CPC B25J 9/161 (2013.01) [B25J 9/1697 (2013.01); B25J 19/023 (2013.01); G06N 3/08 (2013.01)] | 20 Claims |
1. A computer-implemented action imitation method for a robot, comprising steps of:
collecting a plurality of action images of a to-be-imitated object;
processing the action images through a pre-trained convolutional neural network to obtain a position coordinate set of position coordinates of a plurality of key points of each of the action images, wherein two adjacent ones of the key points are connected to form a plurality of linkages;
calculating a rotational angle of each of the linkages of the to-be-imitated object based on the position coordinate sets of the action images; and
controlling the robot to move according to the rotational angle of each of the linkages of the to-be-imitated object;
wherein the step of calculating the rotational angle of each of the linkages of the to-be-imitated object based on the position coordinate sets of the action images comprises:
calculating a length of each of the linkages of the to-be-imitated object based on the position coordinate set; and
calculating the rotational angle of each of the linkages of the to-be-imitated object based on the length of each of the linkages of the to-be-imitated object and a preset maximum length of each of the linkages of the to-be-imitated object.
|