Abstract
This paper proposes a cooperative visual object tracking by a multi-robot system, where robust cognitive sharing is essential between robots. Robots identify the object of interest by using various types of information in the image recognition field. However, the most effective type of information for recognizing an object accurately is the difference between the object and its surrounding environment. Therefore we propose two evaluation parameters, called ambiguity and stationarity, in order to select the best information. Although robots select the best feature to recognize, if there are some objects that have the same information as the object of interest, robots can not discern the difference. To solve this problem, robots share the relation between the landmarks and the object of interest. Thus we propose a method to generate landmark information autonomously. The experimental results are promising with regard to effective multi-robot cognitive sharing.
