Robot, method, and manipulating system

A method for controlling a robot comprising an image-pickup acquisition unit configured to acquire an image-pickup image of an environmental space including a target object to be grasped, and a manipulator, the method comprising:

• causing the robot to acquire, by the image-pickup acquisition unit, a plurality of image-pickup images of the target object to be grasped while the robot is moved so as to approach the target object to be grasped;
• calculating, for information acquired from the image-pickup images, a plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions by using a learned model, the learned model receiving the information acquired from the image-pickup images and outputting the plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions;
• attempting to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected among the plurality of grasping positions based on a result of the calculation;
• and
• determining whether there are remaining grasping positions on the target object at which an attempt to grasp has not been made,
• wherein the grasping positions are on the target object where the target object is to be grasped.

A manipulating system comprising a manipulator, the manipulating system further comprising:

• an image-pickup acquisition unit configured to acquire an image-pickup image of an environmental space including a target object to be grasped;
• and
• a control unit configured to control a motion performed by the manipulating system, wherein
• the control unit
• causes the manipulating system to acquire, by the image-pickup acquisition unit, a plurality of image-pickup images of the target object to be grasped while it moves the manipulating system so that the manipulating system approaches the target object to be grasped,
• calculates, for information acquired from the image-pickup images, a plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions by using a learned model, the learned model receiving the information acquired from the image-pickup images and outputting the plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions,
• attempts to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected among the plurality of grasping positions based on a result of the calculation, and
• determines whether there are remaining grasping positions on the target object at which an attempt to grasp has not been made,
• wherein the grasping positions are on the target object where the target object is to be grasped.