Title :
A prediction method considering object motion for humanoid robot with visual sensor
Author :
Baba, Ken-ichi ; Kawamura, Atsuo ; Motoi, N. ; Asano, Yuji
Author_Institution :
Dept. of Electr. & Comput. Eng., Yokohama Nat. Univ., Yokohama, Japan
Abstract :
This paper proposes a prediction method considering object motion for a humanoid robot with a visual sensor. A visual servo control method is one of the useful methods to control the robot based on visual information. Robot can track the movable object by using this method. However, this system does not consider the future response of the object motion. As a result, the delay arises. In order to solve this problem, it is necessary to predict the object motion from the visual information. This paper proposes the prediction method considering object motion based on visual servo system. By using this method, the robot predicts the goal position which is the stop position of the movable object. Thereafter, the robot walks to the above prediction position. The robot moves to goal position without useless trajectory. The experiments with this prediction control method are conducted to confirm the validity of the proposed method. From these results, the validity of the proposed method is confirmed.
Keywords :
humanoid robots; image sensors; motion estimation; position control; robot vision; goal position; humanoid robot; object motion; prediction method; robot vision; stop position; visual information; visual sensor; visual servo control method; visual servo system; Equations; Head; Robot kinematics; Robot sensing systems; Servosystems; Visualization;
Conference_Titel :
Advanced Motion Control (AMC),2014 IEEE 13th International Workshop on
Conference_Location :
Yokohama
DOI :
10.1109/AMC.2014.6823302