Abstract
A vision-based object tracking algorithm is proposed for a robot manipulator with stereo cameras, where the fuzzy rule-based systems(FRBS) are employed to represent the mapping from image features for the end position of the robot and the target to joint angle space variables for each angle of the robot. For the rule extraction of this FRBS, Wang & Mendel's rule extraction method is used in such a way that the initial rule table is built up with irregularly generated input-output pairs in a certain work space and updated every vision sampling time with newly generated input-output pair corresponding to the end position of the robot during operation. Once the rules are made up, estimated reference joint angles can be obtained using FRBS where image coordinates of the target object are applied as input variables, and then PD control scheme can be used to generate control inputs to move the robot. To show the validity of the proposed algorithm, some computer simulations are illustrated with the mathematical model of PUMA 560 and a few experiments are achieved on a real commercial manipulator, Movemaster, respectively.
| Original language | English |
|---|---|
| Pages | II-674 - II-678 |
| State | Published - 1999 |
| Event | Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99 - Seoul, South Korea Duration: 22 Aug 1999 → 25 Aug 1999 |
Conference
| Conference | Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99 |
|---|---|
| City | Seoul, South Korea |
| Period | 22/08/99 → 25/08/99 |