| 摘要 |
To make it possible to teach a grasping action for a work object whose shape and 3D position are unknown to a robot by an intuitive and simple input operation by an operator. (a) a picked-up image of the working space is displayed on a display device 21, and (b) an operation in which a recognition area including a part of a work object 90 to be grasped by a hand 11 is specified in two dimensions on an image of the work object 90 displayed on the display device 21 is received. (c) an operation in which a prime shape model to be applied to the part to be grasped is specified from among a plurality of prime shape models, and (d) a parameter group to specify the shape, position, and posture of the prime shape model is determined by fitting the specified prime shape model onto 3D position data of a space corresponding to the recognition area. (e) a grasping pattern applicable to grasping of the work object 90 is selected by searching a database 15 in which grasping patterns applicable by a hand 11 to prime shape models are stored. |
