关键词: 多传感器, 信息融合, 工件识别, 区间数

Abstract: A new method was proposed for the target recognition problem of robot non-vision multi-sensors. The method applies the theory of interval multiple attribute decision making and obtains the weight vector of attributes by solving the optimal programming of minimizing the maximum deviation of comprehensive incidence degrees between the object types and the unknown part. The result of recognition for the unknown object is given by the comprehensive correlation degree. It can avoid the subjectivity of selecting attributes weights and improve the objectivity of target recognition. It is straightforward and can be performed on computer easily. Finally, a simulated example is given to demonstrate the feasibility and practicability of the proposed method.

Key words: multi-sensor, information fusion, parts recognition, interval number