Multi criteria robot control based on fuzzy behavioral algorithms

In this paper a three-layered control scheme for the incorporation of linguistically formulated control strategies into a robot controller is discussed. Based upon the behavioral decomposition of activities, the controller consists of parallel working layers with possibly conflicting behaviors. Each layer is encoded as a fuzzy algorithm. The first layer of the controller contains a recently introduced fuzzy algorithm for the solution of the inverse kinematics for redundant robots. This algorithm is demonstrated on a three-link planar manipulator. The kinematic redundancy of the system is used for local collision avoidance and joint limit avoidance. Instead of optimizing each layer independently, we are interested in a good overall behavior of the controller.