In vision-guided robotic operations, vision is used for extracting necessary information for achieving the task. Since visual recognition is usually performed with limited resources, visual sensing strategies should be planned so that only necessary information is obtained eciently. This paper describes a method of generating visual sensing strategies for assembly tasks based on knowledge of the task to be performed. The generation of the appropriate visual sensing strategy entails knowing what

more »

... information to extract, where to get it and how to get it. This is facilitated by the knowledge of the task, which describes what objects are involved in the operation, and how they are assembled. In the proposed method, using the task analysis based on face contact relations between objects, necessary information for the current operation is rst extracted. Then, visual features to be observed are determined using the knowledge of the sensor, which describes the relationship between a visual feature and information to be obtained. Finally, feasible sensing strategies are evaluated based on the predicted success probability, and the best one is selected. Our method has been implemented using a laser range nder as the sensor. Experimental results show the feasibility of the method, and point out the importance of task-oriented evaluation of sensing strategies. 3 2 [4][5] [6][7] 3 ( )