LEARNING-METHOD FOR MULTI-CONTROLLER OF ROBOT BEHAVIOR

In this paper, we propose a hierarchical behavior controller and a lea rning algorithm for the behavior controller which consists of several subcontrollers to indicate the desired trajectories for robot actuator s. This algorithm selects the subcontroller which is not appropriate a nd needs to be tuned, by evaluating each subcontroller using multiple regression analysis based on previously obtained evaluation values. Th is process can reduce the learning iterations by avoiding attempts to tune good subcontrollers. The proposed algorithm is applied to the pro blem of selecting and tuning subcontrollers at the middle layer in the hierarchical behavior controller in order to compensate imperfect ini tial controllers. The hierarchical behavior controller is applied to t he problem of controlling a seven-link brachiation robot, that moves d ynamically from branch to branch like a gibbon, a long-armed ape, swin ging its body like a pendulum.