Design of a force reflection controller for telerobot systems using neural network and fuzzy logic

This paper presents a new method for selecting the force-reflection gain in a position-force type bilateral teleoperation system. The force-reflection gain greatly affects the task performance of a teleoperation system; too small gain results in poor task performance while too large gain results in system instability. The maximum boundary of the gain guaranteeing the stability greatly depends upon characteristics of the elements in the system such as: a master arm which is combined with the human operator's hand and the environments with which the slave arm contacts. In normal practice, it is, therefore, very difficult to determine such maximum boundary of the gain. To overcome this difficulty, this paper proposes a force-reflection gain selecting algorithm based on artificial neural network and fuzzy logic. The method estimates characteristics of the master arm and the environments by using neural networks and, then, determines the force-reflection gain from the estimated characteristics by using fuzzy logic. In order to show the effectiveness of the proposed algorithm, a series of experiments are conducted under various conditions of teleoperation using a laboratory-made telerobot system.