficient between values of features and action series. Then ChiMerge algorithm is employed to discritize the value of the selected feature into a small number of intervals. Consequently, quantization of a state space for accomplishing the given task is achieved. By using this state space to reinforcement learning algorithm, an appropriate behavior to the given task is acquired. To show validity of our method, we show an experimental result of computer simulation. Key words: Cognitive Robot, Vision, Tactile...

• Type: Journal
• Year: 1998
• Where: AR
• Authors: Kazunori Terada, Takayuki Nakamura, Hideaki Takeda, Toyoaki Nishida
• Keywords: AR 1998, Cognitive Robot, Visual Features, Visual Information