Recently, visual servoing a task object for a slave arm with an eye-in-hand has drawn an interesting attention. In such a task in an unstructured environment, it is difficult to define the optimal feature jacobian matrix which is the differential relationship between robot pose, and image feature change.
To overcome this difficulty, this paper proposes an auto-tuning fuzzy rule-based visual servo algorithm. This algorithm takes a role of feature jacobian matrix based on auto-tuning fuzzy logic. Since the fuzzy rule continually learn the environment around the slave arm, this method can be applied to the unstructured environment in real time.
The effectiveness of the proposed algorithm is verified through a series of simulation and experiment. The results show that through the learning procedure, the slave arm can track a task object in real time.
