Title :
Sensor data fusion using perception net for a precise assembly task
Author :
Choi, Jae Weon ; Fang, Tae Hyun ; Yoo, Wan-Suk ; Lee, Man Hyung
Author_Institution :
Sch. of Mech. Eng., Pusan Nat. Univ., South Korea
Abstract :
A sensor fusion method is presented for a peg-in-hole insertion task. Three kinds of sensor are fused for task execution. The vision and proximity sensors are mainly used for gross motion control, and the force/torque sensor is used for fine motion control of the robot. Covariance analysis is conducted for each sensor discussed in this paper, and the perception net is introduced to improve the usefulness of each sensor by optimally weighting its output.
Keywords :
covariance analysis; image sensors; industrial manipulators; motion control; robotic assembly; sensor fusion; covariance analysis; fine motion control; force sensor; gross motion control; peg-in-hole insertion task; perception net; precise assembly task; proximity sensors; sensor data fusion; task execution; torque sensor; vision sensors; Assembly; Manipulators; Mechanical sensors; Pi control; Proportional control; Robot control; Robot sensing systems; Sensor fusion; Sensor systems; Tactile sensors;
Journal_Title :
Mechatronics, IEEE/ASME Transactions on
DOI :
10.1109/TMECH.2003.820020
