| CPC B25J 9/1612 (2013.01) [B25J 9/1697 (2013.01); G06T 7/11 (2017.01); G06T 7/80 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/10032 (2013.01)] | 14 Claims |

|
13. A robot control method executed in a robot control apparatus that includes a first camera mounted on a robot, a second camera mounted on a hand of the robot, and circuitry including a CPU, the robot control method comprising:
capturing a first image by the first camera:
capturing a second image by the second camera;
acquiring, by the circuitry, information about an object to be gripped by the hand and target gripping positions, the target gripping positions being specified by a user in the first image as contact points between the hand and the object at which the hand is controlled to grip the object;
generating, by the circuitry, a first camera-based encompassing box that encompasses the object in the first image, and a second camera-based encompassing box that encompasses the object in the second image;
calculating, by the circuitry, first relative positions of the target gripping positions with respect to the first camera-based encompassing box in the first image;
calculating, by the circuitry, second relative positions of the target gripping positions with respect to the second camera-based encompassing box in the second image, based on the first relative positions that were calculated with respect to the first camera-based encompassing box in the first image;
setting, by the circuitry, the second relative positions of the target gripping positions as corrected target gripping positions in the second image; and
generating, by the circuitry, control information for causing the hand of the robot to grip the object at the corrected target gripping positions in the second image.
|